{ "schemaVersion": 2, "generatedAt": "2026-06-20T07:13:41.379Z", "generatedBy": "scripts/generate-models-json.mjs", "sources": [ { "id": "litellm", "name": "LiteLLM model prices and context window", "url": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json" }, { "id": "models.dev", "name": "models.dev API", "url": "https://models.dev/api.json" }, { "id": "openrouter", "name": "OpenRouter models API", "url": "https://openrouter.ai/api/v1/models" } ], "summary": { "modelCount": 3619, "rawProviderModelCount": 7748, "duplicateProviderModelRecordsMerged": 4129, "providerCount": 166, "availabilityProviderCount": 236, "sourceCounts": { "models.dev": 2308, "litellm": 1829, "openrouter": 340 }, "pricingOfferCount": 8033, "modelsWithPricing": 3428, "modelsWithoutPricing": 191, "modelsWith1MContext": 467, "modelsWithImageInput": 1283, "modelsWithImageOutput": 168, "modelsWithAudioInput": 224, "modelsWithToolCalling": 2097, "modelsWithReasoning": 1415 }, "models": [ { "id": "302ai/doubao-seed-1-6-thinking-250715", "provider": "302ai", "model": "doubao-seed-1-6-thinking-250715", "displayName": "doubao-seed-1-6-thinking-250715", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/doubao-seed-1-6-thinking-250715" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "doubao-seed-1-6-thinking-250715", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.121, "output": 1.21 } } ] }, "metadata": { "displayNames": [ "doubao-seed-1-6-thinking-250715" ], "releaseDate": "2025-07-15", "lastUpdated": "2025-07-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "doubao-seed-1-6-thinking-250715", "modelKey": "doubao-seed-1-6-thinking-250715", "displayName": "doubao-seed-1-6-thinking-250715", "metadata": { "lastUpdated": "2025-07-15", "openWeights": false, "releaseDate": "2025-07-15" } } ] }, { "id": "302ai/doubao-seed-1-6-vision-250815", "provider": "302ai", "model": "doubao-seed-1-6-vision-250815", "displayName": "doubao-seed-1-6-vision-250815", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/doubao-seed-1-6-vision-250815" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "doubao-seed-1-6-vision-250815", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.114, "output": 1.143 } } ] }, "metadata": { "displayNames": [ "doubao-seed-1-6-vision-250815" ], "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "doubao-seed-1-6-vision-250815", "modelKey": "doubao-seed-1-6-vision-250815", "displayName": "doubao-seed-1-6-vision-250815", "metadata": { "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } } ] }, { "id": "302ai/doubao-seed-1-8-251215", "provider": "302ai", "model": "doubao-seed-1-8-251215", "displayName": "doubao-seed-1-8-251215", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/doubao-seed-1-8-251215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 224000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "doubao-seed-1-8-251215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.114, "output": 0.286 } } ] }, "metadata": { "displayNames": [ "doubao-seed-1-8-251215" ], "releaseDate": "2025-12-18", "lastUpdated": "2025-12-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "doubao-seed-1-8-251215", "modelKey": "doubao-seed-1-8-251215", "displayName": "doubao-seed-1-8-251215", "metadata": { "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18" } } ] }, { "id": "302ai/doubao-seed-code-preview-251028", "provider": "302ai", "model": "doubao-seed-code-preview-251028", "displayName": "doubao-seed-code-preview-251028", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/doubao-seed-code-preview-251028" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "doubao-seed-code-preview-251028", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 1.14 } } ] }, "metadata": { "displayNames": [ "doubao-seed-code-preview-251028" ], "releaseDate": "2025-11-11", "lastUpdated": "2025-11-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "doubao-seed-code-preview-251028", "modelKey": "doubao-seed-code-preview-251028", "displayName": "doubao-seed-code-preview-251028", "metadata": { "lastUpdated": "2025-11-11", "openWeights": false, "releaseDate": "2025-11-11" } } ] }, { "id": "abacus/o3", "provider": "abacus", "model": "o3", "displayName": "o3", "family": "o", "sources": [ "models.dev" ], "providers": [ "abacus" ], "aliases": [ "abacus/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "o3" ], "families": [ "o" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "o3", "modelKey": "o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } } ] }, { "id": "abacus/route-llm", "provider": "abacus", "model": "route-llm", "displayName": "Route LLM", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "abacus" ], "aliases": [ "abacus/route-llm" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "route-llm", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Route LLM" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "route-llm", "modelKey": "route-llm", "displayName": "Route LLM", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "abliteration-ai/abliterated-model", "provider": "abliteration-ai", "model": "abliterated-model", "displayName": "Abliterated Model", "sources": [ "models.dev" ], "providers": [ "abliteration-ai" ], "aliases": [ "abliteration-ai/abliterated-model" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 150000, "inputTokens": 150000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abliteration-ai", "model": "abliterated-model", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "displayNames": [ "Abliterated Model" ], "releaseDate": "2026-01-06", "lastUpdated": "2026-01-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abliteration-ai", "providerName": "abliteration.ai", "providerApi": "https://api.abliteration.ai/v1", "providerDoc": "https://docs.abliteration.ai/models", "model": "abliterated-model", "modelKey": "abliterated-model", "displayName": "Abliterated Model", "metadata": { "lastUpdated": "2026-01-06", "openWeights": true, "releaseDate": "2026-01-06" } } ] }, { "id": "ai21/j2-light", "provider": "ai21", "model": "j2-light", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/j2-light" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "j2-light", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "j2-light", "mode": "completion" } ] }, { "id": "ai21/j2-mid", "provider": "ai21", "model": "j2-mid", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/j2-mid" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "j2-mid", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 10 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "j2-mid", "mode": "completion" } ] }, { "id": "ai21/j2-ultra", "provider": "ai21", "model": "j2-ultra", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/j2-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "j2-ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 15 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "j2-ultra", "mode": "completion" } ] }, { "id": "ai21/jamba-1.5", "provider": "ai21", "model": "jamba-1.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-1.5", "mode": "chat" } ] }, { "id": "ai21/jamba-1.5-large", "provider": "ai21", "model": "jamba-1.5-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-1.5-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-1.5-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-1.5-large", "mode": "chat" } ] }, { "id": "ai21/jamba-1.5-large@001", "provider": "ai21", "model": "jamba-1.5-large@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-1.5-large@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-1.5-large@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-1.5-large@001", "mode": "chat" } ] }, { "id": "ai21/jamba-1.5-mini", "provider": "ai21", "model": "jamba-1.5-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-1.5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-1.5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-1.5-mini", "mode": "chat" } ] }, { "id": "ai21/jamba-1.5-mini@001", "provider": "ai21", "model": "jamba-1.5-mini@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-1.5-mini@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-1.5-mini@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-1.5-mini@001", "mode": "chat" } ] }, { "id": "ai21/jamba-large-1.6", "provider": "ai21", "model": "jamba-large-1.6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-large-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-large-1.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-large-1.6", "mode": "chat" } ] }, { "id": "ai21/jamba-large-1.7", "provider": "ai21", "model": "jamba-large-1.7", "displayName": "AI21: Jamba Large 1.7", "family": "jamba", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "ai21", "kilo", "openrouter" ], "aliases": [ "ai21/jamba-large-1.7", "kilo/ai21/jamba-large-1.7", "openrouter/ai21/jamba-large-1.7" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "ai21/jamba-large-1.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openrouter", "model": "ai21/jamba-large-1.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "litellm", "provider": "ai21", "model": "jamba-large-1.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "openrouter", "provider": "openrouter", "model": "ai21/jamba-large-1.7", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "AI21: Jamba Large 1.7", "Jamba Large 1.7" ], "families": [ "jamba" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-08-09", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "response_format", "stop", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "ai21/jamba-large-1.7", "modelKey": "ai21/jamba-large-1.7", "displayName": "AI21: Jamba Large 1.7", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "ai21/jamba-large-1.7", "modelKey": "ai21/jamba-large-1.7", "displayName": "Jamba Large 1.7", "family": "jamba", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-08-08", "openWeights": true, "releaseDate": "2025-08-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-large-1.7", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "ai21/jamba-large-1.7", "displayName": "AI21: Jamba Large 1.7", "metadata": { "canonicalSlug": "ai21/jamba-large-1.7", "createdAt": "2025-08-08T16:03:40.000Z", "huggingFaceId": "ai21labs/AI21-Jamba-Large-1.7", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/ai21/jamba-large-1.7/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "stop", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 4096, "is_moderated": false } } } ] }, { "id": "ai21/jamba-mini-1.6", "provider": "ai21", "model": "jamba-mini-1.6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-mini-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-mini-1.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-mini-1.6", "mode": "chat" } ] }, { "id": "ai21/jamba-mini-1.7", "provider": "ai21", "model": "jamba-mini-1.7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ai21" ], "aliases": [ "ai21/jamba-mini-1.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ai21", "model": "jamba-mini-1.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ai21", "model": "jamba-mini-1.7", "mode": "chat" } ] }, { "id": "aihubmix/alicloud-deepseek-v4-flash", "provider": "aihubmix", "model": "alicloud-deepseek-v4-flash", "displayName": "DeepSeek V4 Flash (Alibaba Cloud)", "family": "deepseek-flash", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/alicloud-deepseek-v4-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "alicloud-deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash (Alibaba Cloud)" ], "families": [ "deepseek-flash" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "alicloud-deepseek-v4-flash", "modelKey": "alicloud-deepseek-v4-flash", "displayName": "DeepSeek V4 Flash (Alibaba Cloud)", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "aihubmix/alicloud-deepseek-v4-pro", "provider": "aihubmix", "model": "alicloud-deepseek-v4-pro", "displayName": "DeepSeek V4 Pro (Alibaba Cloud)", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/alicloud-deepseek-v4-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "alicloud-deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.69, "output": 3.38 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro (Alibaba Cloud)" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "alicloud-deepseek-v4-pro", "modelKey": "alicloud-deepseek-v4-pro", "displayName": "DeepSeek V4 Pro (Alibaba Cloud)", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "aihubmix/alicloud-glm-5.1", "provider": "aihubmix", "model": "alicloud-glm-5.1", "displayName": "GLM-5.1 (Alibaba Cloud)", "family": "glm", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/alicloud-glm-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "alicloud-glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.169, "cacheWrite": 1.05625, "input": 0.84, "output": 3.38 } } ] }, "metadata": { "displayNames": [ "GLM-5.1 (Alibaba Cloud)" ], "families": [ "glm" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "alicloud-glm-5.1", "modelKey": "alicloud-glm-5.1", "displayName": "GLM-5.1 (Alibaba Cloud)", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27" } } ] }, { "id": "aihubmix/coding-glm-5.1", "provider": "aihubmix", "model": "coding-glm-5.1", "displayName": "Coding GLM 5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-glm-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.013, "input": 0.06, "output": 0.22 } } ] }, "metadata": { "displayNames": [ "Coding GLM 5.1" ], "families": [ "glm" ], "releaseDate": "2026-04-11", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-glm-5.1", "modelKey": "coding-glm-5.1", "displayName": "Coding GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-11" } } ] }, { "id": "aihubmix/coding-glm-5.1-free", "provider": "aihubmix", "model": "coding-glm-5.1-free", "displayName": "Coding GLM 5.1 (free)", "family": "glm-free", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-glm-5.1-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-glm-5.1-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Coding GLM 5.1 (free)" ], "families": [ "glm-free" ], "releaseDate": "2026-04-11", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-glm-5.1-free", "modelKey": "coding-glm-5.1-free", "displayName": "Coding GLM 5.1 (free)", "family": "glm-free", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-11" } } ] }, { "id": "aihubmix/coding-minimax-m2.7", "provider": "aihubmix", "model": "coding-minimax-m2.7", "displayName": "Coding MiniMax M2.7", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-minimax-m2.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 128100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Coding MiniMax M2.7" ], "families": [ "minimax" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-minimax-m2.7", "modelKey": "coding-minimax-m2.7", "displayName": "Coding MiniMax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "aihubmix/coding-minimax-m2.7-free", "provider": "aihubmix", "model": "coding-minimax-m2.7-free", "displayName": "Coding MiniMax M2.7 (Free)", "family": "minimax-free", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-minimax-m2.7-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 128100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-minimax-m2.7-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Coding MiniMax M2.7 (Free)" ], "families": [ "minimax-free" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-minimax-m2.7-free", "modelKey": "coding-minimax-m2.7-free", "displayName": "Coding MiniMax M2.7 (Free)", "family": "minimax-free", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "aihubmix/coding-minimax-m2.7-highspeed", "provider": "aihubmix", "model": "coding-minimax-m2.7-highspeed", "displayName": "Coding MiniMax M2.7 Highspeed", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-minimax-m2.7-highspeed" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 128100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Coding MiniMax M2.7 Highspeed" ], "families": [ "minimax" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-minimax-m2.7-highspeed", "modelKey": "coding-minimax-m2.7-highspeed", "displayName": "Coding MiniMax M2.7 Highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "aihubmix/coding-xiaomi-mimo-v2.5", "provider": "aihubmix", "model": "coding-xiaomi-mimo-v2.5", "displayName": "Coding Xiaomi MiMo-V2.5", "family": "mimo-v2.5", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-xiaomi-mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-xiaomi-mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.016, "input": 0.08, "output": 0.4 }, "tiered": { "contextOver200K": { "input": 0.16, "output": 0.8, "cache_read": 0.032 }, "tiers": [ { "input": 0.16, "output": 0.8, "cache_read": 0.032, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Coding Xiaomi MiMo-V2.5" ], "families": [ "mimo-v2.5" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-xiaomi-mimo-v2.5", "modelKey": "coding-xiaomi-mimo-v2.5", "displayName": "Coding Xiaomi MiMo-V2.5", "family": "mimo-v2.5", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/coding-xiaomi-mimo-v2.5-pro", "provider": "aihubmix", "model": "coding-xiaomi-mimo-v2.5-pro", "displayName": "Coding Xiaomi MiMo-V2.5-Pro", "family": "mimo-v2.5-pro", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/coding-xiaomi-mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "coding-xiaomi-mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 0.6 }, "tiered": { "contextOver200K": { "input": 0.4, "output": 1.2, "cache_read": 0.08 }, "tiers": [ { "input": 0.4, "output": 1.2, "cache_read": 0.08, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Coding Xiaomi MiMo-V2.5-Pro" ], "families": [ "mimo-v2.5-pro" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "coding-xiaomi-mimo-v2.5-pro", "modelKey": "coding-xiaomi-mimo-v2.5-pro", "displayName": "Coding Xiaomi MiMo-V2.5-Pro", "family": "mimo-v2.5-pro", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/deep-deepseek-v4-flash", "provider": "aihubmix", "model": "deep-deepseek-v4-flash", "displayName": "DeepSeek V4 Flash (DeepSeek)", "family": "deepseek-flash", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/deep-deepseek-v4-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "deep-deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0308, "input": 0.154, "output": 0.308 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash (DeepSeek)" ], "families": [ "deepseek-flash" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "deep-deepseek-v4-flash", "modelKey": "deep-deepseek-v4-flash", "displayName": "DeepSeek V4 Flash (DeepSeek)", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "aihubmix/deep-deepseek-v4-pro", "provider": "aihubmix", "model": "deep-deepseek-v4-pro", "displayName": "DeepSeek V4 Pro (DeepSeek)", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/deep-deepseek-v4-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "deep-deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.004302, "input": 0.478, "output": 0.956 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro (DeepSeek)" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "deep-deepseek-v4-pro", "modelKey": "deep-deepseek-v4-pro", "displayName": "DeepSeek V4 Pro (DeepSeek)", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "aihubmix/doubao-seed-2-0-code-preview", "provider": "aihubmix", "model": "doubao-seed-2-0-code-preview", "displayName": "Doubao Seed 2.0 Code Preview", "family": "seed", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/doubao-seed-2-0-code-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "doubao-seed-2-0-code-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09644, "input": 0.48, "output": 2.41 }, "tiered": { "tiers": [ { "input": 0.72, "output": 3.62, "cache_read": 0.144656, "tier": { "size": 32000 } }, { "input": 1.45, "output": 7.23, "cache_read": 0.28932, "tier": { "size": 128000 } } ] } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Code Preview" ], "families": [ "seed" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "doubao-seed-2-0-code-preview", "modelKey": "doubao-seed-2-0-code-preview", "displayName": "Doubao Seed 2.0 Code Preview", "family": "seed", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "aihubmix/doubao-seed-2-0-lite-260428", "provider": "aihubmix", "model": "doubao-seed-2-0-lite-260428", "displayName": "Doubao Seed 2.0 Lite 260428", "family": "seed", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/doubao-seed-2-0-lite-260428" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "doubao-seed-2-0-lite-260428", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01692, "input": 0.08, "inputAudio": 1.269, "output": 0.51 }, "tiered": { "tiers": [ { "input": 0.13, "output": 0.76, "cache_read": 0.02536, "input_audio": 1.902, "tier": { "size": 32000 } }, { "input": 0.25, "output": 1.52, "cache_read": 0.05072, "input_audio": 3.804, "tier": { "size": 128000 } } ] } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Lite 260428" ], "families": [ "seed" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "doubao-seed-2-0-lite-260428", "modelKey": "doubao-seed-2-0-lite-260428", "displayName": "Doubao Seed 2.0 Lite 260428", "family": "seed", "metadata": { "lastUpdated": "2026-04-28", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "aihubmix/doubao-seed-2-0-mini-260428", "provider": "aihubmix", "model": "doubao-seed-2-0-mini-260428", "displayName": "Doubao Seed 2.0 Mini 260428", "family": "seed", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/doubao-seed-2-0-mini-260428" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "doubao-seed-2-0-mini-260428", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.00564, "input": 0.03, "inputAudio": 0.423, "output": 0.28 }, "tiered": { "tiers": [ { "input": 0.06, "output": 0.56, "cache_read": 0.01128, "input_audio": 0.846, "tier": { "size": 32000 } }, { "input": 0.11, "output": 1.13, "cache_read": 0.02256, "input_audio": 1.692, "tier": { "size": 128000 } } ] } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Mini 260428" ], "families": [ "seed" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "doubao-seed-2-0-mini-260428", "modelKey": "doubao-seed-2-0-mini-260428", "displayName": "Doubao Seed 2.0 Mini 260428", "family": "seed", "metadata": { "lastUpdated": "2026-04-28", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "aihubmix/doubao-seed-2-0-pro", "provider": "aihubmix", "model": "doubao-seed-2-0-pro", "displayName": "Doubao Seed 2.0 Pro", "family": "seed", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/doubao-seed-2-0-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "doubao-seed-2-0-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09644, "input": 0.48, "output": 2.41 }, "tiered": { "tiers": [ { "input": 0.72, "output": 3.62, "cache_read": 0.144656, "tier": { "size": 32000 } }, { "input": 1.45, "output": 7.23, "cache_read": 0.28932, "tier": { "size": 128000 } } ] } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Pro" ], "families": [ "seed" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "doubao-seed-2-0-pro", "modelKey": "doubao-seed-2-0-pro", "displayName": "Doubao Seed 2.0 Pro", "family": "seed", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "aihubmix/xiaomi-mimo-v2.5", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5", "displayName": "Xiaomi MiMo-V2.5", "family": "mimo-v2.5", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/xiaomi-mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.088, "input": 0.44, "output": 2.2 }, "tiered": { "contextOver200K": { "input": 0.88, "output": 4.4, "cache_read": 0.176 }, "tiers": [ { "input": 0.88, "output": 4.4, "cache_read": 0.176, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Xiaomi MiMo-V2.5" ], "families": [ "mimo-v2.5" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "xiaomi-mimo-v2.5", "modelKey": "xiaomi-mimo-v2.5", "displayName": "Xiaomi MiMo-V2.5", "family": "mimo-v2.5", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/xiaomi-mimo-v2.5-free", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-free", "displayName": "Xiaomi MiMo-V2.5 (free)", "family": "mimo-v2.5", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/xiaomi-mimo-v2.5-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Xiaomi MiMo-V2.5 (free)" ], "families": [ "mimo-v2.5" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "xiaomi-mimo-v2.5-free", "modelKey": "xiaomi-mimo-v2.5-free", "displayName": "Xiaomi MiMo-V2.5 (free)", "family": "mimo-v2.5", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/xiaomi-mimo-v2.5-pro", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-pro", "displayName": "Xiaomi MiMo-V2.5-Pro", "family": "mimo-v2.5-pro", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/xiaomi-mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 1.1, "output": 3.3 }, "tiered": { "contextOver200K": { "input": 2.2, "output": 6.6, "cache_read": 0.44 }, "tiers": [ { "input": 2.2, "output": 6.6, "cache_read": 0.44, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Xiaomi MiMo-V2.5-Pro" ], "families": [ "mimo-v2.5-pro" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "xiaomi-mimo-v2.5-pro", "modelKey": "xiaomi-mimo-v2.5-pro", "displayName": "Xiaomi MiMo-V2.5-Pro", "family": "mimo-v2.5-pro", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/xiaomi-mimo-v2.5-pro-free", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-pro-free", "displayName": "Xiaomi MiMo-V2.5-Pro (free)", "family": "mimo-v2.5-pro", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/xiaomi-mimo-v2.5-pro-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "xiaomi-mimo-v2.5-pro-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Xiaomi MiMo-V2.5-Pro (free)" ], "families": [ "mimo-v2.5-pro" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "xiaomi-mimo-v2.5-pro-free", "modelKey": "xiaomi-mimo-v2.5-pro-free", "displayName": "Xiaomi MiMo-V2.5-Pro (free)", "family": "mimo-v2.5-pro", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-13", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "aihubmix/zai-glm-5.1", "provider": "aihubmix", "model": "zai-glm-5.1", "displayName": "GLM-5.1 (Z.ai)", "family": "glm", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/zai-glm-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "zai-glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.183112, "input": 0.845, "output": 3.38 } } ] }, "metadata": { "displayNames": [ "GLM-5.1 (Z.ai)" ], "families": [ "glm" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "zai-glm-5.1", "modelKey": "zai-glm-5.1", "displayName": "GLM-5.1 (Z.ai)", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27" } } ] }, { "id": "aiml/dev", "provider": "aiml", "model": "dev", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux/dev" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux/dev", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.033 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux/dev", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/flux-pro", "provider": "aiml", "model": "flux-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.065 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux-pro", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/flux-realism", "provider": "aiml", "model": "flux-realism", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux-realism" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux-realism", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.046 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux-realism", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Pro - Professional-grade image generation model" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/schnell", "provider": "aiml", "model": "schnell", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux/schnell" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux/schnell", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.004 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux/schnell", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Schnell - Fast generation model optimized for speed" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/text-to-image", "provider": "aiml", "model": "text-to-image", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux/kontext-max/text-to-image", "aiml/flux/kontext-pro/text-to-image" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux/kontext-max/text-to-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.104 } }, { "source": "litellm", "provider": "aiml", "model": "aiml/flux/kontext-pro/text-to-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.052 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux/kontext-max/text-to-image", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux/kontext-pro/text-to-image", "mode": "image_generation", "metadata": { "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/v1.1", "provider": "aiml", "model": "v1.1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux-pro/v1.1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux-pro/v1.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.052 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux-pro/v1.1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "aiml/v1.1-ultra", "provider": "aiml", "model": "v1.1-ultra", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml" ], "aliases": [ "aiml/flux-pro/v1.1-ultra" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/flux-pro/v1.1-ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.063 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/flux-pro/v1.1-ultra", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "alibaba-cn/moonshot-kimi-k2-instruct", "provider": "alibaba-cn", "model": "moonshot-kimi-k2-instruct", "displayName": "Moonshot Kimi K2 Instruct", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/moonshot-kimi-k2-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "moonshot-kimi-k2-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 2.294 } } ] }, "metadata": { "displayNames": [ "Moonshot Kimi K2 Instruct" ], "families": [ "kimi-k2" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "moonshot-kimi-k2-instruct", "modelKey": "moonshot-kimi-k2-instruct", "displayName": "Moonshot Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "alibaba-cn/qvq-max", "provider": "alibaba-cn", "model": "qvq-max", "displayName": "QVQ Max", "family": "qvq", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qvq-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qvq-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.147, "output": 4.588 } } ] }, "metadata": { "displayNames": [ "QVQ Max" ], "families": [ "qvq" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qvq-max", "modelKey": "qvq-max", "displayName": "QVQ Max", "family": "qvq", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "alibaba-cn/tongyi-intent-detect-v3", "provider": "alibaba-cn", "model": "tongyi-intent-detect-v3", "displayName": "Tongyi Intent Detect V3", "family": "yi", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/tongyi-intent-detect-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "tongyi-intent-detect-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.058, "output": 0.144 } } ] }, "metadata": { "displayNames": [ "Tongyi Intent Detect V3" ], "families": [ "yi" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "tongyi-intent-detect-v3", "modelKey": "tongyi-intent-detect-v3", "displayName": "Tongyi Intent Detect V3", "family": "yi", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01" } } ] }, { "id": "alibaba-token-plan-cn/wan2.7-image", "provider": "alibaba-token-plan-cn", "model": "wan2.7-image", "displayName": "Wan2.7 Image", "sources": [ "models.dev" ], "providers": [ "alibaba-token-plan-cn" ], "aliases": [ "alibaba-token-plan-cn/wan2.7-image" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "wan2.7-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Wan2.7 Image" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "wan2.7-image", "modelKey": "wan2.7-image", "displayName": "Wan2.7 Image", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "alibaba-token-plan-cn/wan2.7-image-pro", "provider": "alibaba-token-plan-cn", "model": "wan2.7-image-pro", "displayName": "Wan2.7 Image Pro", "sources": [ "models.dev" ], "providers": [ "alibaba-token-plan-cn" ], "aliases": [ "alibaba-token-plan-cn/wan2.7-image-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "wan2.7-image-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Wan2.7 Image Pro" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "wan2.7-image-pro", "modelKey": "wan2.7-image-pro", "displayName": "Wan2.7 Image Pro", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "alibaba-token-plan/wan2.7-image", "provider": "alibaba-token-plan", "model": "wan2.7-image", "displayName": "Wan2.7 Image", "sources": [ "models.dev" ], "providers": [ "alibaba-token-plan" ], "aliases": [ "alibaba-token-plan/wan2.7-image" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan", "model": "wan2.7-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Wan2.7 Image" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "wan2.7-image", "modelKey": "wan2.7-image", "displayName": "Wan2.7 Image", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "alibaba-token-plan/wan2.7-image-pro", "provider": "alibaba-token-plan", "model": "wan2.7-image-pro", "displayName": "Wan2.7 Image Pro", "sources": [ "models.dev" ], "providers": [ "alibaba-token-plan" ], "aliases": [ "alibaba-token-plan/wan2.7-image-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan", "model": "wan2.7-image-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Wan2.7 Image Pro" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "wan2.7-image-pro", "modelKey": "wan2.7-image-pro", "displayName": "Wan2.7 Image Pro", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "alibaba/qvq-max", "provider": "alibaba", "model": "qvq-max", "displayName": "QVQ Max", "family": "qvq", "sources": [ "models.dev" ], "providers": [ "alibaba" ], "aliases": [ "alibaba/qvq-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qvq-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 4.8 } } ] }, "metadata": { "displayNames": [ "QVQ Max" ], "families": [ "qvq" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qvq-max", "modelKey": "qvq-max", "displayName": "QVQ Max", "family": "qvq", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "alibaba/qwen-2.5-14b-instruct", "provider": "alibaba", "model": "qwen-2.5-14b-instruct", "displayName": "Qwen 2.5 14B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/qwen-2.5-14b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Qwen 2.5 14B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "qwen-2.5-14b-instruct", "modelKey": "qwen-2.5-14b-instruct", "displayName": "Qwen 2.5 14B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } } ] }, { "id": "alibaba/qwen-2.5-72b-instruct", "provider": "alibaba", "model": "qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cortecs", "kilo", "nano-gpt", "novita", "novita-ai", "openrouter" ], "aliases": [ "cortecs/qwen-2.5-72b-instruct", "kilo/qwen/qwen-2.5-72b-instruct", "nano-gpt/qwen/qwen-2.5-72b-instruct", "novita-ai/qwen/qwen-2.5-72b-instruct", "novita/qwen/qwen-2.5-72b-instruct", "openrouter/qwen/qwen-2.5-72b-instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 8192, "outputTokens": 33000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "qwen-2.5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.062, "output": 0.231 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.39 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.357, "output": 0.408 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.38, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.36, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.38, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-2.5-72b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 72B Instruct", "Qwen2.5 72B", "Qwen2.5 72B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06", "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen-2.5-72b-instruct", "modelKey": "qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-2.5-72b-instruct", "modelKey": "qwen/qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "metadata": { "lastUpdated": "2026-01-10", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen-2.5-72b-instruct", "modelKey": "qwen/qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B", "metadata": { "lastUpdated": "2025-07-03", "openWeights": false, "releaseDate": "2025-07-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen-2.5-72b-instruct", "modelKey": "qwen/qwen-2.5-72b-instruct", "displayName": "Qwen 2.5 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-10-15", "openWeights": true, "releaseDate": "2024-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-2.5-72b-instruct", "modelKey": "qwen/qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen-2.5-72b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-2.5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "metadata": { "canonicalSlug": "qwen/qwen-2.5-72b-instruct", "createdAt": "2024-09-19T00:00:00.000Z", "huggingFaceId": "Qwen/Qwen2.5-72B-Instruct", "instructType": "chatml", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 32768, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-2.5-7b-instruct", "provider": "alibaba", "model": "qwen-2.5-7b-instruct", "displayName": "Qwen: Qwen2.5 7B Instruct", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen-2.5-7b-instruct", "openrouter/qwen/qwen-2.5-7b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-2.5-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.1 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-2.5-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-2.5-7b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 7B Instruct", "Qwen: Qwen2.5 7B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-09", "lastUpdated": "2025-04-16", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-2.5-7b-instruct", "modelKey": "qwen/qwen-2.5-7b-instruct", "displayName": "Qwen: Qwen2.5 7B Instruct", "metadata": { "lastUpdated": "2025-04-16", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-2.5-7b-instruct", "modelKey": "qwen/qwen-2.5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2024-10-16", "openWeights": true, "releaseDate": "2024-10-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-2.5-7b-instruct", "displayName": "Qwen: Qwen2.5 7B Instruct", "metadata": { "canonicalSlug": "qwen/qwen-2.5-7b-instruct", "createdAt": "2024-10-16T00:00:00.000Z", "huggingFaceId": "Qwen/Qwen2.5-7B-Instruct", "instructType": "chatml", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/qwen/qwen-2.5-7b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-2.5-7b-vision-instruct", "provider": "alibaba", "model": "qwen-2.5-7b-vision-instruct", "displayName": "Qwen 2.5 7B Vision Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "inference" ], "aliases": [ "inference/qwen/qwen-2.5-7b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 125000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inference", "model": "qwen/qwen-2.5-7b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 7B Vision Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "qwen/qwen-2.5-7b-vision-instruct", "modelKey": "qwen/qwen-2.5-7b-vision-instruct", "displayName": "Qwen 2.5 7B Vision Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "alibaba/qwen-2.5-coder-32b", "provider": "alibaba", "model": "qwen-2.5-coder-32b", "displayName": "Qwen 2.5 Coder 32B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "abacus" ], "aliases": [ "abacus/qwen-2.5-coder-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "qwen-2.5-coder-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.79, "output": 0.79 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 Coder 32B" ], "families": [ "qwen" ], "releaseDate": "2024-11-11", "lastUpdated": "2024-11-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "qwen-2.5-coder-32b", "modelKey": "qwen-2.5-coder-32b", "displayName": "Qwen 2.5 Coder 32B", "family": "qwen", "metadata": { "lastUpdated": "2024-11-11", "openWeights": true, "releaseDate": "2024-11-11" } } ] }, { "id": "alibaba/qwen-2.5-coder-32b-instruct", "provider": "alibaba", "model": "qwen-2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen-2.5-coder-32b-instruct", "openrouter/qwen/qwen-2.5-coder-32b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 33792, "maxTokens": 33792, "outputTokens": 33792, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-2.5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.2, "output": 0.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-2.5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen-2.5-coder-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-2.5-coder-32b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.66, "output": 1 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 Coder 32B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-11-11", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-2.5-coder-32b-instruct", "modelKey": "qwen/qwen-2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-11-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-2.5-coder-32b-instruct", "modelKey": "qwen/qwen-2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2024-11-11", "openWeights": true, "releaseDate": "2024-11-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen-2.5-coder-32b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "metadata": { "canonicalSlug": "qwen/qwen-2.5-coder-32b-instruct", "createdAt": "2024-11-11T23:40:00.000Z", "huggingFaceId": "Qwen/Qwen2.5-Coder-32B-Instruct", "instructType": "chatml", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-3-14b", "provider": "alibaba", "model": "qwen-3-14b", "displayName": "Qwen3-14B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/alibaba/qwen-3-14b", "vercel_ai_gateway/alibaba/qwen-3-14b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen-3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.24 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Qwen3-14B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-01", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen-3-14b", "modelKey": "alibaba/qwen-3-14b", "displayName": "Qwen3-14B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-14b", "mode": "chat" } ] }, { "id": "alibaba/qwen-3-235b", "provider": "alibaba", "model": "qwen-3-235b", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/alibaba/qwen-3-235b", "vercel_ai_gateway/alibaba/qwen-3-235b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 40960, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen-3-235b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-235b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B Instruct 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-01", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen-3-235b", "modelKey": "alibaba/qwen-3-235b", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-235b", "mode": "chat" } ] }, { "id": "alibaba/qwen-3-30b", "provider": "alibaba", "model": "qwen-3-30b", "displayName": "Qwen3-30B-A3B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/alibaba/qwen-3-30b", "vercel_ai_gateway/alibaba/qwen-3-30b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen-3-30b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-30b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Qwen3-30B-A3B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-01", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen-3-30b", "modelKey": "alibaba/qwen-3-30b", "displayName": "Qwen3-30B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-30b", "mode": "chat" } ] }, { "id": "alibaba/qwen-3-32b", "provider": "alibaba", "model": "qwen-3-32b", "displayName": "Qwen 3.32B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cerebras", "vercel", "vercel_ai_gateway" ], "aliases": [ "cerebras/qwen-3-32b", "vercel/alibaba/qwen-3-32b", "vercel_ai_gateway/alibaba/qwen-3-32b" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen-3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.64 } }, { "source": "litellm", "provider": "cerebras", "model": "cerebras/qwen-3-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.8 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Qwen 3.32B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-01", "lastUpdated": "2025-04", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen-3-32b", "modelKey": "alibaba/qwen-3-32b", "displayName": "Qwen 3.32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/qwen-3-32b", "mode": "chat", "metadata": { "source": "https://inference-docs.cerebras.ai/support/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen-3-32b", "mode": "chat" } ] }, { "id": "alibaba/qwen-3-6-plus", "provider": "alibaba", "model": "qwen-3-6-plus", "displayName": "Qwen 3.6 Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "frogbot", "venice" ], "aliases": [ "frogbot/qwen-3-6-plus", "venice/qwen-3-6-plus" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "qwen-3-6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "venice", "model": "qwen-3-6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0625, "cacheWrite": 0.78, "input": 0.625, "output": 3.75 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 7.5, "cache_read": 0.0625, "cache_write": 0.78 }, "tiers": [ { "input": 2.5, "output": 7.5, "cache_read": 0.0625, "cache_write": 0.78, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 Plus", "Qwen 3.6 Plus Uncensored" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "qwen-3-6-plus", "modelKey": "qwen-3-6-plus", "displayName": "Qwen 3.6 Plus", "family": "qwen", "metadata": { "lastUpdated": "2026-04-03", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen-3-6-plus", "modelKey": "qwen-3-6-plus", "displayName": "Qwen 3.6 Plus Uncensored", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen-3-7-max", "provider": "alibaba", "model": "qwen-3-7-max", "displayName": "Qwen 3.7 Max", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen-3-7-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen-3-7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.27, "cacheWrite": 3.35, "input": 2.7, "output": 8.05 } } ] }, "metadata": { "displayNames": [ "Qwen 3.7 Max" ], "families": [ "qwen" ], "releaseDate": "2026-05-22", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen-3-7-max", "modelKey": "qwen-3-7-max", "displayName": "Qwen 3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-22" } } ] }, { "id": "alibaba/qwen-3-7-plus", "provider": "alibaba", "model": "qwen-3-7-plus", "displayName": "Qwen 3.7 Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen-3-7-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen-3-7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 2 }, "tiered": { "contextOver200K": { "input": 1.5, "output": 6, "cache_read": 0.15, "cache_write": 1.875 }, "tiers": [ { "input": 1.5, "output": 6, "cache_read": 0.15, "cache_write": 1.875, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Qwen 3.7 Plus" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-06-02", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen-3-7-plus", "modelKey": "qwen-3-7-plus", "displayName": "Qwen 3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-06-02" } } ] }, { "id": "alibaba/qwen-3.6-max-preview", "provider": "alibaba", "model": "qwen-3.6-max-preview", "displayName": "Qwen 3.6 Max Preview", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/qwen-3.6-max-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 240000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen-3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 1.625, "input": 1.3, "output": 7.8 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 Max Preview" ], "families": [ "qwen" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen-3.6-max-preview", "modelKey": "alibaba/qwen-3.6-max-preview", "displayName": "Qwen 3.6 Max Preview", "family": "qwen", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-20" } } ] }, { "id": "alibaba/qwen-3.6-plus", "provider": "alibaba", "model": "qwen-3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "auriko", "nano-gpt" ], "aliases": [ "auriko/qwen-3.6-plus", "nano-gpt/qwen-3.6-plus" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "auriko", "model": "qwen-3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen-3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.7 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 Plus", "Qwen3.6 Plus" ], "families": [ "qwen", "qwen3.6" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "qwen-3.6-plus", "modelKey": "qwen-3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen-3.6-plus", "modelKey": "qwen-3.6-plus", "displayName": "Qwen 3.6 Plus", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } } ] }, { "id": "alibaba/qwen-coder", "provider": "alibaba", "model": "qwen-coder", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-coder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-coder", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-coder-plus", "provider": "alibaba", "model": "qwen-coder-plus", "displayName": "Qwen Coder Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/qwen-coder-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.502, "output": 1.004 } } ] }, "metadata": { "displayNames": [ "Qwen Coder Plus" ], "families": [ "qwen" ], "releaseDate": "2024-09-18", "lastUpdated": "2024-09-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-coder-plus", "modelKey": "qwen-coder-plus", "displayName": "Qwen Coder Plus", "family": "qwen", "metadata": { "lastUpdated": "2024-09-18", "openWeights": false, "releaseDate": "2024-09-18" } } ] }, { "id": "alibaba/qwen-deep-research", "provider": "alibaba", "model": "qwen-deep-research", "displayName": "Qwen Deep Research", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-deep-research" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 7.742, "output": 23.367 } } ] }, "metadata": { "displayNames": [ "Qwen Deep Research" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-deep-research", "modelKey": "qwen-deep-research", "displayName": "Qwen Deep Research", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01" } } ] }, { "id": "alibaba/qwen-doc-turbo", "provider": "alibaba", "model": "qwen-doc-turbo", "displayName": "Qwen Doc Turbo", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-doc-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-doc-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.087, "output": 0.144 } } ] }, "metadata": { "displayNames": [ "Qwen Doc Turbo" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-doc-turbo", "modelKey": "qwen-doc-turbo", "displayName": "Qwen Doc Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01" } } ] }, { "id": "alibaba/qwen-flash", "provider": "alibaba", "model": "qwen-flash", "displayName": "Qwen Flash", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "alibaba", "alibaba-cn", "dashscope", "llmgateway" ], "aliases": [ "302ai/qwen-flash", "alibaba-cn/qwen-flash", "alibaba/qwen-flash", "dashscope/qwen-flash", "llmgateway/qwen-flash" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1000000, "inputTokens": 997952, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.022, "output": 0.22 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.022, "output": 0.216 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen Flash", "Qwen-Flash" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-07-28", "lastUpdated": "2025-07-28", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen-flash", "modelKey": "qwen-flash", "displayName": "Qwen-Flash", "metadata": { "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-flash", "modelKey": "qwen-flash", "displayName": "Qwen Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-flash", "modelKey": "qwen-flash", "displayName": "Qwen Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-flash", "modelKey": "qwen-flash", "displayName": "Qwen Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-flash", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-flash-2025-07-28", "provider": "alibaba", "model": "qwen-flash-2025-07-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-flash-2025-07-28" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 997952, "inputTokens": 997952, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-flash-2025-07-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-flash-2025-07-28", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-image", "provider": "alibaba", "model": "qwen-image", "displayName": "Qwen Image", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nvidia", "regolo-ai" ], "aliases": [ "nvidia/qwen/qwen-image", "regolo-ai/qwen-image" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "qwen-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "Qwen Image", "Qwen-Image" ], "families": [ "qwen" ], "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen-image", "modelKey": "qwen/qwen-image", "displayName": "Qwen Image", "family": "qwen", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen-image", "modelKey": "qwen-image", "displayName": "Qwen-Image", "family": "qwen", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01" } } ] }, { "id": "alibaba/qwen-image-2.0", "provider": "alibaba", "model": "qwen-image-2.0", "displayName": "Qwen Image 2.0", "family": "qwen", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-token-plan", "alibaba-token-plan-cn", "dashscope" ], "aliases": [ "alibaba-token-plan-cn/qwen-image-2.0", "alibaba-token-plan/qwen-image-2.0", "dashscope/qwen-image-2.0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen-image-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen-image-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-image-2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen Image 2.0" ], "families": [ "qwen" ], "modes": [ "image_generation" ], "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen-image-2.0", "modelKey": "qwen-image-2.0", "displayName": "Qwen Image 2.0", "family": "qwen", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen-image-2.0", "modelKey": "qwen-image-2.0", "displayName": "Qwen Image 2.0", "family": "qwen", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-image-2.0", "mode": "image_generation", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "alibaba/qwen-image-2.0-pro", "provider": "alibaba", "model": "qwen-image-2.0-pro", "displayName": "Qwen Image 2.0 Pro", "family": "qwen", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-token-plan", "alibaba-token-plan-cn", "dashscope" ], "aliases": [ "alibaba-token-plan-cn/qwen-image-2.0-pro", "alibaba-token-plan/qwen-image-2.0-pro", "dashscope/qwen-image-2.0-pro" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen-image-2.0-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen-image-2.0-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-image-2.0-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen Image 2.0 Pro" ], "families": [ "qwen" ], "modes": [ "image_generation" ], "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen-image-2.0-pro", "modelKey": "qwen-image-2.0-pro", "displayName": "Qwen Image 2.0 Pro", "family": "qwen", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen-image-2.0-pro", "modelKey": "qwen-image-2.0-pro", "displayName": "Qwen Image 2.0 Pro", "family": "qwen", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-image-2.0-pro", "mode": "image_generation", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "alibaba/qwen-image-edit", "provider": "alibaba", "model": "qwen-image-edit", "displayName": "Qwen Image Edit", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/qwen/qwen-image-edit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen-image-edit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen Image Edit" ], "families": [ "qwen" ], "releaseDate": "2025-08-19", "lastUpdated": "2025-08-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen-image-edit", "modelKey": "qwen/qwen-image-edit", "displayName": "Qwen Image Edit", "family": "qwen", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } } ] }, { "id": "alibaba/qwen-long", "provider": "alibaba", "model": "qwen-long", "displayName": "Qwen Long", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn", "nano-gpt" ], "aliases": [ "alibaba-cn/qwen-long", "nano-gpt/qwen-long" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 10000000, "inputTokens": 10000000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-long", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.287 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen-long", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Qwen Long", "Qwen Long 10M" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-01-25", "lastUpdated": "2025-01-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-long", "modelKey": "qwen-long", "displayName": "Qwen Long", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen-long", "modelKey": "qwen-long", "displayName": "Qwen Long 10M", "metadata": { "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } } ] }, { "id": "alibaba/qwen-math-plus", "provider": "alibaba", "model": "qwen-math-plus", "displayName": "Qwen Math Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-math-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-math-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 1.721 } } ] }, "metadata": { "displayNames": [ "Qwen Math Plus" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-08-16", "lastUpdated": "2024-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-math-plus", "modelKey": "qwen-math-plus", "displayName": "Qwen Math Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09-19", "openWeights": false, "releaseDate": "2024-08-16" } } ] }, { "id": "alibaba/qwen-math-turbo", "provider": "alibaba", "model": "qwen-math-turbo", "displayName": "Qwen Math Turbo", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-math-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-math-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } } ] }, "metadata": { "displayNames": [ "Qwen Math Turbo" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-math-turbo", "modelKey": "qwen-math-turbo", "displayName": "Qwen Math Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09-19", "openWeights": false, "releaseDate": "2024-09-19" } } ] }, { "id": "alibaba/qwen-max", "provider": "alibaba", "model": "qwen-max", "displayName": "Qwen Max", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "dashscope", "llmgateway", "nano-gpt" ], "aliases": [ "alibaba-cn/qwen-max", "alibaba/qwen-max", "dashscope/qwen-max", "llmgateway/qwen-max", "nano-gpt/qwen-max" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 131072, "inputTokens": 32000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.345, "output": 1.377 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.6, "output": 6.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.6, "output": 6.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5997, "output": 6.392 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.6, "output": 6.4 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 Max", "Qwen Max" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-04-03", "lastUpdated": "2025-01-25", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-max", "modelKey": "qwen-max", "displayName": "Qwen Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2024-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-max", "modelKey": "qwen-max", "displayName": "Qwen Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2024-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-max", "modelKey": "qwen-max", "displayName": "Qwen Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2024-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen-max", "modelKey": "qwen-max", "displayName": "Qwen 2.5 Max", "metadata": { "lastUpdated": "2024-04-03", "openWeights": false, "releaseDate": "2024-04-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-max", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-max-2025-01-25", "provider": "alibaba", "model": "qwen-max-2025-01-25", "displayName": "Qwen2.5-Max-2025-01-25", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/qwen-max-2025-01-25" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Qwen2.5-Max-2025-01-25" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen-max-2025-01-25", "modelKey": "qwen-max-2025-01-25", "displayName": "Qwen2.5-Max-2025-01-25", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "alibaba/qwen-max-latest", "provider": "alibaba", "model": "qwen-max-latest", "displayName": "Qwen-Max-Latest", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "302ai", "llmgateway" ], "aliases": [ "302ai/qwen-max-latest", "llmgateway/qwen-max-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen-max-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.343, "output": 1.372 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-max-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.345, "output": 1.377 } } ] }, "metadata": { "displayNames": [ "Qwen Max Latest", "Qwen-Max-Latest" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-04-03", "lastUpdated": "2025-01-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen-max-latest", "modelKey": "qwen-max-latest", "displayName": "Qwen-Max-Latest", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2024-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-max-latest", "modelKey": "qwen-max-latest", "displayName": "Qwen Max Latest", "family": "qwen", "metadata": { "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } } ] }, { "id": "alibaba/qwen-mt-plus", "provider": "alibaba", "model": "qwen-mt-plus", "displayName": "Qwen-MT Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "novita", "novita-ai" ], "aliases": [ "alibaba-cn/qwen-mt-plus", "alibaba/qwen-mt-plus", "novita-ai/qwen/qwen-mt-plus", "novita/qwen/qwen-mt-plus" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-mt-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.259, "output": 0.775 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-mt-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.46, "output": 7.37 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen-mt-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.75 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen-mt-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Qwen MT Plus", "Qwen-MT Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-01", "lastUpdated": "2025-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-mt-plus", "modelKey": "qwen-mt-plus", "displayName": "Qwen-MT Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-mt-plus", "modelKey": "qwen-mt-plus", "displayName": "Qwen-MT Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen-mt-plus", "modelKey": "qwen/qwen-mt-plus", "displayName": "Qwen MT Plus", "metadata": { "lastUpdated": "2025-09-03", "openWeights": true, "releaseDate": "2025-09-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen-mt-plus", "mode": "chat" } ] }, { "id": "alibaba/qwen-mt-turbo", "provider": "alibaba", "model": "qwen-mt-turbo", "displayName": "Qwen-MT Turbo", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-mt-turbo", "alibaba/qwen-mt-turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-mt-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.101, "output": 0.28 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-mt-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.49 } } ] }, "metadata": { "displayNames": [ "Qwen-MT Turbo" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-01", "lastUpdated": "2025-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-mt-turbo", "modelKey": "qwen-mt-turbo", "displayName": "Qwen-MT Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-mt-turbo", "modelKey": "qwen-mt-turbo", "displayName": "Qwen-MT Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01" } } ] }, { "id": "alibaba/qwen-omni-turbo", "provider": "alibaba", "model": "qwen-omni-turbo", "displayName": "Qwen-Omni Turbo", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "llmgateway" ], "aliases": [ "alibaba-cn/qwen-omni-turbo", "alibaba/qwen-omni-turbo", "llmgateway/qwen-omni-turbo" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-omni-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.058, "inputAudio": 3.584, "output": 0.23, "outputAudio": 7.168 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-omni-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "inputAudio": 4.44, "output": 0.27, "outputAudio": 8.89 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-omni-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "inputAudio": 4.44, "output": 0.27, "outputAudio": 8.89 } } ] }, "metadata": { "displayNames": [ "Qwen-Omni Turbo" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-01-19", "lastUpdated": "2025-03-26", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-omni-turbo", "modelKey": "qwen-omni-turbo", "displayName": "Qwen-Omni Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-26", "openWeights": false, "releaseDate": "2025-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-omni-turbo", "modelKey": "qwen-omni-turbo", "displayName": "Qwen-Omni Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-26", "openWeights": false, "releaseDate": "2025-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-omni-turbo", "modelKey": "qwen-omni-turbo", "displayName": "Qwen-Omni Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-26", "openWeights": false, "releaseDate": "2025-01-19" } } ] }, { "id": "alibaba/qwen-omni-turbo-realtime", "provider": "alibaba", "model": "qwen-omni-turbo-realtime", "displayName": "Qwen-Omni Turbo Realtime", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-omni-turbo-realtime", "alibaba/qwen-omni-turbo-realtime" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-omni-turbo-realtime", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "inputAudio": 3.584, "output": 0.918, "outputAudio": 7.168 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-omni-turbo-realtime", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "inputAudio": 4.44, "output": 1.07, "outputAudio": 8.89 } } ] }, "metadata": { "displayNames": [ "Qwen-Omni Turbo Realtime" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-05-08", "lastUpdated": "2025-05-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-omni-turbo-realtime", "modelKey": "qwen-omni-turbo-realtime", "displayName": "Qwen-Omni Turbo Realtime", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-omni-turbo-realtime", "modelKey": "qwen-omni-turbo-realtime", "displayName": "Qwen-Omni Turbo Realtime", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } } ] }, { "id": "alibaba/qwen-plus", "provider": "alibaba", "model": "qwen-plus", "displayName": "Qwen Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "alibaba", "alibaba-cn", "dashscope", "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "302ai/qwen-plus", "alibaba-cn/qwen-plus", "alibaba/qwen-plus", "dashscope/qwen-plus", "kilo/qwen/qwen-plus", "llmgateway/qwen-plus", "nano-gpt/qwen-plus", "openrouter/qwen/qwen-plus" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1000000, "inputTokens": 995904, "maxTokens": 16384, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 1.2 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.287, "reasoningOutput": 1.147 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.2, "reasoningOutput": 4 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 1.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.2, "reasoningOutput": 4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3995, "output": 1.2002 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.052, "cacheWrite": 0.325, "input": 0.26, "output": 0.78 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-plus", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.052, "cacheWrite": 0.325, "input": 0.26, "output": 0.78 } } ] }, "metadata": { "displayNames": [ "Qwen Plus", "Qwen-Plus", "Qwen: Qwen-Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen-plus", "modelKey": "qwen-plus", "displayName": "Qwen-Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-plus", "modelKey": "qwen-plus", "displayName": "Qwen Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-plus", "modelKey": "qwen-plus", "displayName": "Qwen Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-plus", "modelKey": "qwen/qwen-plus", "displayName": "Qwen: Qwen-Plus", "metadata": { "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-plus", "modelKey": "qwen-plus", "displayName": "Qwen Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen-plus", "modelKey": "qwen-plus", "displayName": "Qwen Plus", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-plus", "modelKey": "qwen/qwen-plus", "displayName": "Qwen Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-plus", "displayName": "Qwen: Qwen-Plus", "metadata": { "canonicalSlug": "qwen/qwen-plus-2025-01-25", "createdAt": "2025-02-01T11:37:20.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints" }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 1000000, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-plus-2025-01-25", "provider": "alibaba", "model": "qwen-plus-2025-01-25", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-plus-2025-01-25" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 129024, "inputTokens": 129024, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-01-25", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-01-25", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-plus-2025-04-28", "provider": "alibaba", "model": "qwen-plus-2025-04-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-plus-2025-04-28" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 129024, "inputTokens": 129024, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-04-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.2, "reasoningOutput": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-04-28", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-plus-2025-07-14", "provider": "alibaba", "model": "qwen-plus-2025-07-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-plus-2025-07-14" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 129024, "inputTokens": 129024, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-07-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.2, "reasoningOutput": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-07-14", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-plus-2025-07-28", "provider": "alibaba", "model": "qwen-plus-2025-07-28", "displayName": "Qwen: Qwen Plus 0728", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "dashscope", "kilo", "openrouter" ], "aliases": [ "dashscope/qwen-plus-2025-07-28", "kilo/qwen/qwen-plus-2025-07-28", "openrouter/qwen/qwen-plus-2025-07-28" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 997952, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-plus-2025-07-28", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 0.78 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 0.78 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-07-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.26, "output": 0.78 } } ] }, "metadata": { "displayNames": [ "Qwen Plus 0728", "Qwen: Qwen Plus 0728" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-09", "lastUpdated": "2026-03-15", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-plus-2025-07-28", "modelKey": "qwen/qwen-plus-2025-07-28", "displayName": "Qwen: Qwen Plus 0728", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-plus-2025-07-28", "modelKey": "qwen/qwen-plus-2025-07-28", "displayName": "Qwen Plus 0728", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-09-08", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-07-28", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28", "displayName": "Qwen: Qwen Plus 0728", "metadata": { "canonicalSlug": "qwen/qwen-plus-2025-07-28", "createdAt": "2025-09-08T16:06:39.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-plus-2025-07-28:thinking", "provider": "alibaba", "model": "qwen-plus-2025-07-28:thinking", "displayName": "Qwen: Qwen Plus 0728 (thinking)", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen-plus-2025-07-28:thinking", "openrouter/qwen/qwen-plus-2025-07-28:thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen-plus-2025-07-28:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 0.78 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.325, "input": 0.26, "output": 0.78 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28:thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 0.325, "input": 0.26, "output": 0.78 } } ] }, "metadata": { "displayNames": [ "Qwen Plus 0728 (thinking)", "Qwen: Qwen Plus 0728 (thinking)" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-09", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen-plus-2025-07-28:thinking", "modelKey": "qwen/qwen-plus-2025-07-28:thinking", "displayName": "Qwen: Qwen Plus 0728 (thinking)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen-plus-2025-07-28:thinking", "modelKey": "qwen/qwen-plus-2025-07-28:thinking", "displayName": "Qwen Plus 0728 (thinking)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-09-08", "openWeights": false, "releaseDate": "2025-09-08", "reasoningOptions": [ { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen-plus-2025-07-28:thinking", "displayName": "Qwen: Qwen Plus 0728 (thinking)", "metadata": { "canonicalSlug": "qwen/qwen-plus-2025-07-28", "createdAt": "2025-09-08T16:06:39.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen-plus-2025-09-11", "provider": "alibaba", "model": "qwen-plus-2025-09-11", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-plus-2025-09-11" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 997952, "inputTokens": 997952, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-09-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-2025-09-11", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-plus-character", "provider": "alibaba", "model": "qwen-plus-character", "displayName": "Qwen Plus Character", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-plus-character" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-plus-character", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.287 } } ] }, "metadata": { "displayNames": [ "Qwen Plus Character" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-plus-character", "modelKey": "qwen-plus-character", "displayName": "Qwen Plus Character", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01" } } ] }, { "id": "alibaba/qwen-plus-character-ja", "provider": "alibaba", "model": "qwen-plus-character-ja", "displayName": "Qwen Plus Character (Japanese)", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba" ], "aliases": [ "alibaba/qwen-plus-character-ja" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen-plus-character-ja", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "Qwen Plus Character (Japanese)" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-plus-character-ja", "modelKey": "qwen-plus-character-ja", "displayName": "Qwen Plus Character (Japanese)", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01" } } ] }, { "id": "alibaba/qwen-plus-latest", "provider": "alibaba", "model": "qwen-plus-latest", "displayName": "Qwen Plus Latest", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "dashscope", "llmgateway" ], "aliases": [ "dashscope/qwen-plus-latest", "llmgateway/qwen-plus-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 997952, "inputTokens": 997952, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen-plus-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.287 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-plus-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen Plus Latest" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-01-25", "lastUpdated": "2025-01-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-plus-latest", "modelKey": "qwen-plus-latest", "displayName": "Qwen Plus Latest", "family": "qwen", "metadata": { "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-plus-latest", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-qwq-32b-preview", "provider": "alibaba", "model": "qwen-qwq-32b-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview", "mode": "chat" } ] }, { "id": "alibaba/qwen-sea-lion-v4-32b-it", "provider": "alibaba", "model": "qwen-sea-lion-v4-32b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "alibaba/qwen-turbo", "provider": "alibaba", "model": "qwen-turbo", "displayName": "Qwen Turbo", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "dashscope", "llmgateway", "nano-gpt", "qiniu-ai" ], "aliases": [ "alibaba-cn/qwen-turbo", "alibaba/qwen-turbo", "dashscope/qwen-turbo", "llmgateway/qwen-turbo", "nano-gpt/qwen-turbo", "qiniu-ai/qwen-turbo" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.044, "output": 0.087, "reasoningOutput": 0.431 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2, "reasoningOutput": 0.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2, "reasoningOutput": 0.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04998, "output": 0.2006 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2, "reasoningOutput": 0.5 } } ] }, "metadata": { "displayNames": [ "Qwen Turbo", "Qwen-Turbo" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-11-01", "lastUpdated": "2025-07-15", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-turbo", "modelKey": "qwen-turbo", "displayName": "Qwen Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-15", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-turbo", "modelKey": "qwen-turbo", "displayName": "Qwen Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-turbo", "modelKey": "qwen-turbo", "displayName": "Qwen Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen-turbo", "modelKey": "qwen-turbo", "displayName": "Qwen Turbo", "metadata": { "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen-turbo", "modelKey": "qwen-turbo", "displayName": "Qwen-Turbo", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-turbo", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-turbo-2024-11-01", "provider": "alibaba", "model": "qwen-turbo-2024-11-01", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-turbo-2024-11-01" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-turbo-2024-11-01", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-turbo-2024-11-01", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-turbo-2025-04-28", "provider": "alibaba", "model": "qwen-turbo-2025-04-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-turbo-2025-04-28" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-turbo-2025-04-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2, "reasoningOutput": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-turbo-2025-04-28", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-turbo-latest", "provider": "alibaba", "model": "qwen-turbo-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen-turbo-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen-turbo-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2, "reasoningOutput": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen-turbo-latest", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen-v2p5-14b-instruct", "provider": "alibaba", "model": "qwen-v2p5-14b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen-v2p5-7b", "provider": "alibaba", "model": "qwen-v2p5-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b", "mode": "chat" } ] }, { "id": "alibaba/qwen-vl-max", "provider": "alibaba", "model": "qwen-vl-max", "displayName": "Qwen-VL Max", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "llmgateway" ], "aliases": [ "alibaba-cn/qwen-vl-max", "alibaba/qwen-vl-max", "llmgateway/qwen-vl-max" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-vl-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "output": 0.574 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-vl-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 3.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-vl-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "Qwen-VL Max" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-04-08", "lastUpdated": "2025-08-13", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-max", "modelKey": "qwen-vl-max", "displayName": "Qwen-VL Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-13", "openWeights": false, "releaseDate": "2024-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-max", "modelKey": "qwen-vl-max", "displayName": "Qwen-VL Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-13", "openWeights": false, "releaseDate": "2024-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-vl-max", "modelKey": "qwen-vl-max", "displayName": "Qwen-VL Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-13", "openWeights": false, "releaseDate": "2024-04-08" } } ] }, { "id": "alibaba/qwen-vl-max-2025-01-25", "provider": "alibaba", "model": "qwen-vl-max-2025-01-25", "displayName": "Qwen VL-MAX-2025-01-25", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/qwen-vl-max-2025-01-25" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Qwen VL-MAX-2025-01-25" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen-vl-max-2025-01-25", "modelKey": "qwen-vl-max-2025-01-25", "displayName": "Qwen VL-MAX-2025-01-25", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "alibaba/qwen-vl-ocr", "provider": "alibaba", "model": "qwen-vl-ocr", "displayName": "Qwen-VL OCR", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen-vl-ocr", "alibaba/qwen-vl-ocr" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 34096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-vl-ocr", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.717, "output": 0.717 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-vl-ocr", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Qwen-VL OCR" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-10-28", "lastUpdated": "2025-04-13", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-ocr", "modelKey": "qwen-vl-ocr", "displayName": "Qwen-VL OCR", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-13", "openWeights": false, "releaseDate": "2024-10-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-ocr", "modelKey": "qwen-vl-ocr", "displayName": "Qwen-VL OCR", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-13", "openWeights": false, "releaseDate": "2024-10-28" } } ] }, { "id": "alibaba/qwen-vl-plus", "provider": "alibaba", "model": "qwen-vl-plus", "displayName": "Qwen-VL Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "llmgateway", "openrouter" ], "aliases": [ "alibaba-cn/qwen-vl-plus", "alibaba/qwen-vl-plus", "llmgateway/qwen-vl-plus", "openrouter/qwen/qwen-vl-plus" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 8192, "maxTokens": 2048, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.287 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.63 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.63 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen-vl-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.21, "output": 0.63 } } ] }, "metadata": { "displayNames": [ "Qwen-VL Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-01-25", "lastUpdated": "2025-08-15", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-plus", "modelKey": "qwen-vl-plus", "displayName": "Qwen-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen-vl-plus", "modelKey": "qwen-vl-plus", "displayName": "Qwen-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen-vl-plus", "modelKey": "qwen-vl-plus", "displayName": "Qwen-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen-vl-plus", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-235b-a22b-2507-v1:0", "provider": "alibaba", "model": "qwen.qwen3-235b-a22b-2507-v1:0", "displayName": "Qwen3 235B A22B 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-235b-a22b-2507-v1:0", "bedrock_converse/qwen.qwen3-235b-a22b-2507-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-235b-a22b-2507-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-235b-a22b-2507-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-235b-a22b-2507-v1:0", "modelKey": "qwen.qwen3-235b-a22b-2507-v1:0", "displayName": "Qwen3 235B A22B 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-18", "openWeights": true, "releaseDate": "2025-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-235b-a22b-2507-v1:0", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-32b-v1:0", "provider": "alibaba", "model": "qwen.qwen3-32b-v1:0", "displayName": "Qwen3 32B (dense)", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-32b-v1:0", "bedrock_converse/qwen.qwen3-32b-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-32b-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-32b-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Qwen3 32B (dense)" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-32b-v1:0", "modelKey": "qwen.qwen3-32b-v1:0", "displayName": "Qwen3 32B (dense)", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-18", "openWeights": true, "releaseDate": "2025-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-32b-v1:0", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-coder-30b-a3b-v1:0", "provider": "alibaba", "model": "qwen.qwen3-coder-30b-a3b-v1:0", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-coder-30b-a3b-v1:0", "bedrock_converse/qwen.qwen3-coder-30b-a3b-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-coder-30b-a3b-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-30b-a3b-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder 30B A3B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-coder-30b-a3b-v1:0", "modelKey": "qwen.qwen3-coder-30b-a3b-v1:0", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-18", "openWeights": false, "releaseDate": "2025-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-30b-a3b-v1:0", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-coder-480b-a35b-v1:0", "provider": "alibaba", "model": "qwen.qwen3-coder-480b-a35b-v1:0", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-coder-480b-a35b-v1:0", "bedrock_converse/qwen.qwen3-coder-480b-a35b-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262000, "inputTokens": 262000, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-coder-480b-a35b-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 1.8 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-480b-a35b-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder 480B A35B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-coder-480b-a35b-v1:0", "modelKey": "qwen.qwen3-coder-480b-a35b-v1:0", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-18", "openWeights": true, "releaseDate": "2025-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-480b-a35b-v1:0", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-coder-next", "provider": "alibaba", "model": "qwen.qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-coder-next", "bedrock_converse/qwen.qwen3-coder-next" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 1.8 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Next" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2026-02-06", "lastUpdated": "2026-02-06", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-coder-next", "modelKey": "qwen.qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-06", "openWeights": true, "releaseDate": "2026-02-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "alibaba/qwen.qwen3-next-80b-a3b", "provider": "alibaba", "model": "qwen.qwen3-next-80b-a3b", "displayName": "Qwen/Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-next-80b-a3b", "bedrock_converse/qwen.qwen3-next-80b-a3b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-next-80b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-next-80b-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Next-80B-A3B-Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-09-18", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-next-80b-a3b", "modelKey": "qwen.qwen3-next-80b-a3b", "displayName": "Qwen/Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-next-80b-a3b", "mode": "chat" } ] }, { "id": "alibaba/qwen.qwen3-vl-235b-a22b", "provider": "alibaba", "model": "qwen.qwen3-vl-235b-a22b", "displayName": "Qwen/Qwen3-VL-235B-A22B-Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/qwen.qwen3-vl-235b-a22b", "bedrock_converse/qwen.qwen3-vl-235b-a22b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "qwen.qwen3-vl-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "qwen.qwen3-vl-235b-a22b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.53, "output": 2.66 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-235B-A22B-Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-10-04", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "qwen.qwen3-vl-235b-a22b", "modelKey": "qwen.qwen3-vl-235b-a22b", "displayName": "Qwen/Qwen3-VL-235B-A22B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "qwen.qwen3-vl-235b-a22b", "mode": "chat" } ] }, { "id": "alibaba/qwen1p5-72b-chat", "provider": "alibaba", "model": "qwen1p5-72b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat", "mode": "chat" } ] }, { "id": "alibaba/qwen2-5-14b-instruct", "provider": "alibaba", "model": "qwen2-5-14b-instruct", "displayName": "Qwen2.5 14B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-14b-instruct", "alibaba/qwen2-5-14b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-14b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.431 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-14b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 14B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-14b-instruct", "modelKey": "qwen2-5-14b-instruct", "displayName": "Qwen2.5 14B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-14b-instruct", "modelKey": "qwen2-5-14b-instruct", "displayName": "Qwen2.5 14B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-32b-instruct", "provider": "alibaba", "model": "qwen2-5-32b-instruct", "displayName": "Qwen2.5 32B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-32b-instruct", "alibaba/qwen2-5-32b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 32B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-32b-instruct", "modelKey": "qwen2-5-32b-instruct", "displayName": "Qwen2.5 32B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-32b-instruct", "modelKey": "qwen2-5-32b-instruct", "displayName": "Qwen2.5 32B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-72b-instruct", "provider": "alibaba", "model": "qwen2-5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-72b-instruct", "alibaba/qwen2-5-72b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 1.721 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 5.6 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 72B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-72b-instruct", "modelKey": "qwen2-5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-72b-instruct", "modelKey": "qwen2-5-72b-instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-7b-instruct", "provider": "alibaba", "model": "qwen2-5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-7b-instruct", "alibaba/qwen2-5-7b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.144 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.175, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 7B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-7b-instruct", "modelKey": "qwen2-5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-7b-instruct", "modelKey": "qwen2-5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-coder-32b-instruct", "provider": "alibaba", "model": "qwen2-5-coder-32b-instruct", "displayName": "Qwen2.5-Coder 32B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-coder-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-Coder 32B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-11", "lastUpdated": "2024-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-coder-32b-instruct", "modelKey": "qwen2-5-coder-32b-instruct", "displayName": "Qwen2.5-Coder 32B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-11", "openWeights": true, "releaseDate": "2024-11" } } ] }, { "id": "alibaba/qwen2-5-coder-7b-instruct", "provider": "alibaba", "model": "qwen2-5-coder-7b-instruct", "displayName": "Qwen2.5-Coder 7B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-coder-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-coder-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.287 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-Coder 7B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-11", "lastUpdated": "2024-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-coder-7b-instruct", "modelKey": "qwen2-5-coder-7b-instruct", "displayName": "Qwen2.5-Coder 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-11", "openWeights": true, "releaseDate": "2024-11" } } ] }, { "id": "alibaba/qwen2-5-math-72b-instruct", "provider": "alibaba", "model": "qwen2-5-math-72b-instruct", "displayName": "Qwen2.5-Math 72B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-math-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-math-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 1.721 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-Math 72B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-math-72b-instruct", "modelKey": "qwen2-5-math-72b-instruct", "displayName": "Qwen2.5-Math 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-math-7b-instruct", "provider": "alibaba", "model": "qwen2-5-math-7b-instruct", "displayName": "Qwen2.5-Math 7B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-math-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-math-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.287 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-Math 7B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-math-7b-instruct", "modelKey": "qwen2-5-math-7b-instruct", "displayName": "Qwen2.5-Math 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-omni-7b", "provider": "alibaba", "model": "qwen2-5-omni-7b", "displayName": "Qwen2.5-Omni 7B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-omni-7b", "alibaba/qwen2-5-omni-7b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-omni-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.087, "inputAudio": 5.448, "output": 0.345 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-omni-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "inputAudio": 6.76, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-Omni 7B" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-12", "lastUpdated": "2024-12", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-omni-7b", "modelKey": "qwen2-5-omni-7b", "displayName": "Qwen2.5-Omni 7B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-12", "openWeights": true, "releaseDate": "2024-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-omni-7b", "modelKey": "qwen2-5-omni-7b", "displayName": "Qwen2.5-Omni 7B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-12", "openWeights": true, "releaseDate": "2024-12" } } ] }, { "id": "alibaba/qwen2-5-vl-32b-instruct", "provider": "alibaba", "model": "qwen2-5-vl-32b-instruct", "displayName": "Qwen2.5 VL 32B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/qwen2-5-vl-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen2-5-vl-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 4.2 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 VL 32B Instruct" ], "families": [ "qwen" ], "releaseDate": "2025-03-15", "lastUpdated": "2025-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen2-5-vl-32b-instruct", "modelKey": "qwen2-5-vl-32b-instruct", "displayName": "Qwen2.5 VL 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-03-15", "openWeights": true, "releaseDate": "2025-03-15" } } ] }, { "id": "alibaba/qwen2-5-vl-72b-instruct", "provider": "alibaba", "model": "qwen2-5-vl-72b-instruct", "displayName": "Qwen2.5-VL 72B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "llmgateway" ], "aliases": [ "alibaba-cn/qwen2-5-vl-72b-instruct", "alibaba/qwen2-5-vl-72b-instruct", "llmgateway/qwen2-5-vl-72b-instruct" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.294, "output": 6.881 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.8, "output": 8.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen2-5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.8, "output": 8.4 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-VL 72B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-vl-72b-instruct", "modelKey": "qwen2-5-vl-72b-instruct", "displayName": "Qwen2.5-VL 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-vl-72b-instruct", "modelKey": "qwen2-5-vl-72b-instruct", "displayName": "Qwen2.5-VL 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen2-5-vl-72b-instruct", "modelKey": "qwen2-5-vl-72b-instruct", "displayName": "Qwen2.5-VL 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-5-vl-7b-instruct", "provider": "alibaba", "model": "qwen2-5-vl-7b-instruct", "displayName": "Qwen2.5-VL 7B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen2-5-vl-7b-instruct", "alibaba/qwen2-5-vl-7b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen2-5-vl-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.717 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen2-5-vl-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.05 } } ] }, "metadata": { "displayNames": [ "Qwen2.5-VL 7B Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-09", "lastUpdated": "2024-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-vl-7b-instruct", "modelKey": "qwen2-5-vl-7b-instruct", "displayName": "Qwen2.5-VL 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen2-5-vl-7b-instruct", "modelKey": "qwen2-5-vl-7b-instruct", "displayName": "Qwen2.5-VL 7B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "openWeights": true, "releaseDate": "2024-09" } } ] }, { "id": "alibaba/qwen2-72b-instruct", "provider": "alibaba", "model": "qwen2-72b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "alibaba/qwen2-7b-instruct", "provider": "alibaba", "model": "qwen2-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2-audio-7b-instruct", "provider": "alibaba", "model": "qwen2-audio-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sambanova" ], "aliases": [ "sambanova/Qwen2-Audio-7B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sambanova", "model": "sambanova/Qwen2-Audio-7B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 100 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Qwen2-Audio-7B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "alibaba/qwen2-vl-2b-instruct", "provider": "alibaba", "model": "qwen2-vl-2b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2-vl-72b-instruct", "provider": "alibaba", "model": "qwen2-vl-72b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "nebius" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct", "nebius/Qwen/Qwen2-VL-72B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "functionCalling": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2-VL-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2-VL-72B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen2-vl-7b-instruct", "provider": "alibaba", "model": "qwen2-vl-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "nebius" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct", "nebius/Qwen/Qwen2-VL-7B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2-VL-7B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.06 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2-VL-7B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen2.5-14b-instruct", "provider": "alibaba", "model": "qwen2.5-14b-instruct", "displayName": "Qwen/Qwen2.5-14B-Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "siliconflow", "siliconflow-cn" ], "aliases": [ "siliconflow-cn/Qwen/Qwen2.5-14B-Instruct", "siliconflow/Qwen/Qwen2.5-14B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 33000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-14B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-14B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen2.5-14B-Instruct" ], "families": [ "qwen" ], "releaseDate": "2024-09-18", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-14B-Instruct", "modelKey": "Qwen/Qwen2.5-14B-Instruct", "displayName": "Qwen/Qwen2.5-14B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-14B-Instruct", "modelKey": "Qwen/Qwen2.5-14B-Instruct", "displayName": "Qwen/Qwen2.5-14B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } } ] }, { "id": "alibaba/qwen2.5-32b-eva-v0.2", "provider": "alibaba", "model": "qwen2.5-32b-eva-v0.2", "displayName": "Qwen 2.5 32b EVA", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen2.5-32B-EVA-v0.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 24576, "inputTokens": 24576, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen2.5-32B-EVA-v0.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.493, "output": 0.493 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 32b EVA" ], "releaseDate": "2024-09-01", "lastUpdated": "2024-09-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen2.5-32B-EVA-v0.2", "modelKey": "Qwen2.5-32B-EVA-v0.2", "displayName": "Qwen 2.5 32b EVA", "metadata": { "lastUpdated": "2024-09-01", "openWeights": false, "releaseDate": "2024-09-01" } } ] }, { "id": "alibaba/qwen2.5-32b-instruct", "provider": "alibaba", "model": "qwen2.5-32b-instruct", "displayName": "Qwen/Qwen2.5-32B-Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "nebius", "siliconflow", "siliconflow-cn" ], "aliases": [ "nebius/Qwen/Qwen2.5-32B-Instruct", "siliconflow-cn/Qwen/Qwen2.5-32B-Instruct", "siliconflow/Qwen/Qwen2.5-32B-Instruct" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-32B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen2.5-32B-Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2024-09-19", "lastUpdated": "2025-11-25", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-32B-Instruct", "modelKey": "Qwen/Qwen2.5-32B-Instruct", "displayName": "Qwen/Qwen2.5-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-32B-Instruct", "modelKey": "Qwen/Qwen2.5-32B-Instruct", "displayName": "Qwen/Qwen2.5-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-32B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen2.5-32b-instruct-abliterated", "provider": "alibaba", "model": "qwen2.5-32b-instruct-abliterated", "displayName": "Qwen 2.5 32B Abliterated", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "huihui-ai/Qwen2.5-32B-Instruct-abliterated", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 32B Abliterated" ], "families": [ "qwen" ], "releaseDate": "2025-01-06", "lastUpdated": "2025-01-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "huihui-ai/Qwen2.5-32B-Instruct-abliterated", "modelKey": "huihui-ai/Qwen2.5-32B-Instruct-abliterated", "displayName": "Qwen 2.5 32B Abliterated", "family": "qwen", "metadata": { "lastUpdated": "2025-01-06", "openWeights": false, "releaseDate": "2025-01-06" } } ] }, { "id": "alibaba/qwen2.5-72b-instruct", "provider": "alibaba", "model": "qwen2.5-72b-instruct", "displayName": "Qwen 2.5 72B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "chutes", "deepinfra", "hyperbolic", "nebius", "siliconflow", "siliconflow-cn" ], "aliases": [ "abacus/Qwen/Qwen2.5-72B-Instruct", "chutes/Qwen/Qwen2.5-72B-Instruct", "deepinfra/Qwen/Qwen2.5-72B-Instruct", "hyperbolic/Qwen/Qwen2.5-72B-Instruct", "nebius/Qwen/Qwen2.5-72B-Instruct", "siliconflow-cn/Qwen/Qwen2.5-72B-Instruct", "siliconflow/Qwen/Qwen2.5-72B-Instruct" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.38 } }, { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14945, "input": 0.2989, "output": 1.1957 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.39 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 72B Instruct", "Qwen/Qwen2.5-72B-Instruct", "Qwen2.5 72B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "Qwen/Qwen2.5-72B-Instruct", "modelKey": "Qwen/Qwen2.5-72B-Instruct", "displayName": "Qwen 2.5 72B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen2.5-72B-Instruct", "modelKey": "Qwen/Qwen2.5-72B-Instruct", "displayName": "Qwen2.5 72B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-72B-Instruct", "modelKey": "Qwen/Qwen2.5-72B-Instruct", "displayName": "Qwen/Qwen2.5-72B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-72B-Instruct", "modelKey": "Qwen/Qwen2.5-72B-Instruct", "displayName": "Qwen/Qwen2.5-72B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-72B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen2.5-72B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-72B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen2.5-72b-instruct-128k", "provider": "alibaba", "model": "qwen2.5-72b-instruct-128k", "displayName": "Qwen/Qwen2.5-72B-Instruct-128K", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "siliconflow", "siliconflow-cn" ], "aliases": [ "siliconflow-cn/Qwen/Qwen2.5-72B-Instruct-128K", "siliconflow/Qwen/Qwen2.5-72B-Instruct-128K" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-72B-Instruct-128K", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-72B-Instruct-128K", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen2.5-72B-Instruct-128K" ], "families": [ "qwen" ], "releaseDate": "2024-09-18", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-72B-Instruct-128K", "modelKey": "Qwen/Qwen2.5-72B-Instruct-128K", "displayName": "Qwen/Qwen2.5-72B-Instruct-128K", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-72B-Instruct-128K", "modelKey": "Qwen/Qwen2.5-72B-Instruct-128K", "displayName": "Qwen/Qwen2.5-72B-Instruct-128K", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } } ] }, { "id": "alibaba/qwen2.5-72b-instruct-turbo", "provider": "alibaba", "model": "qwen2.5-72b-instruct-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "alibaba/qwen2.5-7b-instruct", "provider": "alibaba", "model": "qwen2.5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "deepinfra", "novita", "novita-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "deepinfra/Qwen/Qwen2.5-7B-Instruct", "novita-ai/qwen/qwen2.5-7b-instruct", "novita/qwen/qwen2.5-7b-instruct", "siliconflow-cn/Qwen/Qwen2.5-7B-Instruct", "siliconflow/Qwen/Qwen2.5-7B-Instruct" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 33000, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "functionCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen2.5-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.07 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-7B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-7B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-7B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen2.5-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.07 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen2.5-7B-Instruct", "Qwen2.5 7B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen2.5-7b-instruct", "modelKey": "qwen/qwen2.5-7b-instruct", "displayName": "Qwen2.5 7B Instruct", "metadata": { "lastUpdated": "2025-04-16", "openWeights": true, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-7B-Instruct", "modelKey": "Qwen/Qwen2.5-7B-Instruct", "displayName": "Qwen/Qwen2.5-7B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-7B-Instruct", "modelKey": "Qwen/Qwen2.5-7B-Instruct", "displayName": "Qwen/Qwen2.5-7B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-7B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen2.5-7b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2.5-7b-instruct-turbo", "provider": "alibaba", "model": "qwen2.5-7b-instruct-turbo", "displayName": "Qwen 2.5 7B Instruct Turbo", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "together_ai", "togetherai" ], "aliases": [ "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo", "togetherai/Qwen/Qwen2.5-7B-Instruct-Turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen2.5-7B-Instruct-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen 2.5 7B Instruct Turbo" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen2.5-7B-Instruct-Turbo", "modelKey": "Qwen/Qwen2.5-7B-Instruct-Turbo", "displayName": "Qwen 2.5 7B Instruct Turbo", "family": "qwen", "metadata": { "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "alibaba/qwen2.5-coder-32b-instruct", "provider": "alibaba", "model": "qwen2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "chutes", "cloudflare-ai-gateway", "cloudflare-workers-ai", "hyperbolic", "nano-gpt", "nscale", "nvidia", "ovhcloud", "siliconflow", "siliconflow-cn", "synthetic" ], "aliases": [ "chutes/Qwen/Qwen2.5-Coder-32B-Instruct", "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "cloudflare-workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "nano-gpt/qwen/Qwen2.5-Coder-32B-Instruct", "nscale/Qwen/Qwen2.5-Coder-32B-Instruct", "nvidia/qwen/qwen2.5-coder-32b-instruct", "ovhcloud/Qwen2.5-Coder-32B-Instruct", "siliconflow-cn/Qwen/Qwen2.5-Coder-32B-Instruct", "siliconflow/Qwen/Qwen2.5-Coder-32B-Instruct", "synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 128000, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0136, "input": 0.0272, "output": 0.1087 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 1 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/qwen/qwen2.5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } }, { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen2.5-coder-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.2 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Qwen2.5-Coder-32B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.87, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 Coder 32B Instruct", "Qwen 2.5 Coder 32b", "Qwen/Qwen2.5-Coder-32B-Instruct", "Qwen2.5 Coder 32B Instruct", "Qwen2.5 Coder 32b Instruct", "Qwen2.5-Coder-32B-Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "modelKey": "Qwen/Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "modelKey": "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "displayName": "Qwen 2.5 Coder 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/qwen/qwen2.5-coder-32b-instruct", "modelKey": "@cf/qwen/qwen2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-02-27", "openWeights": true, "releaseDate": "2025-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen2.5-Coder-32B-Instruct", "modelKey": "qwen/Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen 2.5 Coder 32b", "metadata": { "lastUpdated": "2025-07-03", "openWeights": false, "releaseDate": "2025-07-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen2.5-coder-32b-instruct", "modelKey": "qwen/qwen2.5-coder-32b-instruct", "displayName": "Qwen2.5 Coder 32b Instruct", "metadata": { "lastUpdated": "2024-11-06", "openWeights": true, "releaseDate": "2024-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "modelKey": "Qwen/Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen/Qwen2.5-Coder-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-11-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "modelKey": "Qwen/Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen/Qwen2.5-Coder-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-11-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:Qwen/Qwen2.5-Coder-32B-Instruct", "modelKey": "hf:Qwen/Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen2.5-Coder-32B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-11-11", "openWeights": true, "releaseDate": "2024-11-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-32B-Instruct", "mode": "chat", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Qwen2.5-Coder-32B-Instruct", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct" } } ] }, { "id": "alibaba/qwen2.5-coder-3b-instruct", "provider": "alibaba", "model": "qwen2.5-coder-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nscale" ], "aliases": [ "nscale/Qwen/Qwen2.5-Coder-3B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0.03 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-3B-Instruct", "mode": "chat", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "alibaba/qwen2.5-coder-7b", "provider": "alibaba", "model": "qwen2.5-coder-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate", "nebius" ], "aliases": [ "llamagate/qwen2.5-coder-7b", "nebius/Qwen/Qwen2.5-Coder-7B" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/qwen2.5-coder-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.12 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-Coder-7B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0.03 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/qwen2.5-coder-7b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-Coder-7B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen2.5-coder-7b-fast", "provider": "alibaba", "model": "qwen2.5-coder-7b-fast", "displayName": "Qwen2.5 Coder 7B fast", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/qwen2.5-coder-7b-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "qwen2.5-coder-7b-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.09 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 Coder 7B fast" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-15", "lastUpdated": "2024-09-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen2.5-coder-7b-fast", "modelKey": "qwen2.5-coder-7b-fast", "displayName": "Qwen2.5 Coder 7B fast", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-15", "openWeights": false, "releaseDate": "2024-09-15" } } ] }, { "id": "alibaba/qwen2.5-coder-7b-instruct", "provider": "alibaba", "model": "qwen2.5-coder-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nscale" ], "aliases": [ "nscale/Qwen/Qwen2.5-Coder-7B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-7B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0.03 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/Qwen/Qwen2.5-Coder-7B-Instruct", "mode": "chat", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "alibaba/qwen2.5-vl-32b-instruct", "provider": "alibaba", "model": "qwen2.5-vl-32b-instruct", "displayName": "Qwen2.5 VL 32B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "chutes", "deepinfra", "io-net", "meganova", "siliconflow", "siliconflow-cn" ], "aliases": [ "chutes/Qwen/Qwen2.5-VL-32B-Instruct", "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "io-net/Qwen/Qwen2.5-VL-32B-Instruct", "meganova/Qwen/Qwen2.5-VL-32B-Instruct", "siliconflow-cn/Qwen/Qwen2.5-VL-32B-Instruct", "siliconflow/Qwen/Qwen2.5-VL-32B-Instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02715, "input": 0.0543, "output": 0.2174 } }, { "source": "models.dev", "provider": "io-net", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.1, "input": 0.05, "output": 0.22 } }, { "source": "models.dev", "provider": "meganova", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.27 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.27 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 VL 32B Instruct", "Qwen/Qwen2.5-VL-32B-Instruct", "Qwen2.5 VL 32B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-32B-Instruct", "displayName": "Qwen2.5 VL 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-32B-Instruct", "displayName": "Qwen 2.5 VL 32B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-11-01", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-32B-Instruct", "displayName": "Qwen2.5 VL 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-32B-Instruct", "displayName": "Qwen/Qwen2.5-VL-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-VL-32B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-32B-Instruct", "displayName": "Qwen/Qwen2.5-VL-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-03-24" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2.5-vl-72b-instruct", "provider": "alibaba", "model": "qwen2.5-vl-72b-instruct", "displayName": "Qwen2.5-VL-72B-Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "nebius", "novita", "novita-ai", "openrouter", "ovhcloud", "qiniu-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "kilo/qwen/qwen2.5-vl-72b-instruct", "nano-gpt/TEE/qwen2.5-vl-72b-instruct", "nebius/Qwen/Qwen2.5-VL-72B-Instruct", "novita-ai/qwen/qwen2.5-vl-72b-instruct", "novita/qwen/qwen2.5-vl-72b-instruct", "openrouter/qwen/qwen2.5-vl-72b-instruct", "ovhcloud/Qwen2.5-VL-72B-Instruct", "ovhcloud/qwen2.5-vl-72b-instruct", "qiniu-ai/qwen2.5-vl-72b-instruct", "siliconflow-cn/Qwen/Qwen2.5-VL-72B-Instruct", "siliconflow/Qwen/Qwen2.5-VL-72B-Instruct" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "supports1MContext": false, "responseSchema": true, "toolChoice": false, "parallelFunctionCalling": false, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen2.5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.8, "output": 0.8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen2.5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.31, "input": 0.25, "output": 0.75 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen2.5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen2.5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 0.8, "output": 1 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen2.5-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.01, "output": 1.01 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.59 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-VL-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen2.5-vl-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Qwen2.5-VL-72B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.91, "output": 0.91 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen2.5-vl-72b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 0.8, "output": 1 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 VL 72B Instruct", "Qwen/Qwen2.5-VL-72B-Instruct", "Qwen2.5 VL 72B Instruct", "Qwen2.5 VL 72B TEE", "Qwen2.5-VL-72B-Instruct", "Qwen: Qwen2.5 VL 72B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-02-01", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen2.5-vl-72b-instruct", "modelKey": "qwen/qwen2.5-vl-72b-instruct", "displayName": "Qwen: Qwen2.5 VL 72B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen2.5-vl-72b-instruct", "modelKey": "TEE/qwen2.5-vl-72b-instruct", "displayName": "Qwen2.5 VL 72B TEE", "family": "qwen", "metadata": { "lastUpdated": "2025-02-01", "openWeights": false, "releaseDate": "2025-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-72B-Instruct", "displayName": "Qwen2.5-VL-72B-Instruct", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen2.5-vl-72b-instruct", "modelKey": "qwen/qwen2.5-vl-72b-instruct", "displayName": "Qwen2.5 VL 72B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-03-25", "openWeights": true, "releaseDate": "2025-03-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen2.5-vl-72b-instruct", "modelKey": "qwen/qwen2.5-vl-72b-instruct", "displayName": "Qwen2.5 VL 72B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-02-01", "openWeights": true, "releaseDate": "2025-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen2.5-vl-72b-instruct", "modelKey": "qwen2.5-vl-72b-instruct", "displayName": "Qwen2.5-VL-72B-Instruct", "metadata": { "lastUpdated": "2025-03-31", "openWeights": true, "releaseDate": "2025-03-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen2.5-vl-72b-instruct", "modelKey": "qwen2.5-vl-72b-instruct", "displayName": "Qwen 2.5 VL 72B Instruct", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-72B-Instruct", "displayName": "Qwen/Qwen2.5-VL-72B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-VL-72B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-72B-Instruct", "displayName": "Qwen/Qwen2.5-VL-72B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen2.5-VL-72B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen2.5-vl-72b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Qwen2.5-VL-72B-Instruct", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen2.5-vl-72b-instruct", "displayName": "Qwen: Qwen2.5 VL 72B Instruct", "metadata": { "canonicalSlug": "qwen/qwen2.5-vl-72b-instruct", "createdAt": "2025-02-01T11:45:11.000Z", "huggingFaceId": "Qwen/Qwen2.5-VL-72B-Instruct", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 128000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "alibaba/qwen2.5-vl-7b-instruct", "provider": "alibaba", "model": "qwen2.5-vl-7b-instruct", "displayName": "Qwen/Qwen2.5-VL-7B-Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "qiniu-ai", "siliconflow" ], "aliases": [ "qiniu-ai/qwen2.5-vl-7b-instruct", "siliconflow/Qwen/Qwen2.5-VL-7B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen2.5-VL-7B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "Qwen 2.5 VL 7B Instruct", "Qwen/Qwen2.5-VL-7B-Instruct" ], "families": [ "qwen" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen2.5-vl-7b-instruct", "modelKey": "qwen2.5-vl-7b-instruct", "displayName": "Qwen 2.5 VL 7B Instruct", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen2.5-VL-7B-Instruct", "modelKey": "Qwen/Qwen2.5-VL-7B-Instruct", "displayName": "Qwen/Qwen2.5-VL-7B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-28" } } ] }, { "id": "alibaba/qwen25-coder-32b-instruct", "provider": "alibaba", "model": "qwen25-coder-32b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/qwen25-coder-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/qwen25-coder-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/qwen25-coder-32b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen25-coder-7b", "provider": "alibaba", "model": "qwen25-coder-7b", "displayName": "Qwen2.5 Coder 7B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/qwen25-coder-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen25-coder-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "Qwen2.5 Coder 7B" ], "families": [ "qwen" ], "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen25-coder-7b", "modelKey": "qwen25-coder-7b", "displayName": "Qwen2.5 Coder 7B", "family": "qwen", "metadata": { "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } } ] }, { "id": "alibaba/qwen25-vl-72b-instruct", "provider": "alibaba", "model": "qwen25-vl-72b-instruct", "displayName": "Qwen25 VL 72b", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen25-vl-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen25-vl-72b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69989, "output": 0.69989 } } ] }, "metadata": { "displayNames": [ "Qwen25 VL 72b" ], "releaseDate": "2025-05-10", "lastUpdated": "2025-05-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen25-vl-72b-instruct", "modelKey": "qwen25-vl-72b-instruct", "displayName": "Qwen25 VL 72b", "metadata": { "lastUpdated": "2025-05-10", "openWeights": false, "releaseDate": "2025-05-10" } } ] }, { "id": "alibaba/qwen2p5-0p5b-instruct", "provider": "alibaba", "model": "qwen2p5-0p5b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-14b", "provider": "alibaba", "model": "qwen2p5-14b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-14b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-1p5b-instruct", "provider": "alibaba", "model": "qwen2p5-1p5b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-32b", "provider": "alibaba", "model": "qwen2p5-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-32b-instruct", "provider": "alibaba", "model": "qwen2p5-32b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-72b", "provider": "alibaba", "model": "qwen2p5-72b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-72b-instruct", "provider": "alibaba", "model": "qwen2p5-72b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-7b-instruct", "provider": "alibaba", "model": "qwen2p5-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-0p5b", "provider": "alibaba", "model": "qwen2p5-coder-0p5b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-0p5b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-0p5b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-14b", "provider": "alibaba", "model": "qwen2p5-coder-14b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-14b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-14b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-1p5b", "provider": "alibaba", "model": "qwen2p5-coder-1p5b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-1p5b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-1p5b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-32b", "provider": "alibaba", "model": "qwen2p5-coder-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-32b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-32b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "alibaba/qwen2p5-coder-32b-instruct-128k", "provider": "alibaba", "model": "qwen2p5-coder-32b-instruct-128k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-32b-instruct-32k-rope", "provider": "alibaba", "model": "qwen2p5-coder-32b-instruct-32k-rope", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-32b-instruct-64k", "provider": "alibaba", "model": "qwen2p5-coder-32b-instruct-64k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-3b", "provider": "alibaba", "model": "qwen2p5-coder-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-3b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-7b", "provider": "alibaba", "model": "qwen2p5-coder-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-coder-7b-instruct", "provider": "alibaba", "model": "qwen2p5-coder-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-math-72b-instruct", "provider": "alibaba", "model": "qwen2p5-math-72b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-vl-32b-instruct", "provider": "alibaba", "model": "qwen2p5-vl-32b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-vl-3b-instruct", "provider": "alibaba", "model": "qwen2p5-vl-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-vl-72b-instruct", "provider": "alibaba", "model": "qwen2p5-vl-72b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen2p5-vl-7b-instruct", "provider": "alibaba", "model": "qwen2p5-vl-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen3-0p6b", "provider": "alibaba", "model": "qwen3-0p6b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-0p6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-0p6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-0p6b", "mode": "chat" } ] }, { "id": "alibaba/qwen3-14b", "provider": "alibaba", "model": "qwen3-14b", "displayName": "Qwen3 14B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "deepinfra", "fireworks_ai", "kilo", "nano-gpt", "nebius", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "alibaba-cn/qwen3-14b", "alibaba/qwen3-14b", "deepinfra/Qwen/Qwen3-14B", "fireworks_ai/accounts/fireworks/models/qwen3-14b", "kilo/qwen/qwen3-14b", "nano-gpt/qwen/qwen3-14b", "nebius/Qwen/Qwen3-14B", "openrouter/qwen/qwen3-14b", "siliconflow-cn/Qwen/Qwen3-14B", "siliconflow/Qwen/Qwen3-14B" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 131702, "inputTokens": 41000, "maxTokens": 40960, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.574, "reasoningOutput": 1.434 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.4, "reasoningOutput": 4.2 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.06, "output": 0.24 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.24 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.24 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-14B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen3-14B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.24 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-14b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Qwen 3 14b", "Qwen/Qwen3-14B", "Qwen3 14B", "Qwen: Qwen3 14B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-14b", "modelKey": "qwen3-14b", "displayName": "Qwen3 14B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-14b", "modelKey": "qwen3-14b", "displayName": "Qwen3 14B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-14b", "modelKey": "qwen/qwen3-14b", "displayName": "Qwen: Qwen3 14B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-14b", "modelKey": "qwen/qwen3-14b", "displayName": "Qwen 3 14b", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-14b", "modelKey": "qwen/qwen3-14b", "displayName": "Qwen3 14B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-14B", "modelKey": "Qwen/Qwen3-14B", "displayName": "Qwen/Qwen3-14B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-14B", "modelKey": "Qwen/Qwen3-14B", "displayName": "Qwen/Qwen3-14B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-14B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-14b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen3-14B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-14b", "displayName": "Qwen: Qwen3 14B", "metadata": { "canonicalSlug": "qwen/qwen3-14b-04-28", "createdAt": "2025-04-28T21:41:18.000Z", "huggingFaceId": "Qwen/Qwen3-14B", "instructType": "qwen3", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-14b-04-28/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 40960, "max_completion_tokens": 40960, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-14b-instruct", "provider": "alibaba", "model": "qwen3-14b-instruct", "displayName": "OpenPipe Qwen3 14B Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "wandb" ], "aliases": [ "wandb/OpenPipe/Qwen3-14B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "wandb", "model": "OpenPipe/Qwen3-14B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.22 } } ] }, "metadata": { "displayNames": [ "OpenPipe Qwen3 14B Instruct" ], "families": [ "qwen" ], "releaseDate": "2025-04-29", "lastUpdated": "2026-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "OpenPipe/Qwen3-14B-Instruct", "modelKey": "OpenPipe/Qwen3-14B-Instruct", "displayName": "OpenPipe Qwen3 14B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-04-29" } } ] }, { "id": "alibaba/qwen3-1p7b", "provider": "alibaba", "model": "qwen3-1p7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-1p7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b", "mode": "chat" } ] }, { "id": "alibaba/qwen3-1p7b-fp8-draft", "provider": "alibaba", "model": "qwen3-1p7b-fp8-draft", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft", "mode": "chat" } ] }, { "id": "alibaba/qwen3-1p7b-fp8-draft-131072", "provider": "alibaba", "model": "qwen3-1p7b-fp8-draft-131072", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072", "mode": "chat" } ] }, { "id": "alibaba/qwen3-1p7b-fp8-draft-40960", "provider": "alibaba", "model": "qwen3-1p7b-fp8-draft-40960", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960", "mode": "chat" } ] }, { "id": "alibaba/qwen3-235b", "provider": "alibaba", "model": "qwen3-235b", "displayName": "Qwen3-235B-A22B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "iflowcn" ], "aliases": [ "iflowcn/qwen3-235b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-235b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3-235B-A22B" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-235b", "modelKey": "qwen3-235b", "displayName": "Qwen3-235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "alibaba/qwen3-235b-2507-cs", "provider": "alibaba", "model": "qwen3-235b-2507-cs", "displayName": "qwen3-235b-2507-cs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/cerebras/qwen3-235b-2507-cs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-235b-2507-cs" ], "statuses": [ "deprecated" ], "releaseDate": "2025-08-06", "lastUpdated": "2025-08-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "cerebras/qwen3-235b-2507-cs", "modelKey": "cerebras/qwen3-235b-2507-cs", "displayName": "qwen3-235b-2507-cs", "status": "deprecated", "metadata": { "lastUpdated": "2025-08-06", "openWeights": false, "releaseDate": "2025-08-06" } } ] }, { "id": "alibaba/qwen3-235b-a22b", "provider": "alibaba", "model": "qwen3-235b-a22b", "displayName": "Qwen3 235B-A22B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "alibaba", "alibaba-cn", "deepinfra", "fireworks_ai", "hyperbolic", "kilo", "nano-gpt", "nebius", "openrouter", "qiniu-ai", "siliconflow" ], "aliases": [ "302ai/qwen3-235b-a22b", "alibaba-cn/qwen3-235b-a22b", "alibaba/qwen3-235b-a22b", "deepinfra/Qwen/Qwen3-235B-A22B", "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b", "hyperbolic/Qwen/Qwen3-235B-A22B", "kilo/qwen/qwen3-235b-a22b", "nano-gpt/qwen/qwen3-235b-a22b", "nebius/Qwen/Qwen3-235B-A22B", "openrouter/qwen/qwen3-235b-a22b", "qiniu-ai/qwen3-235b-a22b", "siliconflow/Qwen/Qwen3-235B-A22B" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 2.86 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 1.147, "reasoningOutput": 2.868 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8, "reasoningOutput": 8.4 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.455, "output": 1.82 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.455, "output": 1.82 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-235B-A22B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.42 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.54 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen3-235B-A22B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen3-235B-A22B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.455, "output": 1.82 } } ] }, "metadata": { "displayNames": [ "Qwen 3 235B A22B", "Qwen 3 235b A22B", "Qwen/Qwen3-235B-A22B", "Qwen3 235B-A22B", "Qwen3-235B-A22B", "Qwen: Qwen3 235B A22B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen3-235b-a22b", "modelKey": "qwen3-235b-a22b", "displayName": "Qwen3-235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-29", "openWeights": false, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-235b-a22b", "modelKey": "qwen3-235b-a22b", "displayName": "Qwen3 235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-235b-a22b", "modelKey": "qwen3-235b-a22b", "displayName": "Qwen3 235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-235b-a22b", "modelKey": "qwen/qwen3-235b-a22b", "displayName": "Qwen: Qwen3 235B A22B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-235b-a22b", "modelKey": "qwen/qwen3-235b-a22b", "displayName": "Qwen 3 235b A22B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": false, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-235b-a22b", "modelKey": "qwen/qwen3-235b-a22b", "displayName": "Qwen3 235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 38912 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-235b-a22b", "modelKey": "qwen3-235b-a22b", "displayName": "Qwen 3 235B A22B", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-235B-A22B", "modelKey": "Qwen/Qwen3-235B-A22B", "displayName": "Qwen/Qwen3-235B-A22B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/Qwen/Qwen3-235B-A22B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen3-235B-A22B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b", "displayName": "Qwen: Qwen3 235B A22B", "metadata": { "canonicalSlug": "qwen/qwen3-235b-a22b-04-28", "createdAt": "2025-04-28T21:29:17.000Z", "huggingFaceId": "Qwen/Qwen3-235B-A22B", "instructType": "qwen3", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-235b-a22b-2507", "provider": "alibaba", "model": "qwen3-235b-a22b-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen3-235b-a22b-2507", "openrouter/qwen/qwen3-235b-a22b-2507" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-235b-a22b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.071, "output": 0.1 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3-235b-a22b-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.071, "output": 0.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-2507", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B Instruct 2507", "Qwen: Qwen3 235B A22B Instruct 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-04", "lastUpdated": "2026-01", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-235b-a22b-2507", "modelKey": "qwen/qwen3-235b-a22b-2507", "displayName": "Qwen: Qwen3 235B A22B Instruct 2507", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-235b-a22b-2507", "modelKey": "qwen/qwen3-235b-a22b-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-07-21", "openWeights": true, "releaseDate": "2025-07-21" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3-235b-a22b-2507", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-2507", "displayName": "Qwen: Qwen3 235B A22B Instruct 2507", "metadata": { "canonicalSlug": "qwen/qwen3-235b-a22b-07-25", "createdAt": "2025-07-21T17:39:15.000Z", "huggingFaceId": "Qwen/Qwen3-235B-A22B-Instruct-2507", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-235b-a22b-fp8", "provider": "alibaba", "model": "qwen3-235b-a22b-fp8", "displayName": "Qwen3 235B A22B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "jiekou", "llmgateway", "novita", "novita-ai" ], "aliases": [ "jiekou/qwen/qwen3-235b-a22b-fp8", "llmgateway/qwen3-235b-a22b-fp8", "novita-ai/qwen/qwen3-235b-a22b-fp8", "novita/qwen/qwen3-235b-a22b-fp8" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 40960, "maxTokens": 20000, "outputTokens": 20000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-235b-a22b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-235b-a22b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-235b-a22b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B", "Qwen3 235B A22B FP8" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-235b-a22b-fp8", "modelKey": "qwen/qwen3-235b-a22b-fp8", "displayName": "Qwen3 235B A22B", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-235b-a22b-fp8", "modelKey": "qwen3-235b-a22b-fp8", "displayName": "Qwen3 235B A22B FP8", "family": "qwen", "metadata": { "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-235b-a22b-fp8", "modelKey": "qwen/qwen3-235b-a22b-fp8", "displayName": "Qwen3 235B A22B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-fp8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-235b-a22b-fp8-tput", "provider": "alibaba", "model": "qwen3-235b-a22b-fp8-tput", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" } } ] }, { "id": "alibaba/qwen3-235b-a22b-instruct", "provider": "alibaba", "model": "qwen3-235b-a22b-instruct", "displayName": "Qwen3-235B-A22B-Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "iflowcn" ], "aliases": [ "iflowcn/qwen3-235b-a22b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3-235B-A22B-Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-01", "lastUpdated": "2025-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-235b-a22b-instruct", "modelKey": "qwen3-235b-a22b-instruct", "displayName": "Qwen3-235B-A22B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } } ] }, { "id": "alibaba/qwen3-235b-a22b-instruct-2507", "provider": "alibaba", "model": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "cortecs", "crusoe", "deepinfra", "fireworks_ai", "friendli", "jiekou", "llmgateway", "meganova", "modelscope", "nano-gpt", "nebius", "novita", "novita-ai", "qiniu-ai", "replicate", "scaleway", "siliconflow", "siliconflow-cn", "submodel", "synthetic", "venice", "wandb" ], "aliases": [ "302ai/qwen3-235b-a22b-instruct-2507", "abacus/Qwen/Qwen3-235B-A22B-Instruct-2507", "cortecs/qwen3-235b-a22b-instruct-2507", "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "friendli/Qwen/Qwen3-235B-A22B-Instruct-2507", "jiekou/qwen/qwen3-235b-a22b-instruct-2507", "llmgateway/qwen3-235b-a22b-instruct-2507", "meganova/Qwen/Qwen3-235B-A22B-Instruct-2507", "modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507", "nano-gpt/qwen/Qwen3-235B-A22B-Instruct-2507", "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507", "novita-ai/qwen/qwen3-235b-a22b-instruct-2507", "novita/qwen/qwen3-235b-a22b-instruct-2507", "qiniu-ai/qwen3-235b-a22b-instruct-2507", "replicate/qwen/qwen3-235b-a22b-instruct-2507", "scaleway/qwen3-235b-a22b-instruct-2507", "siliconflow-cn/Qwen/Qwen3-235B-A22B-Instruct-2507", "siliconflow/Qwen/Qwen3-235B-A22B-Instruct-2507", "submodel/Qwen/Qwen3-235B-A22B-Instruct-2507", "synthetic/hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "venice/qwen3-235b-a22b-instruct-2507", "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507" ], "mergedProviderModelRecords": 24, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "functionCalling": true, "parallelFunctionCalling": true, "systemMessages": true, "toolChoice": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.143 } }, { "source": "models.dev", "provider": "abacus", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.6 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.062, "output": 0.408 } }, { "source": "models.dev", "provider": "friendli", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.8 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.58 } }, { "source": "models.dev", "provider": "meganova", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.6 } }, { "source": "models.dev", "provider": "modelscope", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.5 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.58 } }, { "source": "models.dev", "provider": "scaleway", "model": "qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 2.25, "reasoningOutput": 8.4 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.6 } }, { "source": "models.dev", "provider": "submodel", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.3 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "venice", "model": "qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.75 } }, { "source": "models.dev", "provider": "wandb", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.6 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.58 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/qwen/qwen3-235b-a22b-instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.264, "output": 1.06 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10000, "output": 10000 } } ] }, "metadata": { "displayNames": [ "Qwen 3 235B A22B Instruct 2507", "Qwen 3 235B Instruct", "Qwen 3 235b A22B 2507", "Qwen/Qwen3-235B-A22B-Instruct-2507", "Qwen3 235B A22B Instruct", "Qwen3 235B A22B Instruct (2507)", "Qwen3 235B A22B Instruct 2507", "Qwen3 235b A22B Instruct 2507", "qwen3-235b-a22b-instruct-2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "providerModelRecordCount": 24 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "qwen3-235b-a22b-instruct-2507", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-30", "openWeights": false, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-01-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-235b-a22b-instruct-2507", "modelKey": "qwen/qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct (2507)", "family": "qwen", "metadata": { "lastUpdated": "2025-07-08", "openWeights": true, "releaseDate": "2025-07-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-21", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen 3 235b A22B 2507", "metadata": { "lastUpdated": "2025-07-25", "openWeights": false, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-10-04", "openWeights": false, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-235b-a22b-instruct-2507", "modelKey": "qwen/qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-22", "openWeights": true, "releaseDate": "2025-07-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235b A22B Instruct 2507", "metadata": { "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen/Qwen3-235B-A22B-Instruct-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen/Qwen3-235B-A22B-Instruct-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2025-08-23", "openWeights": true, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen 3 235B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-21", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-235b-a22b-instruct-2507", "modelKey": "qwen3-235b-a22b-instruct-2507", "displayName": "Qwen 3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3 235B A22B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-instruct-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/qwen/qwen3-235b-a22b-instruct-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507", "mode": "chat" } ] }, { "id": "alibaba/qwen3-235b-a22b-instruct-2507-maas", "provider": "alibaba", "model": "qwen3-235b-a22b-instruct-2507-maas", "displayName": "Qwen3 235B A22B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-qwen_models" ], "aliases": [ "google-vertex/qwen/qwen3-235b-a22b-instruct-2507-maas", "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "qwen/qwen3-235b-a22b-instruct-2507-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-08-13", "lastUpdated": "2025-08-13", "supportedRegions": [ "global", "us-south1" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "qwen/qwen3-235b-a22b-instruct-2507-maas", "modelKey": "qwen/qwen3-235b-a22b-instruct-2507-maas", "displayName": "Qwen3 235B A22B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-08-13", "openWeights": true, "releaseDate": "2025-08-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedRegions": [ "global", "us-south1" ] } } ] }, { "id": "alibaba/qwen3-235b-a22b-instruct-2507-tee", "provider": "alibaba", "model": "qwen3-235b-a22b-instruct-2507-tee", "displayName": "Qwen3 235B A22B Instruct 2507 TEE", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes", "nano-gpt" ], "aliases": [ "chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "nano-gpt/qwen/Qwen3-235B-A22B-Instruct-2507-TEE" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.1, "output": 0.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Qwen 3 235b A22B 2507 (TEE)", "Qwen3 235B A22B Instruct 2507 TEE" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "displayName": "Qwen3 235B A22B Instruct 2507 TEE", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "modelKey": "qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "displayName": "Qwen 3 235b A22B 2507 (TEE)", "metadata": { "lastUpdated": "2025-07-25", "openWeights": false, "releaseDate": "2025-07-25" } } ] }, { "id": "alibaba/qwen3-235b-a22b-instruct-2507-tput", "provider": "alibaba", "model": "qwen3-235b-a22b-instruct-2507-tput", "displayName": "Qwen3 235B A22B Instruct 2507 FP8", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "together_ai", "togetherai" ], "aliases": [ "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B Instruct 2507 FP8" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-25", "lastUpdated": "2025-07-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "modelKey": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "displayName": "Qwen3 235B A22B Instruct 2507 FP8", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" } } ] }, { "id": "alibaba/qwen3-235b-a22b-thinking", "provider": "alibaba", "model": "qwen3-235b-a22b-thinking", "displayName": "Qwen3 235B A22B Thinking", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "helicone", "vercel" ], "aliases": [ "helicone/qwen3-235b-a22b-thinking", "vercel/alibaba/qwen3-235b-a22b-thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "outputTokens": 81920, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "qwen3-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.9000000000000004 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 4 } } ] }, "metadata": { "displayNames": [ "Qwen3 235B A22B Thinking", "Qwen3 235B A22B Thinking 2507" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-25", "lastUpdated": "2025-07-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-235b-a22b-thinking", "modelKey": "qwen3-235b-a22b-thinking", "displayName": "Qwen3 235B A22B Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-25", "openWeights": false, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-235b-a22b-thinking", "modelKey": "alibaba/qwen3-235b-a22b-thinking", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-09-24" } } ] }, { "id": "alibaba/qwen3-235b-a22b-thinking-2507", "provider": "alibaba", "model": "qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "chutes", "deepinfra", "fireworks_ai", "huggingface", "iflowcn", "io-net", "jiekou", "kilo", "llmgateway", "modelscope", "nano-gpt", "novita", "novita-ai", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "submodel", "synthetic", "together_ai", "venice", "wandb" ], "aliases": [ "chutes/Qwen/Qwen3-235B-A22B-Thinking-2507", "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507", "iflowcn/qwen3-235b-a22b-thinking-2507", "io-net/Qwen/Qwen3-235B-A22B-Thinking-2507", "jiekou/qwen/qwen3-235b-a22b-thinking-2507", "kilo/qwen/qwen3-235b-a22b-thinking-2507", "llmgateway/qwen3-235b-a22b-thinking-2507", "modelscope/Qwen/Qwen3-235B-A22B-Thinking-2507", "nano-gpt/qwen/Qwen3-235B-A22B-Thinking-2507", "novita-ai/qwen/qwen3-235b-a22b-thinking-2507", "novita/qwen/qwen3-235b-a22b-thinking-2507", "openrouter/qwen/qwen3-235b-a22b-thinking-2507", "qiniu-ai/qwen3-235b-a22b-thinking-2507", "siliconflow-cn/Qwen/Qwen3-235B-A22B-Thinking-2507", "siliconflow/Qwen/Qwen3-235B-A22B-Thinking-2507", "submodel/Qwen/Qwen3-235B-A22B-Thinking-2507", "synthetic/hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507", "venice/qwen3-235b-a22b-thinking-2507", "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "input": 0.11, "output": 0.6 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 3 } }, { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "io-net", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "cacheWrite": 0.22, "input": 0.11, "output": 0.6 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 3 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "modelscope", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 3 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.6 } }, { "source": "models.dev", "provider": "submodel", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 3 } }, { "source": "models.dev", "provider": "venice", "model": "qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 3.5 } }, { "source": "models.dev", "provider": "wandb", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.9 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 3 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.11, "output": 0.6 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 3 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10000, "output": 10000 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-thinking-2507", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Qwen 3 235B A22B Thinking 2507", "Qwen 3 235B Thinking", "Qwen 3 235b A22B 2507 Thinking", "Qwen/Qwen3-235B-A22B-Thinking-2507", "Qwen3 235B A22B Thinking (2507)", "Qwen3 235B A22B Thinking 2507", "Qwen3 235B A22b Thinking 2507", "Qwen3-235B-A22B-Thinking", "Qwen3-235B-A22B-Thinking-2507", "Qwen: Qwen3 235B A22B Thinking 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-235b-a22b-thinking-2507", "modelKey": "qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen 3 235B Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-235b-a22b-thinking-2507", "modelKey": "qwen/qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22b Thinking 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-235b-a22b-thinking-2507", "modelKey": "qwen/qwen3-235b-a22b-thinking-2507", "displayName": "Qwen: Qwen3 235B A22B Thinking 2507", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-235b-a22b-thinking-2507", "modelKey": "qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22B Thinking (2507)", "family": "qwen", "metadata": { "lastUpdated": "2025-07-08", "openWeights": true, "releaseDate": "2025-07-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen 3 235b A22B 2507 Thinking", "metadata": { "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-235b-a22b-thinking-2507", "modelKey": "qwen/qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22b Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-235b-a22b-thinking-2507", "modelKey": "qwen/qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-235b-a22b-thinking-2507", "modelKey": "qwen3-235b-a22b-thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "metadata": { "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen/Qwen3-235B-A22B-Thinking-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen/Qwen3-235B-A22B-Thinking-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "lastUpdated": "2025-08-23", "openWeights": true, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-235b-a22b-thinking-2507", "modelKey": "qwen3-235b-a22b-thinking-2507", "displayName": "Qwen 3 235B A22B Thinking 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-04-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-235b-a22b-thinking-2507", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3-235b-a22b-thinking-2507", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-thinking-2507", "displayName": "Qwen: Qwen3 235B A22B Thinking 2507", "metadata": { "canonicalSlug": "qwen/qwen3-235b-a22b-thinking-2507", "createdAt": "2025-07-25T13:19:17.000Z", "huggingFaceId": "Qwen/Qwen3-235B-A22B-Thinking-2507", "instructType": "qwen3", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-235b-a22b-thinking-2507-fast", "provider": "alibaba", "model": "qwen3-235b-a22b-thinking-2507-fast", "displayName": "Qwen3-235B-A22B-Thinking-2507-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "Qwen3-235B-A22B-Thinking-2507-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-25", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast", "modelKey": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast", "displayName": "Qwen3-235B-A22B-Thinking-2507-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-07-25" } } ] }, { "id": "alibaba/qwen3-30b-a3b", "provider": "alibaba", "model": "qwen3-30b-a3b", "displayName": "Qwen3-30B-A3B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "chutes", "dashscope", "deepinfra", "fireworks_ai", "helicone", "kilo", "nano-gpt", "nebius", "openrouter", "qiniu-ai" ], "aliases": [ "302ai/qwen3-30b-a3b", "chutes/Qwen/Qwen3-30B-A3B", "dashscope/qwen3-30b-a3b", "deepinfra/Qwen/Qwen3-30B-A3B", "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b", "helicone/qwen3-30b-a3b", "kilo/qwen/qwen3-30b-a3b", "nano-gpt/qwen/qwen3-30b-a3b", "nebius/Qwen/Qwen3-30B-A3B", "openrouter/qwen/qwen3-30b-a3b", "qiniu-ai/qwen3-30b-a3b" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen3-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 1.08 } }, { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-30B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.06, "output": 0.22 } }, { "source": "models.dev", "provider": "helicone", "model": "qwen3-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.29 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.08, "output": 0.28 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.5 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-30b-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-30B-A3B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.29 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen3-30B-A3B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Qwen3 30B A3B", "Qwen3-30B-A3B", "Qwen: Qwen3 30B A3B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen3-30b-a3b", "modelKey": "qwen3-30b-a3b", "displayName": "Qwen3-30B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-29", "openWeights": false, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-30B-A3B", "modelKey": "Qwen/Qwen3-30B-A3B", "displayName": "Qwen3 30B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-30b-a3b", "modelKey": "qwen3-30b-a3b", "displayName": "Qwen3 30B A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-30b-a3b", "modelKey": "qwen/qwen3-30b-a3b", "displayName": "Qwen: Qwen3 30B A3B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-30b-a3b", "modelKey": "qwen/qwen3-30b-a3b", "displayName": "Qwen3 30B A3B", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-30b-a3b", "modelKey": "qwen/qwen3-30b-a3b", "displayName": "Qwen3 30B A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-30b-a3b", "modelKey": "qwen3-30b-a3b", "displayName": "Qwen3 30B A3B", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-30b-a3b", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-30B-A3B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen3-30B-A3B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b", "displayName": "Qwen: Qwen3 30B A3B", "metadata": { "canonicalSlug": "qwen/qwen3-30b-a3b-04-28", "createdAt": "2025-04-28T22:16:44.000Z", "huggingFaceId": "Qwen/Qwen3-30B-A3B", "instructType": "qwen3", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 40960, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-30b-a3b-2507", "provider": "alibaba", "model": "qwen3-30b-a3b-2507", "displayName": "Qwen3 30B A3B 2507", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "lmstudio" ], "aliases": [ "lmstudio/qwen/qwen3-30b-a3b-2507" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lmstudio", "model": "qwen/qwen3-30b-a3b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3 30B A3B 2507" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lmstudio", "providerName": "LMStudio", "providerApi": "http://127.0.0.1:1234/v1", "providerDoc": "https://lmstudio.ai/models", "model": "qwen/qwen3-30b-a3b-2507", "modelKey": "qwen/qwen3-30b-a3b-2507", "displayName": "Qwen3 30B A3B 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } } ] }, { "id": "alibaba/qwen3-30b-a3b-fp8", "provider": "alibaba", "model": "qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3B FP8", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "jiekou", "llmgateway", "novita", "novita-ai" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "jiekou/qwen/qwen3-30b-a3b-fp8", "llmgateway/qwen3-30b-a3b-fp8", "novita-ai/qwen/qwen3-30b-a3b-fp8", "novita/qwen/qwen3-30b-a3b-fp8" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 40960, "maxTokens": 20000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.051, "output": 0.34 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/qwen/qwen3-30b-a3b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0509, "output": 0.335 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-30b-a3b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.45 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-30b-a3b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-30b-a3b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.45 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-30b-a3b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.45 } } ] }, "metadata": { "displayNames": [ "Qwen3 30B A3B", "Qwen3 30B A3B FP8", "Qwen3 30B A3b fp8" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "modelKey": "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3B FP8", "family": "qwen", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/qwen/qwen3-30b-a3b-fp8", "modelKey": "@cf/qwen/qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3b fp8", "family": "qwen", "metadata": { "lastUpdated": "2025-04-30", "openWeights": true, "releaseDate": "2025-04-30", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-30b-a3b-fp8", "modelKey": "qwen/qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-30b-a3b-fp8", "modelKey": "qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3B FP8", "family": "qwen", "metadata": { "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-30b-a3b-fp8", "modelKey": "qwen/qwen3-30b-a3b-fp8", "displayName": "Qwen3 30B A3B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-30b-a3b-fp8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-30b-a3b-instruct-2507", "provider": "alibaba", "model": "qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "clarifai", "fireworks_ai", "kilo", "llmgateway", "modelscope", "nano-gpt", "nearai", "nebius", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "wandb" ], "aliases": [ "clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "kilo/qwen/qwen3-30b-a3b-instruct-2507", "llmgateway/qwen3-30b-a3b-instruct-2507", "modelscope/Qwen/Qwen3-30B-A3B-Instruct-2507", "nano-gpt/TEE/qwen3-30b-a3b-instruct-2507", "nano-gpt/qwen3-30b-a3b-instruct-2507", "nearai/Qwen/Qwen3-30B-A3B-Instruct-2507", "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507", "openrouter/qwen/qwen3-30b-a3b-instruct-2507", "qiniu-ai/qwen3-30b-a3b-instruct-2507", "siliconflow-cn/Qwen/Qwen3-30B-A3B-Instruct-2507", "siliconflow/Qwen/Qwen3-30B-A3B-Instruct-2507", "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507" ], "mergedProviderModelRecords": 14, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.09, "output": 0.3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "modelscope", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.44999999999999996 } }, { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.55 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.125, "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04815, "output": 0.19305 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.3 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.3 } }, { "source": "models.dev", "provider": "wandb", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-instruct-2507", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04815, "output": 0.19305 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-30B-A3B-Instruct-2507", "Qwen3 30B A3B Instruct (2507)", "Qwen3 30B A3B Instruct 2507", "Qwen3 30B A3B Instruct 2507 TEE", "Qwen3 30B-A3B Instruct 2507", "Qwen3 30b A3b Instruct 2507", "Qwen3-30B-A3B-Instruct-2507", "Qwen: Qwen3 30B A3B Instruct 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-30", "lastUpdated": "2026-02-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 14 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "modelKey": "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-30b-a3b-instruct-2507", "modelKey": "qwen/qwen3-30b-a3b-instruct-2507", "displayName": "Qwen: Qwen3 30B A3B Instruct 2507", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-30b-a3b-instruct-2507", "modelKey": "qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30B A3B Instruct (2507)", "family": "qwen", "metadata": { "lastUpdated": "2025-07-08", "openWeights": true, "releaseDate": "2025-07-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3-30b-a3b-instruct-2507", "modelKey": "qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "metadata": { "lastUpdated": "2025-02-20", "openWeights": false, "releaseDate": "2025-02-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen3-30b-a3b-instruct-2507", "modelKey": "TEE/qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507 TEE", "family": "qwen", "metadata": { "lastUpdated": "2025-07-29", "openWeights": false, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen3 30B-A3B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen3-30B-A3B-Instruct-2507", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-30b-a3b-instruct-2507", "modelKey": "qwen/qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-30b-a3b-instruct-2507", "modelKey": "qwen3-30b-a3b-instruct-2507", "displayName": "Qwen3 30b A3b Instruct 2507", "metadata": { "lastUpdated": "2026-02-04", "openWeights": false, "releaseDate": "2026-02-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen/Qwen3-30B-A3B-Instruct-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen/Qwen3-30B-A3B-Instruct-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507", "displayName": "Qwen3 30B A3B Instruct 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-instruct-2507", "displayName": "Qwen: Qwen3 30B A3B Instruct 2507", "metadata": { "canonicalSlug": "qwen/qwen3-30b-a3b-instruct-2507", "createdAt": "2025-07-29T16:36:05.000Z", "huggingFaceId": "Qwen/Qwen3-30B-A3B-Instruct-2507", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 128000, "max_completion_tokens": 32000, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-30b-a3b-instruct-2507-fp8", "provider": "alibaba", "model": "qwen3-30b-a3b-instruct-2507-fp8", "displayName": "Qwen3 30B 2507", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.42 } } ] }, "metadata": { "displayNames": [ "Qwen3 30B 2507" ], "families": [ "qwen" ], "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", "modelKey": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", "displayName": "Qwen3 30B 2507", "family": "qwen", "metadata": { "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } } ] }, { "id": "alibaba/qwen3-30b-a3b-thinking-2507", "provider": "alibaba", "model": "qwen3-30b-a3b-thinking-2507", "displayName": "Qwen3 30B A3B Thinking 2507", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "clarifai", "fireworks_ai", "kilo", "llmgateway", "modelscope", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "kilo/qwen/qwen3-30b-a3b-thinking-2507", "llmgateway/qwen3-30b-a3b-thinking-2507", "modelscope/Qwen/Qwen3-30B-A3B-Thinking-2507", "openrouter/qwen/qwen3-30b-a3b-thinking-2507", "qiniu-ai/qwen3-30b-a3b-thinking-2507", "siliconflow-cn/Qwen/Qwen3-30B-A3B-Thinking-2507", "siliconflow/Qwen/Qwen3-30B-A3B-Thinking-2507" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.36, "output": 1.3 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-30b-a3b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.051, "output": 0.34 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-30b-a3b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "modelscope", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.08, "output": 0.4 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.3 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.3 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-thinking-2507", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "input": 0.08, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-30B-A3B-Thinking-2507", "Qwen3 30B A3B Thinking (2507)", "Qwen3 30B A3B Thinking 2507", "Qwen3 30b A3b Thinking 2507", "Qwen: Qwen3 30B A3B Thinking 2507" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-31", "lastUpdated": "2026-02-25", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "modelKey": "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "displayName": "Qwen3 30B A3B Thinking 2507", "family": "qwen", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-30b-a3b-thinking-2507", "modelKey": "qwen/qwen3-30b-a3b-thinking-2507", "displayName": "Qwen: Qwen3 30B A3B Thinking 2507", "metadata": { "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-30b-a3b-thinking-2507", "modelKey": "qwen3-30b-a3b-thinking-2507", "displayName": "Qwen3 30B A3B Thinking (2507)", "family": "qwen", "metadata": { "lastUpdated": "2025-07-08", "openWeights": true, "releaseDate": "2025-07-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Thinking-2507", "displayName": "Qwen3 30B A3B Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-30b-a3b-thinking-2507", "modelKey": "qwen/qwen3-30b-a3b-thinking-2507", "displayName": "Qwen3 30B A3B Thinking 2507", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-30b-a3b-thinking-2507", "modelKey": "qwen3-30b-a3b-thinking-2507", "displayName": "Qwen3 30b A3b Thinking 2507", "metadata": { "lastUpdated": "2026-02-04", "openWeights": false, "releaseDate": "2026-02-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Thinking-2507", "displayName": "Qwen/Qwen3-30B-A3B-Thinking-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-30B-A3B-Thinking-2507", "modelKey": "Qwen/Qwen3-30B-A3B-Thinking-2507", "displayName": "Qwen/Qwen3-30B-A3B-Thinking-2507", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-31" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-30b-a3b-thinking-2507", "displayName": "Qwen: Qwen3 30B A3B Thinking 2507", "metadata": { "canonicalSlug": "qwen/qwen3-30b-a3b-thinking-2507", "createdAt": "2025-08-28T16:39:52.000Z", "huggingFaceId": "Qwen/Qwen3-30B-A3B-Thinking-2507", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-32b", "provider": "alibaba", "model": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "alibaba", "alibaba-cn", "cortecs", "deepinfra", "fireworks_ai", "groq", "helicone", "iflowcn", "kilo", "llmgateway", "nano-gpt", "nebius", "openrouter", "ovhcloud", "qiniu-ai", "sambanova", "siliconflow", "siliconflow-cn" ], "aliases": [ "abacus/Qwen/Qwen3-32B", "alibaba-cn/qwen3-32b", "alibaba/qwen3-32b", "cortecs/qwen3-32b", "deepinfra/Qwen/Qwen3-32B", "fireworks_ai/accounts/fireworks/models/qwen3-32b", "groq/qwen/qwen3-32b", "helicone/qwen3-32b", "iflowcn/qwen3-32b", "kilo/qwen/qwen3-32b", "llmgateway/qwen3-32b", "nano-gpt/qwen/qwen3-32b", "nebius/Qwen/Qwen3-32B", "openrouter/qwen/qwen3-32b", "ovhcloud/Qwen3-32B", "ovhcloud/qwen3-32b", "qiniu-ai/qwen3-32b", "sambanova/Qwen3-32B", "siliconflow-cn/Qwen/Qwen3-32B", "siliconflow/Qwen/Qwen3-32B" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "structuredOutput": true, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "Qwen/Qwen3-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.29 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 1.147, "reasoningOutput": 2.868 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8, "reasoningOutput": 8.4 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.099, "output": 0.33 } }, { "source": "models.dev", "provider": "groq", "model": "qwen/qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.59 } }, { "source": "models.dev", "provider": "helicone", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.59 } }, { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.08, "output": 0.24 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8, "reasoningOutput": 8.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.125, "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.28 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.25 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.28 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "groq", "model": "groq/qwen/qwen3-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.29, "output": 0.59 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen3-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Qwen3-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.23 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/Qwen3-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-32b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Qwen 3 32b", "Qwen/Qwen3-32B", "Qwen3 32B", "Qwen3-32B", "Qwen: Qwen3 32B" ], "families": [ "qwen" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "Qwen/Qwen3-32B", "modelKey": "Qwen/Qwen3-32B", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "qwen/qwen3-32b", "modelKey": "qwen/qwen3-32b", "displayName": "Qwen3-32B", "family": "qwen", "status": "beta", "metadata": { "lastUpdated": "2025-06-12", "openWeights": true, "releaseDate": "2025-06-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "default" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3-32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-32b", "modelKey": "qwen/qwen3-32b", "displayName": "Qwen: Qwen3 32B", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-32b", "modelKey": "qwen/qwen3-32b", "displayName": "Qwen 3 32b", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-32B", "modelKey": "Qwen/Qwen3-32B", "displayName": "Qwen3-32B", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-32b", "modelKey": "qwen/qwen3-32b", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3-32B", "metadata": { "lastUpdated": "2025-07-16", "openWeights": true, "releaseDate": "2025-07-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-32b", "modelKey": "qwen3-32b", "displayName": "Qwen3 32B", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-32B", "modelKey": "Qwen/Qwen3-32B", "displayName": "Qwen/Qwen3-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-32B", "modelKey": "Qwen/Qwen3-32B", "displayName": "Qwen/Qwen3-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-32B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-32b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/qwen/qwen3-32b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen3-32B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Qwen3-32B", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Qwen3-32B", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-32b", "displayName": "Qwen: Qwen3 32B", "metadata": { "canonicalSlug": "qwen/qwen3-32b-04-28", "createdAt": "2025-04-28T21:32:25.000Z", "huggingFaceId": "Qwen/Qwen3-32B", "instructType": "qwen3", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-32b-04-28/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 40960, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-32b-cs", "provider": "alibaba", "model": "qwen3-32b-cs", "displayName": "qwen3-32b-cs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/cerebras/qwen3-32b-cs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-32b-cs" ], "statuses": [ "deprecated" ], "releaseDate": "2025-05-15", "lastUpdated": "2025-05-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "cerebras/qwen3-32b-cs", "modelKey": "cerebras/qwen3-32b-cs", "displayName": "qwen3-32b-cs", "status": "deprecated", "metadata": { "lastUpdated": "2025-05-15", "openWeights": false, "releaseDate": "2025-05-15" } } ] }, { "id": "alibaba/qwen3-32b-fp8", "provider": "alibaba", "model": "qwen3-32b-fp8", "displayName": "Qwen3 32B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "jiekou", "lambda_ai", "llmgateway", "novita", "novita-ai" ], "aliases": [ "jiekou/qwen/qwen3-32b-fp8", "lambda_ai/qwen3-32b-fp8", "llmgateway/qwen3-32b-fp8", "novita-ai/qwen/qwen3-32b-fp8", "novita/qwen/qwen3-32b-fp8" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-32b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.45 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-32b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-32b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.45 } }, { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/qwen3-32b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-32b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.45 } } ] }, "metadata": { "displayNames": [ "Qwen3 32B", "Qwen3 32B FP8" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-32b-fp8", "modelKey": "qwen/qwen3-32b-fp8", "displayName": "Qwen3 32B", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-32b-fp8", "modelKey": "qwen3-32b-fp8", "displayName": "Qwen3 32B FP8", "family": "qwen", "metadata": { "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-32b-fp8", "modelKey": "qwen/qwen3-32b-fp8", "displayName": "Qwen3 32B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/qwen3-32b-fp8", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-32b-fp8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-32b-tee", "provider": "alibaba", "model": "qwen3-32b-tee", "displayName": "Qwen3 32B TEE", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/Qwen/Qwen3-32B-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-32B-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.08, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Qwen3 32B TEE" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-32B-TEE", "modelKey": "Qwen/Qwen3-32B-TEE", "displayName": "Qwen3 32B TEE", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3-4b", "provider": "alibaba", "model": "qwen3-4b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "nebius" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-4b", "nebius/Qwen/Qwen3-4B" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "functionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/Qwen3-4B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-4b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/Qwen3-4B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "alibaba/qwen3-4b-fp8", "provider": "alibaba", "model": "qwen3-4b-fp8", "displayName": "Qwen3 4B FP8", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "novita", "novita-ai" ], "aliases": [ "llmgateway/qwen3-4b-fp8", "novita-ai/qwen/qwen3-4b-fp8", "novita/qwen/qwen3-4b-fp8" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 20000, "outputTokens": 20000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-4b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.03 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-4b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.03 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-4b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Qwen3 4B", "Qwen3 4B FP8" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-04-28", "lastUpdated": "2025-04-28", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-4b-fp8", "modelKey": "qwen3-4b-fp8", "displayName": "Qwen3 4B FP8", "family": "qwen", "metadata": { "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-4b-fp8", "modelKey": "qwen/qwen3-4b-fp8", "displayName": "Qwen3 4B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-4b-fp8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-4b-instruct-2507", "provider": "alibaba", "model": "qwen3-4b-instruct-2507", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507", "mode": "chat" } ] }, { "id": "alibaba/qwen3-4b-instruct-2507-gguf", "provider": "alibaba", "model": "qwen3-4b-instruct-2507-gguf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lemonade" ], "aliases": [ "lemonade/Qwen3-4B-Instruct-2507-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lemonade", "model": "lemonade/Qwen3-4B-Instruct-2507-GGUF", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lemonade", "model": "lemonade/Qwen3-4B-Instruct-2507-GGUF", "mode": "chat" } ] }, { "id": "alibaba/qwen3-5-35b-a3b", "provider": "alibaba", "model": "qwen3-5-35b-a3b", "displayName": "Qwen 3.5 35B A3B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen3-5-35b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen3-5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15625, "input": 0.3125, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 35B A3B" ], "families": [ "qwen" ], "releaseDate": "2026-02-25", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-5-35b-a3b", "modelKey": "qwen3-5-35b-a3b", "displayName": "Qwen 3.5 35B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-25", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "alibaba/qwen3-5-397b-a17b", "provider": "alibaba", "model": "qwen3-5-397b-a17b", "displayName": "Qwen 3.5 397B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen3-5-397b-a17b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen3-5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 4.5 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 397B" ], "families": [ "qwen" ], "releaseDate": "2026-02-16", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-5-397b-a17b", "modelKey": "qwen3-5-397b-a17b", "displayName": "Qwen 3.5 397B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "alibaba/qwen3-5-9b", "provider": "alibaba", "model": "qwen3-5-9b", "displayName": "Qwen 3.5 9B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen3-5-9b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen3-5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 9B" ], "families": [ "qwen" ], "releaseDate": "2026-03-05", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-5-9b", "modelKey": "qwen3-5-9b", "displayName": "Qwen 3.5 9B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "alibaba/qwen3-5-9b-mlx-4bit", "provider": "alibaba", "model": "qwen3-5-9b-mlx-4bit", "displayName": "Qwen 3.5 9B (MLX 4-bit)", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "atomic-chat" ], "aliases": [ "atomic-chat/Qwen3_5-9B-MLX-4bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "atomic-chat", "model": "Qwen3_5-9B-MLX-4bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 9B (MLX 4-bit)" ], "families": [ "qwen" ], "releaseDate": "2026-03-05", "lastUpdated": "2026-04-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "atomic-chat", "providerName": "Atomic Chat", "providerApi": "http://127.0.0.1:1337/v1", "providerDoc": "https://atomic.chat", "model": "Qwen3_5-9B-MLX-4bit", "modelKey": "Qwen3_5-9B-MLX-4bit", "displayName": "Qwen 3.5 9B (MLX 4-bit)", "family": "qwen", "metadata": { "lastUpdated": "2026-04-04", "openWeights": true, "releaseDate": "2026-03-05" } } ] }, { "id": "alibaba/qwen3-5-9b-q4-k-m", "provider": "alibaba", "model": "qwen3-5-9b-q4-k-m", "displayName": "Qwen 3.5 9B (Q4_K_M)", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "atomic-chat" ], "aliases": [ "atomic-chat/Qwen3_5-9B-Q4_K_M" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "atomic-chat", "model": "Qwen3_5-9B-Q4_K_M", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 9B (Q4_K_M)" ], "families": [ "qwen" ], "releaseDate": "2026-03-05", "lastUpdated": "2026-04-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "atomic-chat", "providerName": "Atomic Chat", "providerApi": "http://127.0.0.1:1337/v1", "providerDoc": "https://atomic.chat", "model": "Qwen3_5-9B-Q4_K_M", "modelKey": "Qwen3_5-9B-Q4_K_M", "displayName": "Qwen 3.5 9B (Q4_K_M)", "family": "qwen", "metadata": { "lastUpdated": "2026-04-04", "openWeights": true, "releaseDate": "2026-03-05" } } ] }, { "id": "alibaba/qwen3-6-27b", "provider": "alibaba", "model": "qwen3-6-27b", "displayName": "Qwen 3.6 27B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen3-6-27b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen3-6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.325, "output": 3.25 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 27B" ], "families": [ "qwen" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-6-27b", "modelKey": "qwen3-6-27b", "displayName": "Qwen 3.6 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "alibaba/qwen3-6-35b", "provider": "alibaba", "model": "qwen3-6-35b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/qwen3-6-35b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "qwen3-6-35b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 35B-A3B" ], "families": [ "qwen" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "qwen3-6-35b", "modelKey": "qwen3-6-35b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3-8b", "provider": "alibaba", "model": "qwen3-8b", "displayName": "Qwen3 8B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "fireworks_ai", "kilo", "llamagate", "nano-gpt", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "alibaba-cn/qwen3-8b", "alibaba/qwen3-8b", "fireworks_ai/accounts/fireworks/models/qwen3-8b", "kilo/qwen/qwen3-8b", "llamagate/qwen3-8b", "nano-gpt/qwen/Qwen3-8B", "openrouter/qwen/qwen3-8b", "siliconflow-cn/Qwen/Qwen3-8B", "siliconflow/Qwen/Qwen3-8B" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 131072, "inputTokens": 41000, "maxTokens": 40960, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.287, "reasoningOutput": 0.717 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.7, "reasoningOutput": 2.1 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.47, "output": 0.47 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.06 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.06 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "llamagate", "model": "llamagate/qwen3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.14 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-8b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen 3 8B", "Qwen/Qwen3-8B", "Qwen3 8B", "Qwen: Qwen3 8B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-8b", "modelKey": "qwen3-8b", "displayName": "Qwen3 8B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-8b", "modelKey": "qwen3-8b", "displayName": "Qwen3 8B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-8b", "modelKey": "qwen/qwen3-8b", "displayName": "Qwen: Qwen3 8B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-8B", "modelKey": "qwen/Qwen3-8B", "displayName": "Qwen 3 8B", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-8b", "modelKey": "qwen/qwen3-8b", "displayName": "Qwen3 8B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-04-28", "openWeights": true, "releaseDate": "2025-04-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-8B", "modelKey": "Qwen/Qwen3-8B", "displayName": "Qwen/Qwen3-8B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-8B", "modelKey": "Qwen/Qwen3-8B", "displayName": "Qwen/Qwen3-8B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-8b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/qwen3-8b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-8b", "displayName": "Qwen: Qwen3 8B", "metadata": { "canonicalSlug": "qwen/qwen3-8b-04-28", "createdAt": "2025-04-28T21:43:52.000Z", "huggingFaceId": "Qwen/Qwen3-8B", "instructType": "qwen3", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-8b-04-28/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 40960, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-8b-fp8", "provider": "alibaba", "model": "qwen3-8b-fp8", "displayName": "Qwen3 8B", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai" ], "aliases": [ "novita-ai/qwen/qwen3-8b-fp8", "novita/qwen/qwen3-8b-fp8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 20000, "outputTokens": 20000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-8b-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.035, "output": 0.138 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-8b-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.138 } } ] }, "metadata": { "displayNames": [ "Qwen3 8B" ], "modes": [ "chat" ], "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-8b-fp8", "modelKey": "qwen/qwen3-8b-fp8", "displayName": "Qwen3 8B", "metadata": { "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-8b-fp8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-asr-flash", "provider": "alibaba", "model": "qwen3-asr-flash", "displayName": "Qwen3-ASR Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen3-asr-flash", "alibaba/qwen3-asr-flash" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 53248, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-asr-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.032, "output": 0.032 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-asr-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.035, "output": 0.035 } } ] }, "metadata": { "displayNames": [ "Qwen3-ASR Flash" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-08", "lastUpdated": "2025-09-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-asr-flash", "modelKey": "qwen3-asr-flash", "displayName": "Qwen3-ASR Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-08", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-asr-flash", "modelKey": "qwen3-asr-flash", "displayName": "Qwen3-ASR Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-08", "openWeights": false, "releaseDate": "2025-09-08" } } ] }, { "id": "alibaba/qwen3-coder", "provider": "alibaba", "model": "qwen3-coder", "displayName": "Qwen3 Coder 480B A35B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fastrouter", "helicone", "kilo", "nano-gpt", "opencode", "openrouter", "vercel", "vercel_ai_gateway" ], "aliases": [ "fastrouter/qwen/qwen3-coder", "helicone/qwen3-coder", "kilo/qwen/qwen3-coder", "nano-gpt/qwen/qwen3-coder", "opencode/qwen3-coder", "openrouter/qwen/qwen3-coder", "vercel/alibaba/qwen3-coder", "vercel_ai_gateway/alibaba/qwen3-coder" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1048576, "inputTokens": 262144, "maxTokens": 262100, "outputTokens": 262100, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "qwen/qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "helicone", "model": "qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.95 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.022, "input": 0.22, "output": 1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.5 } }, { "source": "models.dev", "provider": "opencode", "model": "qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 1.8 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 7.5 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3-coder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.95 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen3-coder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Coder 480B", "Qwen3 Coder", "Qwen3 Coder 480B A35B", "Qwen3 Coder 480B A35B Instruct", "Qwen3 Coder 480B A35B Instruct Turbo", "Qwen: Qwen3 Coder 480B A35B" ], "families": [ "qwen" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "qwen/qwen3-coder", "modelKey": "qwen/qwen3-coder", "displayName": "Qwen3 Coder", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-coder", "modelKey": "qwen3-coder", "displayName": "Qwen3 Coder 480B A35B Instruct Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-coder", "modelKey": "qwen/qwen3-coder", "displayName": "Qwen: Qwen3 Coder 480B A35B", "metadata": { "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-coder", "modelKey": "qwen/qwen3-coder", "displayName": "Qwen 3 Coder 480B", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3-coder", "modelKey": "qwen3-coder", "displayName": "Qwen3 Coder", "family": "qwen", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder", "modelKey": "qwen/qwen3-coder", "displayName": "Qwen3 Coder 480B A35B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-coder", "modelKey": "alibaba/qwen3-coder", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3-coder", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3-coder" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/alibaba/qwen3-coder", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder", "displayName": "Qwen: Qwen3 Coder 480B A35B", "metadata": { "canonicalSlug": "qwen/qwen3-coder-480b-a35b-07-25", "createdAt": "2025-07-23T00:29:06.000Z", "huggingFaceId": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-coder-30b", "provider": "alibaba", "model": "qwen3-coder-30b", "displayName": "Qwen3 Coder 30B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "lmstudio" ], "aliases": [ "lmstudio/qwen/qwen3-coder-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lmstudio", "model": "qwen/qwen3-coder-30b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder 30B" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lmstudio", "providerName": "LMStudio", "providerApi": "http://127.0.0.1:1234/v1", "providerDoc": "https://lmstudio.ai/models", "model": "qwen/qwen3-coder-30b", "modelKey": "qwen/qwen3-coder-30b", "displayName": "Qwen3 Coder 30B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } } ] }, { "id": "alibaba/qwen3-coder-30b-a3b", "provider": "alibaba", "model": "qwen3-coder-30b-a3b", "displayName": "Qwen3-Coder 30B-A3B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "privatemode-ai", "vercel" ], "aliases": [ "privatemode-ai/qwen3-coder-30b-a3b", "vercel/alibaba/qwen3-coder-30b-a3b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "privatemode-ai", "model": "qwen3-coder-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-coder-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Coder 30B A3B Instruct", "Qwen3-Coder 30B-A3B" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "privatemode-ai", "providerName": "Privatemode AI", "providerApi": "http://localhost:8080/v1", "providerDoc": "https://docs.privatemode.ai/api/overview", "model": "qwen3-coder-30b-a3b", "modelKey": "qwen3-coder-30b-a3b", "displayName": "Qwen3-Coder 30B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-coder-30b-a3b", "modelKey": "alibaba/qwen3-coder-30b-a3b", "displayName": "Qwen 3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": false, "releaseDate": "2025-04-01" } } ] }, { "id": "alibaba/qwen3-coder-30b-a3b-instruct", "provider": "alibaba", "model": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "clarifai", "cortecs", "fireworks_ai", "helicone", "kilo", "llmgateway", "modelscope", "nano-gpt", "novita", "novita-ai", "openrouter", "ovhcloud", "scaleway", "siliconflow", "siliconflow-cn" ], "aliases": [ "alibaba-cn/qwen3-coder-30b-a3b-instruct", "alibaba/qwen3-coder-30b-a3b-instruct", "clarifai/qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct", "cortecs/qwen3-coder-30b-a3b-instruct", "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "helicone/qwen3-coder-30b-a3b-instruct", "kilo/qwen/qwen3-coder-30b-a3b-instruct", "llmgateway/qwen3-coder-30b-a3b-instruct", "modelscope/Qwen/Qwen3-Coder-30B-A3B-Instruct", "nano-gpt/qwen3-coder-30b-a3b-instruct", "novita-ai/qwen/qwen3-coder-30b-a3b-instruct", "novita/qwen/qwen3-coder-30b-a3b-instruct", "openrouter/qwen/qwen3-coder-30b-a3b-instruct", "ovhcloud/qwen3-coder-30b-a3b-instruct", "scaleway/qwen3-coder-30b-a3b-instruct", "siliconflow-cn/Qwen/Qwen3-Coder-30B-A3B-Instruct", "siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct" ], "mergedProviderModelRecords": 17, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.216, "output": 0.861 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.25 } }, { "source": "models.dev", "provider": "clarifai", "model": "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11458, "output": 0.74812 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.053, "output": 0.222 } }, { "source": "models.dev", "provider": "helicone", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09999999999999999, "output": 0.3 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.27 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.25 } }, { "source": "models.dev", "provider": "modelscope", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.27 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.27 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.26 } }, { "source": "models.dev", "provider": "scaleway", "model": "qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.27 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder-30b-a3b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.27 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Coder-30B-A3B-Instruct", "Qwen3 Coder 30B A3B Instruct", "Qwen3 Coder 30b A3B Instruct", "Qwen3-Coder 30B-A3B Instruct", "Qwen3-Coder-30B-A3B-Instruct", "Qwen: Qwen3 Coder 30B A3B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct", "modelKey": "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-31", "openWeights": true, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-31", "openWeights": false, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-coder-30b-a3b-instruct", "modelKey": "qwen/qwen3-coder-30b-a3b-instruct", "displayName": "Qwen: Qwen3 Coder 30B A3B Instruct", "metadata": { "lastUpdated": "2025-07-31", "openWeights": true, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "displayName": "Qwen3 Coder 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-31", "openWeights": true, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3 Coder 30B A3B Instruct", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-coder-30b-a3b-instruct", "modelKey": "qwen/qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3 Coder 30b A3B Instruct", "metadata": { "lastUpdated": "2025-10-09", "openWeights": true, "releaseDate": "2025-10-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder-30b-a3b-instruct", "modelKey": "qwen/qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder-30B-A3B-Instruct", "metadata": { "lastUpdated": "2025-10-28", "openWeights": true, "releaseDate": "2025-10-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "qwen3-coder-30b-a3b-instruct", "modelKey": "qwen3-coder-30b-a3b-instruct", "displayName": "Qwen3-Coder 30B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-coder-30b-a3b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder-30b-a3b-instruct", "displayName": "Qwen: Qwen3 Coder 30B A3B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-coder-30b-a3b-instruct", "createdAt": "2025-07-31T14:32:59.000Z", "huggingFaceId": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 160000, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-coder-30b-a3b-instruct-gguf", "provider": "alibaba", "model": "qwen3-coder-30b-a3b-instruct-gguf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lemonade" ], "aliases": [ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lemonade", "model": "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lemonade", "model": "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "mode": "chat" } ] }, { "id": "alibaba/qwen3-coder-480b-a35b-instruct", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3-Coder 480B-A35B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "alibaba", "alibaba-cn", "cortecs", "deepinfra", "fireworks_ai", "huggingface", "jiekou", "llmgateway", "novita", "novita-ai", "nvidia", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "wandb" ], "aliases": [ "302ai/qwen3-coder-480b-a35b-instruct", "abacus/Qwen/qwen3-coder-480b-a35b-instruct", "alibaba-cn/qwen3-coder-480b-a35b-instruct", "alibaba/qwen3-coder-480b-a35b-instruct", "cortecs/qwen3-coder-480b-a35b-instruct", "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct", "jiekou/qwen/qwen3-coder-480b-a35b-instruct", "llmgateway/qwen3-coder-480b-a35b-instruct", "novita-ai/qwen/qwen3-coder-480b-a35b-instruct", "novita/qwen/qwen3-coder-480b-a35b-instruct", "nvidia/qwen/qwen3-coder-480b-a35b-instruct", "qiniu-ai/qwen3-coder-480b-a35b-instruct", "siliconflow-cn/Qwen/Qwen3-Coder-480B-A35B-Instruct", "siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct", "synthetic/hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "toolChoice": true, "parallelFunctionCalling": true, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.86, "output": 3.43 } }, { "source": "models.dev", "provider": "abacus", "model": "Qwen/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.2 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.861, "output": 3.441 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.441, "output": 1.984 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.3 } }, { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "models.dev", "provider": "wandb", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 1.8 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-coder-480b-a35b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.3 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 100000, "output": 150000 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Coder 480B", "Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen3 Coder 480B A35B Instruct", "Qwen3-Coder 480B-A35B Instruct", "Qwen3-Coder-480B-A35B-Instruct", "qwen3-coder-480b-a35b-instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "qwen3-coder-480b-a35b-instruct", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "Qwen/qwen3-coder-480b-a35b-instruct", "modelKey": "Qwen/qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-07-22", "openWeights": true, "releaseDate": "2025-07-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3-Coder 480B-A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3-Coder 480B-A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen3-Coder-480B-A35B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-coder-480b-a35b-instruct", "modelKey": "qwen/qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3-Coder 480B-A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-coder-480b-a35b-instruct", "modelKey": "qwen/qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen3-coder-480b-a35b-instruct", "modelKey": "qwen/qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-coder-480b-a35b-instruct", "modelKey": "qwen3-coder-480b-a35b-instruct", "displayName": "Qwen3 Coder 480B A35B Instruct", "metadata": { "lastUpdated": "2025-08-14", "openWeights": false, "releaseDate": "2025-08-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "modelKey": "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen 3 Coder 480B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen3-Coder-480B-A35B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-coder-480b-a35b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen3-coder-480b-a35b-instruct-fp8", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct-fp8", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "submodel", "together_ai", "togetherai" ], "aliases": [ "submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "togetherai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "submodel", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder 480B A35B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-08-23", "lastUpdated": "2025-08-23", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-08-23", "openWeights": false, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "displayName": "Qwen3 Coder 480B A35B Instruct", "family": "qwen", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" } } ] }, { "id": "alibaba/qwen3-coder-480b-a35b-instruct-int4-mixed-ar", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct-int4-mixed-ar", "displayName": "Qwen 3 Coder 480B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "io-net" ], "aliases": [ "io-net/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 106000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "io-net", "model": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0.44, "input": 0.22, "output": 0.95 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Coder 480B" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-15", "lastUpdated": "2025-01-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", "modelKey": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", "displayName": "Qwen 3 Coder 480B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-15", "openWeights": true, "releaseDate": "2025-01-15" } } ] }, { "id": "alibaba/qwen3-coder-480b-a35b-instruct-maas", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-qwen_models" ], "aliases": [ "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "supportedRegions": [ "global" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedRegions": [ "global" ] } } ] }, { "id": "alibaba/qwen3-coder-480b-a35b-instruct-turbo", "provider": "alibaba", "model": "qwen3-coder-480b-a35b-instruct-turbo", "displayName": "Qwen3 Coder 480B A35B Instruct Turbo", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "deepinfra", "venice" ], "aliases": [ "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "venice/qwen3-coder-480b-a35b-instruct-turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "deepinfra", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1 } }, { "source": "models.dev", "provider": "venice", "model": "qwen3-coder-480b-a35b-instruct-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.35, "output": 1.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.29, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Coder 480B Turbo", "Qwen3 Coder 480B A35B Instruct Turbo" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "modelKey": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "displayName": "Qwen3 Coder 480B A35B Instruct Turbo", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-coder-480b-a35b-instruct-turbo", "modelKey": "qwen3-coder-480b-a35b-instruct-turbo", "displayName": "Qwen 3 Coder 480B Turbo", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "alibaba/qwen3-coder-480b-instruct-bf16", "provider": "alibaba", "model": "qwen3-coder-480b-instruct-bf16", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16", "mode": "chat" } ] }, { "id": "alibaba/qwen3-coder-flash", "provider": "alibaba", "model": "qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "dashscope", "digitalocean", "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "alibaba-cn/qwen3-coder-flash", "alibaba/qwen3-coder-flash", "dashscope/qwen3-coder-flash", "digitalocean/qwen3-coder-flash", "kilo/qwen/qwen3-coder-flash", "llmgateway/qwen3-coder-flash", "nano-gpt/qwen/qwen3-coder-flash", "openrouter/qwen/qwen3-coder-flash" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1000000, "inputTokens": 997952, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.574 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "digitalocean", "model": "qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.7 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.195, "output": 0.975 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.039, "cacheWrite": 0.24375, "input": 0.195, "output": 0.975 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-coder-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.039, "cacheWrite": 0.24375, "input": 0.195, "output": 0.975 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Flash", "Qwen: Qwen3 Coder Flash" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "lastUpdated": "2025-07-28", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-flash", "modelKey": "qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-flash", "modelKey": "qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "qwen3-coder-flash", "modelKey": "qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-coder-flash", "modelKey": "qwen/qwen3-coder-flash", "displayName": "Qwen: Qwen3 Coder Flash", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-coder-flash", "modelKey": "qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-coder-flash", "modelKey": "qwen/qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "metadata": { "lastUpdated": "2025-09-17", "openWeights": false, "releaseDate": "2025-09-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder-flash", "modelKey": "qwen/qwen3-coder-flash", "displayName": "Qwen3 Coder Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-coder-flash", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder-flash", "displayName": "Qwen: Qwen3 Coder Flash", "metadata": { "canonicalSlug": "qwen/qwen3-coder-flash", "createdAt": "2025-09-17T13:25:36.000Z", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-coder-flash/endpoints" }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-coder-flash-2025-07-28", "provider": "alibaba", "model": "qwen3-coder-flash-2025-07-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen3-coder-flash-2025-07-28" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 997952, "inputTokens": 997952, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-coder-flash-2025-07-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-coder-flash-2025-07-28", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3-coder-next", "provider": "alibaba", "model": "qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba-coding-plan", "alibaba-coding-plan-cn", "cortecs", "huggingface", "jiekou", "kilo", "llmgateway", "nano-gpt", "novita-ai", "ollama-cloud", "openrouter", "regolo-ai", "vercel" ], "aliases": [ "alibaba-coding-plan-cn/qwen3-coder-next", "alibaba-coding-plan/qwen3-coder-next", "cortecs/qwen3-coder-next", "huggingface/Qwen/Qwen3-Coder-Next", "jiekou/qwen/qwen3-coder-next", "kilo/qwen/qwen3-coder-next", "llmgateway/qwen3-coder-next", "nano-gpt/qwen/qwen3-coder-next", "novita-ai/qwen/qwen3-coder-next", "ollama-cloud/qwen3-coder-next", "openrouter/qwen/qwen3-coder-next", "regolo-ai/qwen3-coder-next", "vercel/alibaba/qwen3-coder-next" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.158, "output": 0.84 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Coder-Next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.035, "input": 0.12, "output": 0.75 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.108, "output": 0.675 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.11, "output": 0.8 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-coder-next", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder-next", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.07, "input": 0.11, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Next", "Qwen3 Coder Next 80B", "Qwen3-Coder-Next", "Qwen: Qwen3 Coder Next", "qwen/qwen3-coder-next", "qwen3-coder-next" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-03", "lastUpdated": "2026-02-03", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-03", "openWeights": true, "releaseDate": "2026-02-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-03", "openWeights": true, "releaseDate": "2026-02-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "Qwen3 Coder Next 80B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-02-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Coder-Next", "modelKey": "Qwen/Qwen3-Coder-Next", "displayName": "Qwen3-Coder-Next", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-03", "openWeights": true, "releaseDate": "2026-02-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-coder-next", "modelKey": "qwen/qwen3-coder-next", "displayName": "qwen/qwen3-coder-next", "family": "qwen", "metadata": { "lastUpdated": "2026-02", "openWeights": true, "releaseDate": "2026-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-coder-next", "modelKey": "qwen/qwen3-coder-next", "displayName": "Qwen: Qwen3 Coder Next", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-coder-next", "modelKey": "qwen/qwen3-coder-next", "displayName": "Qwen3 Coder Next", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-coder-next", "modelKey": "qwen/qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-03", "openWeights": true, "releaseDate": "2026-02-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "qwen3-coder-next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-08", "openWeights": true, "releaseDate": "2026-02-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder-next", "modelKey": "qwen/qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-02-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen3-coder-next", "modelKey": "qwen3-coder-next", "displayName": "Qwen3-Coder-Next", "family": "qwen", "metadata": { "lastUpdated": "2026-03-01", "openWeights": true, "releaseDate": "2026-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-coder-next", "modelKey": "alibaba/qwen3-coder-next", "displayName": "Qwen3 Coder Next", "family": "qwen", "metadata": { "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2025-07-22" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder-next", "displayName": "Qwen: Qwen3 Coder Next", "metadata": { "canonicalSlug": "qwen/qwen3-coder-next-2025-02-03", "createdAt": "2026-02-04T00:15:01.000Z", "huggingFaceId": "Qwen/Qwen3-Coder-Next", "links": { "details": "/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-coder-next-fp8", "provider": "alibaba", "model": "qwen3-coder-next-fp8", "displayName": "Qwen3 Coder Next FP8", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/Qwen/Qwen3-Coder-Next-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3-Coder-Next-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Next FP8" ], "families": [ "qwen" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2026-02-03", "releaseDate": "2026-02-03", "lastUpdated": "2026-02-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3-Coder-Next-FP8", "modelKey": "Qwen/Qwen3-Coder-Next-FP8", "displayName": "Qwen3 Coder Next FP8", "family": "qwen", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-02-03", "lastUpdated": "2026-02-03", "openWeights": true, "releaseDate": "2026-02-03" } } ] }, { "id": "alibaba/qwen3-coder-next-tee", "provider": "alibaba", "model": "qwen3-coder-next-tee", "displayName": "Qwen3 Coder Next TEE", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/Qwen/Qwen3-Coder-Next-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-Coder-Next-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.12, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Next TEE" ], "families": [ "qwen" ], "releaseDate": "2026-04-25", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-Coder-Next-TEE", "modelKey": "Qwen/Qwen3-Coder-Next-TEE", "displayName": "Qwen3 Coder Next TEE", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2026-04-25" } } ] }, { "id": "alibaba/qwen3-coder-plus", "provider": "alibaba", "model": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "dashscope", "iflowcn", "kilo", "llmgateway", "nano-gpt", "openrouter", "vercel", "zenmux" ], "aliases": [ "alibaba-cn/qwen3-coder-plus", "alibaba-coding-plan-cn/qwen3-coder-plus", "alibaba-coding-plan/qwen3-coder-plus", "alibaba/qwen3-coder-plus", "dashscope/qwen3-coder-plus", "iflowcn/qwen3-coder-plus", "kilo/qwen/qwen3-coder-plus", "llmgateway/qwen3-coder-plus", "nano-gpt/qwen/qwen3-coder-plus", "openrouter/qwen/qwen3-coder-plus", "vercel/alibaba/qwen3-coder-plus", "zenmux/qwen/qwen3-coder-plus" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 1048576, "inputTokens": 997952, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.65, "output": 3.25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "cacheWrite": 0.8125, "input": 0.65, "output": 3.25 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3-coder-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-coder-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3-coder-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder-plus", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "cacheWrite": 0.8125, "input": 0.65, "output": 3.25 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder Plus", "Qwen3-Coder-Plus", "Qwen: Qwen3 Coder Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3-Coder-Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-coder-plus", "modelKey": "qwen/qwen3-coder-plus", "displayName": "Qwen: Qwen3 Coder Plus", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-coder-plus", "modelKey": "qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-coder-plus", "modelKey": "qwen/qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "metadata": { "lastUpdated": "2025-09-17", "openWeights": false, "releaseDate": "2025-09-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder-plus", "modelKey": "qwen/qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-coder-plus", "modelKey": "alibaba/qwen3-coder-plus", "displayName": "Qwen3 Coder Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3-coder-plus", "modelKey": "qwen/qwen3-coder-plus", "displayName": "Qwen3-Coder-Plus", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-23", "openWeights": false, "releaseDate": "2025-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-coder-plus", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3-coder-plus", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3-coder-plus" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder-plus", "displayName": "Qwen: Qwen3 Coder Plus", "metadata": { "canonicalSlug": "qwen/qwen3-coder-plus", "createdAt": "2025-09-23T21:25:07.000Z", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-coder-plus/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-coder-plus-2025-07-22", "provider": "alibaba", "model": "qwen3-coder-plus-2025-07-22", "mode": "chat", "sources": [ "litellm" ], "providers": [ "dashscope" ], "aliases": [ "dashscope/qwen3-coder-plus-2025-07-22" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 997952, "inputTokens": 997952, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-coder-plus-2025-07-22", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-coder-plus-2025-07-22", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3-coder:480b", "provider": "alibaba", "model": "qwen3-coder:480b", "displayName": "qwen3-coder:480b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/qwen3-coder:480b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-coder:480b" ], "families": [ "qwen" ], "releaseDate": "2025-07-22", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3-coder:480b", "modelKey": "qwen3-coder:480b", "displayName": "qwen3-coder:480b", "family": "qwen", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-07-22" } } ] }, { "id": "alibaba/qwen3-coder:480b-cloud", "provider": "alibaba", "model": "qwen3-coder:480b-cloud", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/qwen3-coder:480b-cloud" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/qwen3-coder:480b-cloud", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/qwen3-coder:480b-cloud", "mode": "chat" } ] }, { "id": "alibaba/qwen3-coder:free", "provider": "alibaba", "model": "qwen3-coder:free", "displayName": "Qwen3 Coder 480B A35B (free)", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/qwen/qwen3-coder:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 262000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-coder:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-coder:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3 Coder 480B A35B (free)", "Qwen: Qwen3 Coder 480B A35B (free)" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-07-23", "lastUpdated": "2025-07-23", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-coder:free", "modelKey": "qwen/qwen3-coder:free", "displayName": "Qwen3 Coder 480B A35B (free)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-07-23", "openWeights": true, "releaseDate": "2025-07-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-coder:free", "displayName": "Qwen: Qwen3 Coder 480B A35B (free)", "metadata": { "canonicalSlug": "qwen/qwen3-coder-480b-a35b-07-25", "createdAt": "2025-07-23T00:29:06.000Z", "huggingFaceId": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262000, "max_completion_tokens": 262000, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-embedding-0.6b", "provider": "alibaba", "model": "qwen3-embedding-0.6b", "displayName": "Qwen3 Embedding 0.6B", "family": "qwen", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "digitalocean", "nearai", "novita", "vercel" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-embedding-0.6b", "digitalocean/qwen3-embedding-0.6b", "nearai/Qwen/Qwen3-Embedding-0.6B", "novita/qwen/qwen3-embedding-0.6b", "vercel/alibaba/qwen3-embedding-0.6b" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/qwen/qwen3-embedding-0.6b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.012, "output": 0 } }, { "source": "models.dev", "provider": "digitalocean", "model": "qwen3-embedding-0.6b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0 } }, { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3-Embedding-0.6B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-embedding-0.6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3 Embedding 0.6B" ], "families": [ "qwen", "text-embedding" ], "modes": [ "embedding" ], "statuses": [ "beta" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/qwen/qwen3-embedding-0.6b", "modelKey": "workers-ai/@cf/qwen/qwen3-embedding-0.6b", "displayName": "Qwen3 Embedding 0.6B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "qwen3-embedding-0.6b", "modelKey": "qwen3-embedding-0.6b", "displayName": "Qwen3 Embedding 0.6B", "family": "text-embedding", "status": "beta", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2025-06-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3-Embedding-0.6B", "modelKey": "Qwen/Qwen3-Embedding-0.6B", "displayName": "Qwen3 Embedding 0.6B", "family": "text-embedding", "metadata": { "lastUpdated": "2025-06-03", "openWeights": true, "releaseDate": "2025-06-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-embedding-0.6b", "modelKey": "alibaba/qwen3-embedding-0.6b", "displayName": "Qwen3 Embedding 0.6B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-embedding-0.6b", "mode": "embedding" } ] }, { "id": "alibaba/qwen3-embedding-0p6b", "provider": "alibaba", "model": "qwen3-embedding-0p6b", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b", "mode": "embedding" } ] }, { "id": "alibaba/qwen3-embedding-4b", "provider": "alibaba", "model": "qwen3-embedding-4b", "displayName": "Qwen 3 Embedding 4B", "family": "qwen", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks_ai", "huggingface", "inference", "privatemode-ai", "vercel" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "huggingface/Qwen/Qwen3-Embedding-4B", "inference/qwen/qwen3-embedding-4b", "privatemode-ai/qwen3-embedding-4b", "vercel/alibaba/qwen3-embedding-4b" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Embedding-4B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "models.dev", "provider": "inference", "model": "qwen/qwen3-embedding-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "models.dev", "provider": "privatemode-ai", "model": "qwen3-embedding-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Embedding 4B", "Qwen3 Embedding 4B", "Qwen3-Embedding 4B" ], "families": [ "qwen" ], "modes": [ "embedding" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Embedding-4B", "modelKey": "Qwen/Qwen3-Embedding-4B", "displayName": "Qwen 3 Embedding 4B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "qwen/qwen3-embedding-4b", "modelKey": "qwen/qwen3-embedding-4b", "displayName": "Qwen 3 Embedding 4B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "privatemode-ai", "providerName": "Privatemode AI", "providerApi": "http://localhost:8080/v1", "providerDoc": "https://docs.privatemode.ai/api/overview", "model": "qwen3-embedding-4b", "modelKey": "qwen3-embedding-4b", "displayName": "Qwen3-Embedding 4B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-06-06", "openWeights": true, "releaseDate": "2025-06-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-embedding-4b", "modelKey": "alibaba/qwen3-embedding-4b", "displayName": "Qwen3 Embedding 4B", "family": "qwen", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "mode": "embedding" } ] }, { "id": "alibaba/qwen3-embedding-8b", "provider": "alibaba", "model": "qwen3-embedding-8b", "displayName": "Qwen3 Embedding 8B", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "evroc", "huggingface", "llamagate", "nebius", "novita", "regolo-ai", "scaleway", "vercel" ], "aliases": [ "evroc/Qwen/Qwen3-Embedding-8B", "huggingface/Qwen/Qwen3-Embedding-8B", "llamagate/qwen3-embedding-8b", "nebius/Qwen/Qwen3-Embedding-8B", "novita/qwen/qwen3-embedding-8b", "regolo-ai/qwen3-embedding-8b", "scaleway/qwen3-embedding-8b", "vercel/alibaba/qwen3-embedding-8b" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "temperature": true, "structuredOutput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "Qwen/Qwen3-Embedding-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.12 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Embedding-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-Embedding-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "qwen3-embedding-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "scaleway", "model": "qwen3-embedding-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "llamagate", "model": "llamagate/qwen3-embedding-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-embedding-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Embedding 8B", "Qwen3 Embedding 8B", "Qwen3-Embedding-8B" ], "families": [ "qwen", "text-embedding" ], "modes": [ "embedding" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "Qwen/Qwen3-Embedding-8B", "modelKey": "Qwen/Qwen3-Embedding-8B", "displayName": "Qwen3 Embedding 8B", "family": "text-embedding", "metadata": { "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Embedding-8B", "modelKey": "Qwen/Qwen3-Embedding-8B", "displayName": "Qwen 3 Embedding 8B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-Embedding-8B", "modelKey": "Qwen/Qwen3-Embedding-8B", "displayName": "Qwen3-Embedding-8B", "family": "text-embedding", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen3-embedding-8b", "modelKey": "qwen3-embedding-8b", "displayName": "Qwen3-Embedding-8B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "qwen3-embedding-8b", "modelKey": "qwen3-embedding-8b", "displayName": "Qwen3 Embedding 8B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2025-25-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-embedding-8b", "modelKey": "alibaba/qwen3-embedding-8b", "displayName": "Qwen3 Embedding 8B", "family": "qwen", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/qwen3-embedding-8b", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-embedding-8b", "mode": "embedding" } ] }, { "id": "alibaba/qwen3-livetranslate-flash-realtime", "provider": "alibaba", "model": "qwen3-livetranslate-flash-realtime", "displayName": "Qwen3-LiveTranslate Flash Realtime", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba" ], "aliases": [ "alibaba/qwen3-livetranslate-flash-realtime" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 53248, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3-livetranslate-flash-realtime", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "inputAudio": 10, "output": 10, "outputAudio": 38 } } ] }, "metadata": { "displayNames": [ "Qwen3-LiveTranslate Flash Realtime" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-22", "lastUpdated": "2025-09-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-livetranslate-flash-realtime", "modelKey": "qwen3-livetranslate-flash-realtime", "displayName": "Qwen3-LiveTranslate Flash Realtime", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } } ] }, { "id": "alibaba/qwen3-max", "provider": "alibaba", "model": "qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "alibaba", "alibaba-cn", "dashscope", "iflowcn", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "openrouter", "orcarouter", "qiniu-ai", "vercel", "zenmux" ], "aliases": [ "abacus/qwen3-max", "alibaba-cn/qwen3-max", "alibaba/qwen3-max", "dashscope/qwen3-max", "iflowcn/qwen3-max", "kilo/qwen/qwen3-max", "llmgateway/qwen3-max", "nano-gpt/qwen/qwen3-max", "novita-ai/qwen/qwen3-max", "novita/qwen/qwen3-max", "openrouter/qwen/qwen3-max", "orcarouter/qwen/qwen3-max", "qiniu-ai/qwen3-max", "vercel/alibaba/qwen3-max", "zenmux/qwen/qwen3-max" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 6 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.861, "output": 3.441 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 6 } }, { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.08018, "output": 5.4009 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.11, "output": 8.45 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.156, "cacheWrite": 0.975, "input": 0.78, "output": 3.9 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.359, "output": 1.434 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 6 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 6 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.11, "output": 8.45 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-max", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.156, "cacheWrite": 0.975, "input": 0.78, "output": 3.9 } } ] }, "metadata": { "displayNames": [ "Qwen3 Max", "Qwen3-Max", "Qwen3-Max-Thinking", "Qwen: Qwen3 Max" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-05-28", "lastUpdated": "2025-05-28", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "lastUpdated": "2025-05-28", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3-Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen: Qwen3 Max", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen3 Max", "metadata": { "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-24", "openWeights": false, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-max", "modelKey": "qwen3-max", "displayName": "Qwen3 Max", "metadata": { "lastUpdated": "2025-09-24", "openWeights": false, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-max", "modelKey": "alibaba/qwen3-max", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3-max", "modelKey": "qwen/qwen3-max", "displayName": "Qwen3-Max-Thinking", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-max", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-max", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-max", "displayName": "Qwen: Qwen3 Max", "metadata": { "canonicalSlug": "qwen/qwen3-max", "createdAt": "2025-09-23T21:26:48.000Z", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/qwen/qwen3-max/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-max-2025-09-23", "provider": "alibaba", "model": "qwen3-max-2025-09-23", "displayName": "qwen3-max-2025-09-23", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/qwen3-max-2025-09-23" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 258048, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "qwen3-max-2025-09-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.86, "output": 3.43 } } ] }, "metadata": { "displayNames": [ "qwen3-max-2025-09-23" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "qwen3-max-2025-09-23", "modelKey": "qwen3-max-2025-09-23", "displayName": "qwen3-max-2025-09-23", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-24", "openWeights": false, "releaseDate": "2025-09-24" } } ] }, { "id": "alibaba/qwen3-max-2026-01-23", "provider": "alibaba", "model": "qwen3-max-2026-01-23", "displayName": "Qwen3 Max", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-coding-plan", "alibaba-coding-plan-cn", "dashscope", "llmgateway", "nano-gpt" ], "aliases": [ "alibaba-coding-plan-cn/qwen3-max-2026-01-23", "alibaba-coding-plan/qwen3-max-2026-01-23", "dashscope/qwen3-max-2026-01-23", "llmgateway/qwen3-max-2026-01-23", "nano-gpt/qwen3-max-2026-01-23" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 262144, "inputTokens": 258048, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3-max-2026-01-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3-max-2026-01-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-max-2026-01-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.072, "input": 0.359, "output": 1.434 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3-max-2026-01-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2002, "output": 6.001 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-max-2026-01-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen3 Max", "Qwen3 Max (2026-01-23)", "Qwen3 Max 2026-01-23" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-23", "lastUpdated": "2026-01-23", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3-max-2026-01-23", "modelKey": "qwen3-max-2026-01-23", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3-max-2026-01-23", "modelKey": "qwen3-max-2026-01-23", "displayName": "Qwen3 Max", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-max-2026-01-23", "modelKey": "qwen3-max-2026-01-23", "displayName": "Qwen3 Max (2026-01-23)", "family": "qwen", "metadata": { "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3-max-2026-01-23", "modelKey": "qwen3-max-2026-01-23", "displayName": "Qwen3 Max 2026-01-23", "metadata": { "lastUpdated": "2026-01-26", "openWeights": false, "releaseDate": "2026-01-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-max-2026-01-23", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3-max-preview", "provider": "alibaba", "model": "qwen3-max-preview", "displayName": "Qwen3-Max-Preview", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "dashscope", "iflowcn", "qiniu-ai", "vercel" ], "aliases": [ "dashscope/qwen3-max-preview", "iflowcn/qwen3-max-preview", "qiniu-ai/qwen3-max-preview", "vercel/alibaba/qwen3-max-preview" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "inputTokens": 258048, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 6 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-max-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen3 Max Preview", "Qwen3-Max-Preview" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-max-preview", "modelKey": "qwen3-max-preview", "displayName": "Qwen3-Max-Preview", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-max-preview", "modelKey": "qwen3-max-preview", "displayName": "Qwen3 Max Preview", "metadata": { "lastUpdated": "2025-09-06", "openWeights": false, "releaseDate": "2025-09-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-max-preview", "modelKey": "alibaba/qwen3-max-preview", "displayName": "Qwen3 Max Preview", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-max-preview", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3-max-thinking", "provider": "alibaba", "model": "qwen3-max-thinking", "displayName": "Qwen: Qwen3 Max Thinking", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter", "vercel" ], "aliases": [ "kilo/qwen/qwen3-max-thinking", "openrouter/qwen/qwen3-max-thinking", "vercel/alibaba/qwen3-max-thinking" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-max-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.78, "output": 3.9 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-max-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.78, "output": 3.9 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-max-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 6 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-max-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.78, "output": 3.9 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Max Thinking", "Qwen3 Max Thinking", "Qwen: Qwen3 Max Thinking" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-23", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-max-thinking", "modelKey": "qwen/qwen3-max-thinking", "displayName": "Qwen: Qwen3 Max Thinking", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-max-thinking", "modelKey": "qwen/qwen3-max-thinking", "displayName": "Qwen3 Max Thinking", "family": "qwen", "metadata": { "lastUpdated": "2026-02-09", "openWeights": false, "releaseDate": "2026-02-09", "reasoningOptions": [ { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-max-thinking", "modelKey": "alibaba/qwen3-max-thinking", "displayName": "Qwen 3 Max Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01", "openWeights": true, "releaseDate": "2025-01" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-max-thinking", "displayName": "Qwen: Qwen3 Max Thinking", "metadata": { "canonicalSlug": "qwen/qwen3-max-thinking-20260123", "createdAt": "2026-02-09T21:18:21.000Z", "links": { "details": "/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-next-80b", "provider": "alibaba", "model": "qwen3-next-80b", "displayName": "Qwen 3 Next 80b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/qwen3-next-80b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "qwen3-next-80b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Next 80b" ], "families": [ "qwen" ], "releaseDate": "2025-04-29", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-next-80b", "modelKey": "qwen3-next-80b", "displayName": "Qwen 3 Next 80b", "family": "qwen", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-04-29" } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-instruct", "provider": "alibaba", "model": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "chutes", "dashscope", "deepinfra", "fireworks_ai", "helicone", "huggingface", "io-net", "jiekou", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "nvidia", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "together_ai", "vercel" ], "aliases": [ "alibaba-cn/qwen3-next-80b-a3b-instruct", "alibaba/qwen3-next-80b-a3b-instruct", "chutes/Qwen/Qwen3-Next-80B-A3B-Instruct", "dashscope/qwen3-next-80b-a3b-instruct", "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "helicone/qwen3-next-80b-a3b-instruct", "huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct", "io-net/Qwen/Qwen3-Next-80B-A3B-Instruct", "jiekou/qwen/qwen3-next-80b-a3b-instruct", "kilo/qwen/qwen3-next-80b-a3b-instruct", "llmgateway/qwen3-next-80b-a3b-instruct", "nano-gpt/qwen/Qwen3-Next-80B-A3B-Instruct", "novita-ai/qwen/qwen3-next-80b-a3b-instruct", "novita/qwen/qwen3-next-80b-a3b-instruct", "nvidia/qwen/qwen3-next-80b-a3b-instruct", "openrouter/qwen/qwen3-next-80b-a3b-instruct", "qiniu-ai/qwen3-next-80b-a3b-instruct", "siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Instruct", "siliconflow/Qwen/Qwen3-Next-80B-A3B-Instruct", "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct", "vercel/alibaba/qwen3-next-80b-a3b-instruct" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.574 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2 } }, { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.1, "output": 0.8 } }, { "source": "models.dev", "provider": "helicone", "model": "qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "io-net", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.2, "input": 0.1, "output": 0.8 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 1.1 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.65 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 1.1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.2 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.2 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "Qwen 3 Next 80B Instruct", "Qwen/Qwen3-Next-80B-A3B-Instruct", "Qwen3 Next 80B A3B (Instruct)", "Qwen3 Next 80B A3B Instruct", "Qwen3-Next 80B-A3B Instruct", "Qwen3-Next-80B-A3B-Instruct", "Qwen: Qwen3 Next 80B A3B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09", "lastUpdated": "2025-09", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-next-80b-a3b-instruct", "modelKey": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-next-80b-a3b-instruct", "modelKey": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-next-80b-a3b-instruct", "modelKey": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-11", "openWeights": true, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen 3 Next 80B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-10", "openWeights": true, "releaseDate": "2025-01-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-next-80b-a3b-instruct", "modelKey": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-next-80b-a3b-instruct", "modelKey": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen: Qwen3 Next 80B A3B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-next-80b-a3b-instruct", "modelKey": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen3 Next 80B A3B (Instruct)", "metadata": { "lastUpdated": "2025-09-11", "openWeights": false, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-next-80b-a3b-instruct", "modelKey": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "metadata": { "lastUpdated": "2025-09-10", "openWeights": true, "releaseDate": "2025-09-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen3-next-80b-a3b-instruct", "modelKey": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-next-80b-a3b-instruct", "modelKey": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-next-80b-a3b-instruct", "modelKey": "qwen3-next-80b-a3b-instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "metadata": { "lastUpdated": "2025-09-12", "openWeights": false, "releaseDate": "2025-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen/Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Next-80B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen/Qwen3-Next-80B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-next-80b-a3b-instruct", "modelKey": "alibaba/qwen3-next-80b-a3b-instruct", "displayName": "Qwen3 Next 80B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-next-80b-a3b-instruct", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-next-80b-a3b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct", "displayName": "Qwen: Qwen3 Next 80B A3B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-next-80b-a3b-instruct-2509", "createdAt": "2025-09-11T17:36:53.000Z", "huggingFaceId": "Qwen/Qwen3-Next-80B-A3B-Instruct", "knowledgeCutoff": "2025-09-30", "links": { "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-instruct-maas", "provider": "alibaba", "model": "qwen3-next-80b-a3b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-qwen_models" ], "aliases": [ "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "supportedRegions": [ "global" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedRegions": [ "global" ] } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-instruct:free", "provider": "alibaba", "model": "qwen3-next-80b-a3b-instruct:free", "displayName": "Qwen3 Next 80B A3B Instruct (free)", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/qwen/qwen3-next-80b-a3b-instruct:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3 Next 80B A3B Instruct (free)", "Qwen: Qwen3 Next 80B A3B Instruct (free)" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09", "lastUpdated": "2025-09", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-next-80b-a3b-instruct:free", "modelKey": "qwen/qwen3-next-80b-a3b-instruct:free", "displayName": "Qwen3 Next 80B A3B Instruct (free)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-instruct:free", "displayName": "Qwen: Qwen3 Next 80B A3B Instruct (free)", "metadata": { "canonicalSlug": "qwen/qwen3-next-80b-a3b-instruct-2509", "createdAt": "2025-09-11T17:36:53.000Z", "huggingFaceId": "Qwen/Qwen3-Next-80B-A3B-Instruct", "knowledgeCutoff": "2025-09-30", "links": { "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-thinking", "provider": "alibaba", "model": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "cortecs", "dashscope", "deepinfra", "fireworks_ai", "huggingface", "jiekou", "kilo", "llmgateway", "nano-gpt", "nebius", "novita", "novita-ai", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "together_ai", "vercel" ], "aliases": [ "alibaba-cn/qwen3-next-80b-a3b-thinking", "alibaba/qwen3-next-80b-a3b-thinking", "cortecs/qwen3-next-80b-a3b-thinking", "dashscope/qwen3-next-80b-a3b-thinking", "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking", "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking", "jiekou/qwen/qwen3-next-80b-a3b-thinking", "kilo/qwen/qwen3-next-80b-a3b-thinking", "llmgateway/qwen3-next-80b-a3b-thinking", "nano-gpt/qwen/qwen3-next-80b-a3b-thinking", "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking", "novita-ai/qwen/qwen3-next-80b-a3b-thinking", "novita/qwen/qwen3-next-80b-a3b-thinking", "openrouter/qwen/qwen3-next-80b-a3b-thinking", "qiniu-ai/qwen3-next-80b-a3b-thinking", "siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Thinking", "siliconflow/Qwen/Qwen3-Next-80B-A3B-Thinking", "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking", "vercel/alibaba/qwen3-next-80b-a3b-thinking" ], "mergedProviderModelRecords": 20, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 1.434 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 6 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.164, "output": 1.311 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2 } }, { "source": "models.dev", "provider": "jiekou", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0975, "output": 0.78 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.65 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "cacheWrite": 0.18, "input": 0.15, "output": 1.2, "reasoningOutput": 1.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0975, "output": 0.78 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.2 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.2 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 1.4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.0975, "output": 0.78 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Next-80B-A3B-Thinking", "Qwen3 Next 80B A3B (Thinking)", "Qwen3 Next 80B A3B Thinking", "Qwen3-Next 80B-A3B (Thinking)", "Qwen3-Next-80B-A3B-Thinking", "Qwen: Qwen3 Next 80B A3B Thinking" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09", "lastUpdated": "2025-09", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 20 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-next-80b-a3b-thinking", "modelKey": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-next-80b-a3b-thinking", "modelKey": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3-next-80b-a3b-thinking", "modelKey": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B Thinking", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-11", "openWeights": true, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen3-Next-80B-A3B-Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-11", "openWeights": true, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "qwen/qwen3-next-80b-a3b-thinking", "modelKey": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B Thinking", "family": "qwen", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-next-80b-a3b-thinking", "modelKey": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen: Qwen3 Next 80B A3B Thinking", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-next-80b-a3b-thinking", "modelKey": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3-next-80b-a3b-thinking", "modelKey": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B (Thinking)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen3-Next-80B-A3B-Thinking", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-next-80b-a3b-thinking", "modelKey": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B Thinking", "metadata": { "lastUpdated": "2025-09-10", "openWeights": true, "releaseDate": "2025-09-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-next-80b-a3b-thinking", "modelKey": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-next-80b-a3b-thinking", "modelKey": "qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B Thinking", "metadata": { "lastUpdated": "2025-09-12", "openWeights": false, "releaseDate": "2025-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen/Qwen3-Next-80B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen/Qwen3-Next-80B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-next-80b-a3b-thinking", "modelKey": "alibaba/qwen3-next-80b-a3b-thinking", "displayName": "Qwen3 Next 80B A3B Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09", "openWeights": true, "releaseDate": "2025-09-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-next-80b-a3b-thinking", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-next-80b-a3b-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-next-80b-a3b-thinking", "displayName": "Qwen: Qwen3 Next 80B A3B Thinking", "metadata": { "canonicalSlug": "qwen/qwen3-next-80b-a3b-thinking-2509", "createdAt": "2025-09-11T17:38:04.000Z", "huggingFaceId": "Qwen/Qwen3-Next-80B-A3B-Thinking", "knowledgeCutoff": "2025-09-30", "links": { "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-thinking-fast", "provider": "alibaba", "model": "qwen3-next-80b-a3b-thinking-fast", "displayName": "Qwen3-Next-80B-A3B-Thinking-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "cacheWrite": 0.1875, "input": 0.15, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen3-Next-80B-A3B-Thinking-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-25", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast", "modelKey": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast", "displayName": "Qwen3-Next-80B-A3B-Thinking-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-07-25" } } ] }, { "id": "alibaba/qwen3-next-80b-a3b-thinking-maas", "provider": "alibaba", "model": "qwen3-next-80b-a3b-thinking-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-qwen_models" ], "aliases": [ "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "supportedRegions": [ "global" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-qwen_models", "model": "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedRegions": [ "global" ] } } ] }, { "id": "alibaba/qwen3-next:80b", "provider": "alibaba", "model": "qwen3-next:80b", "displayName": "qwen3-next:80b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/qwen3-next:80b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-next:80b" ], "families": [ "qwen" ], "statuses": [ "deprecated" ], "releaseDate": "2025-09-15", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3-next:80b", "modelKey": "qwen3-next:80b", "displayName": "qwen3-next:80b", "family": "qwen", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-09-15" } } ] }, { "id": "alibaba/qwen3-omni-30b-a3b-captioner", "provider": "alibaba", "model": "qwen3-omni-30b-a3b-captioner", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "siliconflow", "siliconflow-cn" ], "aliases": [ "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Captioner", "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Captioner" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 66000, "outputTokens": 66000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Omni-30B-A3B-Captioner" ], "families": [ "qwen" ], "releaseDate": "2025-10-04", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } } ] }, { "id": "alibaba/qwen3-omni-30b-a3b-instruct", "provider": "alibaba", "model": "qwen3-omni-30b-a3b-instruct", "displayName": "Qwen3 Omni 30B A3B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "novita-ai/qwen/qwen3-omni-30b-a3b-instruct", "novita/qwen/qwen3-omni-30b-a3b-instruct", "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Instruct", "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Instruct" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 66000, "inputTokens": 65536, "maxTokens": 16384, "outputTokens": 66000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-omni-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "inputAudio": 2.2, "output": 0.97, "outputAudio": 1.788 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-omni-30b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.97 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Omni-30B-A3B-Instruct", "Qwen3 Omni 30B A3B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-omni-30b-a3b-instruct", "modelKey": "qwen/qwen3-omni-30b-a3b-instruct", "displayName": "Qwen3 Omni 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-omni-30b-a3b-instruct", "mode": "chat" } ] }, { "id": "alibaba/qwen3-omni-30b-a3b-thinking", "provider": "alibaba", "model": "qwen3-omni-30b-a3b-thinking", "displayName": "Qwen3 Omni 30B A3B Thinking", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "novita-ai/qwen/qwen3-omni-30b-a3b-thinking", "novita/qwen/qwen3-omni-30b-a3b-thinking", "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Thinking", "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Thinking" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 66000, "inputTokens": 65536, "maxTokens": 16384, "outputTokens": 66000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-omni-30b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "inputAudio": 2.2, "output": 0.97, "outputAudio": 1.788 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-omni-30b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.97 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-Omni-30B-A3B-Thinking", "Qwen3 Omni 30B A3B Thinking" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-omni-30b-a3b-thinking", "modelKey": "qwen/qwen3-omni-30b-a3b-thinking", "displayName": "Qwen3 Omni 30B A3B Thinking", "metadata": { "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "modelKey": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "displayName": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-omni-30b-a3b-thinking", "mode": "chat" } ] }, { "id": "alibaba/qwen3-omni-flash", "provider": "alibaba", "model": "qwen3-omni-flash", "displayName": "Qwen3-Omni Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen3-omni-flash", "alibaba/qwen3-omni-flash" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-omni-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.058, "inputAudio": 3.584, "output": 0.23, "outputAudio": 7.168 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-omni-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.43, "inputAudio": 3.81, "output": 1.66, "outputAudio": 15.11 } } ] }, "metadata": { "displayNames": [ "Qwen3-Omni Flash" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-15", "lastUpdated": "2025-09-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-omni-flash", "modelKey": "qwen3-omni-flash", "displayName": "Qwen3-Omni Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-omni-flash", "modelKey": "qwen3-omni-flash", "displayName": "Qwen3-Omni Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } } ] }, { "id": "alibaba/qwen3-omni-flash-realtime", "provider": "alibaba", "model": "qwen3-omni-flash-realtime", "displayName": "Qwen3-Omni Flash Realtime", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen3-omni-flash-realtime", "alibaba/qwen3-omni-flash-realtime" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-omni-flash-realtime", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "inputAudio": 3.584, "output": 0.918, "outputAudio": 7.168 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-omni-flash-realtime", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.52, "inputAudio": 4.57, "output": 1.99, "outputAudio": 18.13 } } ] }, "metadata": { "displayNames": [ "Qwen3-Omni Flash Realtime" ], "families": [ "qwen" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-09-15", "lastUpdated": "2025-09-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-omni-flash-realtime", "modelKey": "qwen3-omni-flash-realtime", "displayName": "Qwen3-Omni Flash Realtime", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-omni-flash-realtime", "modelKey": "qwen3-omni-flash-realtime", "displayName": "Qwen3-Omni Flash Realtime", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } } ] }, { "id": "alibaba/qwen3-reranker-0.6b", "provider": "alibaba", "model": "qwen3-reranker-0.6b", "displayName": "Qwen3 Reranker 0.6B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nearai" ], "aliases": [ "nearai/Qwen/Qwen3-Reranker-0.6B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3-Reranker-0.6B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "displayNames": [ "Qwen3 Reranker 0.6B" ], "families": [ "qwen" ], "releaseDate": "2025-06-03", "lastUpdated": "2025-06-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3-Reranker-0.6B", "modelKey": "Qwen/Qwen3-Reranker-0.6B", "displayName": "Qwen3 Reranker 0.6B", "family": "qwen", "metadata": { "lastUpdated": "2025-06-03", "openWeights": true, "releaseDate": "2025-06-03" } } ] }, { "id": "alibaba/qwen3-reranker-0p6b", "provider": "alibaba", "model": "qwen3-reranker-0p6b", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b", "mode": "rerank" } ] }, { "id": "alibaba/qwen3-reranker-4b", "provider": "alibaba", "model": "qwen3-reranker-4b", "displayName": "Qwen3-Reranker-4B", "family": "qwen", "mode": "rerank", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks_ai", "regolo-ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b", "regolo-ai/qwen3-reranker-4b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": true, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "regolo-ai", "model": "qwen3-reranker-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.12 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3-Reranker-4B" ], "families": [ "qwen" ], "modes": [ "rerank" ], "releaseDate": "2026-02-01", "lastUpdated": "2026-02-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen3-reranker-4b", "modelKey": "qwen3-reranker-4b", "displayName": "Qwen3-Reranker-4B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b", "mode": "rerank" } ] }, { "id": "alibaba/qwen3-reranker-8b", "provider": "alibaba", "model": "qwen3-reranker-8b", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "novita" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b", "novita/qwen/qwen3-reranker-8b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-reranker-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b", "mode": "rerank" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-reranker-8b", "mode": "rerank" } ] }, { "id": "alibaba/qwen3-tts-voicedesign", "provider": "alibaba", "model": "qwen3-tts-voicedesign", "displayName": "Qwen3 TTS VoiceDesign", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/qwen3-tts-voicedesign" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 1, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Qwen3 TTS VoiceDesign" ], "families": [ "qwen" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "qwen3-tts-voicedesign", "modelKey": "qwen3-tts-voicedesign", "displayName": "Qwen3 TTS VoiceDesign", "family": "qwen", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-04-21" } } ] }, { "id": "alibaba/qwen3-vl-235b-a22b", "provider": "alibaba", "model": "qwen3-vl-235b-a22b", "displayName": "Qwen3-VL 235B-A22B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "venice" ], "aliases": [ "alibaba-cn/qwen3-vl-235b-a22b", "alibaba/qwen3-vl-235b-a22b", "venice/qwen3-vl-235b-a22b" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-vl-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.286705, "output": 1.14682, "reasoningOutput": 2.867051 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-vl-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8, "reasoningOutput": 8.4 } }, { "source": "models.dev", "provider": "venice", "model": "qwen3-vl-235b-a22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Qwen3 VL 235B", "Qwen3-VL 235B-A22B" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-235b-a22b", "modelKey": "qwen3-vl-235b-a22b", "displayName": "Qwen3-VL 235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-235b-a22b", "modelKey": "qwen3-vl-235b-a22b", "displayName": "Qwen3-VL 235B-A22B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "qwen3-vl-235b-a22b", "modelKey": "qwen3-vl-235b-a22b", "displayName": "Qwen3 VL 235B", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-01-16" } } ] }, { "id": "alibaba/qwen3-vl-235b-a22b-instruct", "provider": "alibaba", "model": "qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "dashscope", "fireworks_ai", "helicone", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "openrouter", "siliconflow", "siliconflow-cn", "vercel" ], "aliases": [ "dashscope/qwen3-vl-235b-a22b-instruct", "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "helicone/qwen3-vl-235b-a22b-instruct", "kilo/qwen/qwen3-vl-235b-a22b-instruct", "llmgateway/qwen3-vl-235b-a22b-instruct", "nano-gpt/qwen/Qwen3-VL-235B-A22B-Instruct", "novita-ai/qwen/qwen3-vl-235b-a22b-instruct", "novita/qwen/qwen3-vl-235b-a22b-instruct", "openrouter/qwen/qwen3-vl-235b-a22b-instruct", "siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct", "siliconflow/Qwen/Qwen3-VL-235B-A22B-Instruct", "vercel/alibaba/qwen3-vl-235b-a22b-instruct" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.2, "output": 0.88 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3-VL-235B-A22B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.2, "output": 0.88 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.2, "output": 0.88 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-235B-A22B-Instruct", "Qwen3 VL 235B A22B Instruct", "Qwen: Qwen3 VL 235B A22B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "qwen3-vl-235b-a22b-instruct", "modelKey": "qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-235b-a22b-instruct", "modelKey": "qwen/qwen3-vl-235b-a22b-instruct", "displayName": "Qwen: Qwen3 VL 235B A22B Instruct", "metadata": { "lastUpdated": "2026-01-10", "openWeights": true, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-235b-a22b-instruct", "modelKey": "qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-09-15", "openWeights": true, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3-VL-235B-A22B-Instruct", "modelKey": "qwen/Qwen3-VL-235B-A22B-Instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-vl-235b-a22b-instruct", "modelKey": "qwen/qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "metadata": { "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-235b-a22b-instruct", "modelKey": "qwen/qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-09-23", "openWeights": true, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct", "modelKey": "Qwen/Qwen3-VL-235B-A22B-Instruct", "displayName": "Qwen/Qwen3-VL-235B-A22B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct", "modelKey": "Qwen/Qwen3-VL-235B-A22B-Instruct", "displayName": "Qwen/Qwen3-VL-235B-A22B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-vl-235b-a22b-instruct", "modelKey": "alibaba/qwen3-vl-235b-a22b-instruct", "displayName": "Qwen3 VL 235B A22B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2025-09-24" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-vl-235b-a22b-instruct", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-vl-235b-a22b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-instruct", "displayName": "Qwen: Qwen3 VL 235B A22B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-vl-235b-a22b-instruct", "createdAt": "2025-09-23T23:04:47.000Z", "huggingFaceId": "Qwen/Qwen3-VL-235B-A22B-Instruct", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-235b-a22b-instruct-fp8", "provider": "alibaba", "model": "qwen3-vl-235b-a22b-instruct-fp8", "displayName": "Qwen3-VL 235B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gmi", "stackit" ], "aliases": [ "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.64, "output": 1.91 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "Qwen3-VL 235B" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2024-11-01", "lastUpdated": "2024-11-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "modelKey": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "displayName": "Qwen3-VL 235B", "family": "qwen", "metadata": { "lastUpdated": "2024-11-01", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "mode": "chat" } ] }, { "id": "alibaba/qwen3-vl-235b-a22b-instruct-original", "provider": "alibaba", "model": "qwen3-vl-235b-a22b-instruct-original", "displayName": "Qwen3 VL 235B A22B Instruct Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3-vl-235b-a22b-instruct-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3-vl-235b-a22b-instruct-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Qwen3 VL 235B A22B Instruct Original" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3-vl-235b-a22b-instruct-original", "modelKey": "qwen3-vl-235b-a22b-instruct-original", "displayName": "Qwen3 VL 235B A22B Instruct Original", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "alibaba/qwen3-vl-235b-a22b-thinking", "provider": "alibaba", "model": "qwen3-vl-235b-a22b-thinking", "displayName": "Qwen: Qwen3 VL 235B A22B Thinking", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "dashscope", "fireworks_ai", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "dashscope/qwen3-vl-235b-a22b-thinking", "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "kilo/qwen/qwen3-vl-235b-a22b-thinking", "llmgateway/qwen3-vl-235b-a22b-thinking", "nano-gpt/qwen3-vl-235b-a22b-thinking", "novita-ai/qwen/qwen3-vl-235b-a22b-thinking", "novita/qwen/qwen3-vl-235b-a22b-thinking", "openrouter/qwen/qwen3-vl-235b-a22b-thinking", "siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking", "siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 2.6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 6 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.98, "output": 3.95 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 2.6 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-235B-A22B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 3.5 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-235B-A22B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 3.5 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.98, "output": 3.95 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.26, "output": 2.6 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-235B-A22B-Thinking", "Qwen3 VL 235B A22B Thinking", "Qwen: Qwen3 VL 235B A22B Thinking" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-09-24", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-235b-a22b-thinking", "modelKey": "qwen/qwen3-vl-235b-a22b-thinking", "displayName": "Qwen: Qwen3 VL 235B A22B Thinking", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-235b-a22b-thinking", "modelKey": "qwen3-vl-235b-a22b-thinking", "displayName": "Qwen3 VL 235B A22B Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-09-15", "openWeights": true, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3-vl-235b-a22b-thinking", "modelKey": "qwen3-vl-235b-a22b-thinking", "displayName": "Qwen3 VL 235B A22B Thinking", "metadata": { "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-vl-235b-a22b-thinking", "modelKey": "qwen/qwen3-vl-235b-a22b-thinking", "displayName": "Qwen3 VL 235B A22B Thinking", "metadata": { "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-235b-a22b-thinking", "modelKey": "qwen/qwen3-vl-235b-a22b-thinking", "displayName": "Qwen3 VL 235B A22B Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-09-23", "openWeights": true, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-235B-A22B-Thinking", "modelKey": "Qwen/Qwen3-VL-235B-A22B-Thinking", "displayName": "Qwen/Qwen3-VL-235B-A22B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-235B-A22B-Thinking", "modelKey": "Qwen/Qwen3-VL-235B-A22B-Thinking", "displayName": "Qwen/Qwen3-VL-235B-A22B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-vl-235b-a22b-thinking", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-vl-235b-a22b-thinking", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-235b-a22b-thinking", "displayName": "Qwen: Qwen3 VL 235B A22B Thinking", "metadata": { "canonicalSlug": "qwen/qwen3-vl-235b-a22b-thinking", "createdAt": "2025-09-23T23:04:50.000Z", "huggingFaceId": "Qwen/Qwen3-VL-235B-A22B-Thinking", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-30b-a3b", "provider": "alibaba", "model": "qwen3-vl-30b-a3b", "displayName": "Qwen3-VL 30B-A3B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba", "alibaba-cn" ], "aliases": [ "alibaba-cn/qwen3-vl-30b-a3b", "alibaba/qwen3-vl-30b-a3b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-vl-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.108, "output": 0.431, "reasoningOutput": 1.076 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-vl-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8, "reasoningOutput": 2.4 } } ] }, "metadata": { "displayNames": [ "Qwen3-VL 30B-A3B" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04", "lastUpdated": "2025-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-30b-a3b", "modelKey": "qwen3-vl-30b-a3b", "displayName": "Qwen3-VL 30B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-30b-a3b", "modelKey": "qwen3-vl-30b-a3b", "displayName": "Qwen3-VL 30B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "openWeights": true, "releaseDate": "2025-04" } } ] }, { "id": "alibaba/qwen3-vl-30b-a3b-instruct", "provider": "alibaba", "model": "qwen3-vl-30b-a3b-instruct", "displayName": "Qwen3 VL 30B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "evroc", "fireworks_ai", "kilo", "llmgateway", "nearai", "novita", "novita-ai", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "evroc/Qwen/Qwen3-VL-30B-A3B-Instruct", "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "kilo/qwen/qwen3-vl-30b-a3b-instruct", "llmgateway/qwen3-vl-30b-a3b-instruct", "nearai/Qwen/Qwen3-VL-30B-A3B-Instruct", "novita-ai/qwen/qwen3-vl-30b-a3b-instruct", "novita/qwen/qwen3-vl-30b-a3b-instruct", "openrouter/qwen/qwen3-vl-30b-a3b-instruct", "siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct", "siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": true, "supports1MContext": false, "temperature": true, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.94 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.7 } }, { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.55 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.7 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.7 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-30B-A3B-Instruct", "Qwen3 VL 30B", "Qwen3 VL 30B A3B Instruct", "Qwen3-VL 30B-A3B Instruct", "Qwen: Qwen3 VL 30B A3B Instruct", "qwen/qwen3-vl-30b-a3b-instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Instruct", "displayName": "Qwen3 VL 30B", "family": "qwen", "metadata": { "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-30b-a3b-instruct", "modelKey": "qwen/qwen3-vl-30b-a3b-instruct", "displayName": "Qwen: Qwen3 VL 30B A3B Instruct", "metadata": { "lastUpdated": "2025-11-25", "openWeights": true, "releaseDate": "2025-10-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-30b-a3b-instruct", "modelKey": "qwen3-vl-30b-a3b-instruct", "displayName": "Qwen3 VL 30B A3B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-10-02", "openWeights": true, "releaseDate": "2025-10-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Instruct", "displayName": "Qwen3-VL 30B-A3B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-09-23", "openWeights": true, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-vl-30b-a3b-instruct", "modelKey": "qwen/qwen3-vl-30b-a3b-instruct", "displayName": "qwen/qwen3-vl-30b-a3b-instruct", "metadata": { "lastUpdated": "2025-10-11", "openWeights": true, "releaseDate": "2025-10-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-30b-a3b-instruct", "modelKey": "qwen/qwen3-vl-30b-a3b-instruct", "displayName": "Qwen3 VL 30B A3B Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-10-06", "openWeights": true, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-VL-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-30B-A3B-Instruct", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Instruct", "displayName": "Qwen/Qwen3-VL-30B-A3B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-vl-30b-a3b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-instruct", "displayName": "Qwen: Qwen3 VL 30B A3B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-vl-30b-a3b-instruct", "createdAt": "2025-10-06T23:47:56.000Z", "huggingFaceId": "Qwen/Qwen3-VL-30B-A3B-Instruct", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-30b-a3b-thinking", "provider": "alibaba", "model": "qwen3-vl-30b-a3b-thinking", "displayName": "Qwen: Qwen3 VL 30B A3B Thinking", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fireworks_ai", "kilo", "llmgateway", "novita", "novita-ai", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "kilo/qwen/qwen3-vl-30b-a3b-thinking", "llmgateway/qwen3-vl-30b-a3b-thinking", "novita-ai/qwen/qwen3-vl-30b-a3b-thinking", "novita/qwen/qwen3-vl-30b-a3b-thinking", "openrouter/qwen/qwen3-vl-30b-a3b-thinking", "qiniu-ai/qwen3-vl-30b-a3b-thinking", "siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking", "siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 1.56 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 1.56 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-30B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-30B-A3B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 1.56 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-30B-A3B-Thinking", "Qwen3 VL 30B A3B Thinking", "Qwen3-Vl 30b A3b Thinking", "Qwen: Qwen3 VL 30B A3B Thinking", "qwen/qwen3-vl-30b-a3b-thinking" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-10-11", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-30b-a3b-thinking", "modelKey": "qwen/qwen3-vl-30b-a3b-thinking", "displayName": "Qwen: Qwen3 VL 30B A3B Thinking", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-10-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-30b-a3b-thinking", "modelKey": "qwen3-vl-30b-a3b-thinking", "displayName": "Qwen3 VL 30B A3B Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-10-02", "openWeights": true, "releaseDate": "2025-10-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-vl-30b-a3b-thinking", "modelKey": "qwen/qwen3-vl-30b-a3b-thinking", "displayName": "qwen/qwen3-vl-30b-a3b-thinking", "metadata": { "lastUpdated": "2025-10-11", "openWeights": true, "releaseDate": "2025-10-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-30b-a3b-thinking", "modelKey": "qwen/qwen3-vl-30b-a3b-thinking", "displayName": "Qwen3 VL 30B A3B Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-10-06", "openWeights": true, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3-vl-30b-a3b-thinking", "modelKey": "qwen3-vl-30b-a3b-thinking", "displayName": "Qwen3-Vl 30b A3b Thinking", "metadata": { "lastUpdated": "2026-02-09", "openWeights": false, "releaseDate": "2026-02-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-30B-A3B-Thinking", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Thinking", "displayName": "Qwen/Qwen3-VL-30B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-30B-A3B-Thinking", "modelKey": "Qwen/Qwen3-VL-30B-A3B-Thinking", "displayName": "Qwen/Qwen3-VL-30B-A3B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-vl-30b-a3b-thinking", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-30b-a3b-thinking", "displayName": "Qwen: Qwen3 VL 30B A3B Thinking", "metadata": { "canonicalSlug": "qwen/qwen3-vl-30b-a3b-thinking", "createdAt": "2025-10-06T23:47:59.000Z", "huggingFaceId": "Qwen/Qwen3-VL-30B-A3B-Thinking", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-32b-instruct", "provider": "alibaba", "model": "qwen3-vl-32b-instruct", "displayName": "Qwen: Qwen3 VL 32B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "dashscope", "fireworks_ai", "kilo", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "dashscope/qwen3-vl-32b-instruct", "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct", "kilo/qwen/qwen3-vl-32b-instruct", "openrouter/qwen/qwen3-vl-32b-instruct", "siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct", "siliconflow/Qwen/Qwen3-VL-32B-Instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 262144, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.104, "output": 0.416 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-32b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.104, "output": 0.416 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-32B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-vl-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.16, "output": 0.64 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-32b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.104, "output": 0.416 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-32B-Instruct", "Qwen3 VL 32B Instruct", "Qwen: Qwen3 VL 32B Instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-10-21", "lastUpdated": "2025-11-25", "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-32b-instruct", "modelKey": "qwen/qwen3-vl-32b-instruct", "displayName": "Qwen: Qwen3 VL 32B Instruct", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-32b-instruct", "modelKey": "qwen/qwen3-vl-32b-instruct", "displayName": "Qwen3 VL 32B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-10-23", "openWeights": true, "releaseDate": "2025-10-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-32B-Instruct", "modelKey": "Qwen/Qwen3-VL-32B-Instruct", "displayName": "Qwen/Qwen3-VL-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-32B-Instruct", "modelKey": "Qwen/Qwen3-VL-32B-Instruct", "displayName": "Qwen/Qwen3-VL-32B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-21" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-vl-32b-instruct", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-32b-instruct", "displayName": "Qwen: Qwen3 VL 32B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-vl-32b-instruct", "createdAt": "2025-10-23T14:55:32.000Z", "huggingFaceId": "Qwen/Qwen3-VL-32B-Instruct", "links": { "details": "/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints" }, "supportedParameters": [ "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-32b-thinking", "provider": "alibaba", "model": "qwen3-vl-32b-thinking", "displayName": "Qwen/Qwen3-VL-32B-Thinking", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "dashscope", "siliconflow", "siliconflow-cn" ], "aliases": [ "dashscope/qwen3-vl-32b-thinking", "siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking", "siliconflow/Qwen/Qwen3-VL-32B-Thinking" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 262000, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-32B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-32B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-vl-32b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.16, "output": 2.87 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-32B-Thinking" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-10-21", "lastUpdated": "2025-11-25", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-32B-Thinking", "modelKey": "Qwen/Qwen3-VL-32B-Thinking", "displayName": "Qwen/Qwen3-VL-32B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-32B-Thinking", "modelKey": "Qwen/Qwen3-VL-32B-Thinking", "displayName": "Qwen/Qwen3-VL-32B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-21" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-vl-32b-thinking", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" } } ] }, { "id": "alibaba/qwen3-vl-8b", "provider": "alibaba", "model": "qwen3-vl-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/qwen3-vl-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/qwen3-vl-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.55 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/qwen3-vl-8b", "mode": "chat" } ] }, { "id": "alibaba/qwen3-vl-8b-instruct", "provider": "alibaba", "model": "qwen3-vl-8b-instruct", "displayName": "Qwen: Qwen3 VL 8B Instruct", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fireworks_ai", "kilo", "llmgateway", "novita", "novita-ai", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct", "kilo/qwen/qwen3-vl-8b-instruct", "llmgateway/qwen3-vl-8b-instruct", "novita-ai/qwen/qwen3-vl-8b-instruct", "novita/qwen/qwen3-vl-8b-instruct", "openrouter/qwen/qwen3-vl-8b-instruct", "siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct", "siliconflow/Qwen/Qwen3-VL-8B-Instruct" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 262000, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3-vl-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.5 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.68 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.68 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/qwen/qwen3-vl-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-8B-Instruct", "Qwen3 VL 8B Instruct", "Qwen: Qwen3 VL 8B Instruct", "qwen/qwen3-vl-8b-instruct" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-11-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-8b-instruct", "modelKey": "qwen/qwen3-vl-8b-instruct", "displayName": "Qwen: Qwen3 VL 8B Instruct", "metadata": { "lastUpdated": "2025-11-25", "openWeights": true, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-8b-instruct", "modelKey": "qwen3-vl-8b-instruct", "displayName": "Qwen3 VL 8B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-08-19", "openWeights": true, "releaseDate": "2025-08-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3-vl-8b-instruct", "modelKey": "qwen/qwen3-vl-8b-instruct", "displayName": "qwen/qwen3-vl-8b-instruct", "metadata": { "lastUpdated": "2025-10-17", "openWeights": true, "releaseDate": "2025-10-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-8b-instruct", "modelKey": "qwen/qwen3-vl-8b-instruct", "displayName": "Qwen3 VL 8B Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-10-14", "openWeights": true, "releaseDate": "2025-10-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-8B-Instruct", "modelKey": "Qwen/Qwen3-VL-8B-Instruct", "displayName": "Qwen/Qwen3-VL-8B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-8B-Instruct", "modelKey": "Qwen/Qwen3-VL-8B-Instruct", "displayName": "Qwen/Qwen3-VL-8B-Instruct", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/qwen/qwen3-vl-8b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-instruct", "displayName": "Qwen: Qwen3 VL 8B Instruct", "metadata": { "canonicalSlug": "qwen/qwen3-vl-8b-instruct", "createdAt": "2025-10-14T17:35:08.000Z", "huggingFaceId": "Qwen/Qwen3-VL-8B-Instruct", "links": { "details": "/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-8b-thinking", "provider": "alibaba", "model": "qwen3-vl-8b-thinking", "displayName": "Qwen: Qwen3 VL 8B Thinking", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter", "siliconflow", "siliconflow-cn" ], "aliases": [ "kilo/qwen/qwen3-vl-8b-thinking", "openrouter/qwen/qwen3-vl-8b-thinking", "siliconflow-cn/Qwen/Qwen3-VL-8B-Thinking", "siliconflow/Qwen/Qwen3-VL-8B-Thinking" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3-vl-8b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.117, "output": 1.365 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.117, "output": 1.365 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3-VL-8B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 2 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/Qwen3-VL-8B-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.117, "output": 1.365 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3-VL-8B-Thinking", "Qwen3 VL 8B Thinking", "Qwen: Qwen3 VL 8B Thinking" ], "families": [ "qwen" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-11-25", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3-vl-8b-thinking", "modelKey": "qwen/qwen3-vl-8b-thinking", "displayName": "Qwen: Qwen3 VL 8B Thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3-vl-8b-thinking", "modelKey": "qwen/qwen3-vl-8b-thinking", "displayName": "Qwen3 VL 8B Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-10-14", "openWeights": true, "releaseDate": "2025-10-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-8B-Thinking", "modelKey": "Qwen/Qwen3-VL-8B-Thinking", "displayName": "Qwen/Qwen3-VL-8B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3-VL-8B-Thinking", "modelKey": "Qwen/Qwen3-VL-8B-Thinking", "displayName": "Qwen/Qwen3-VL-8B-Thinking", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3-vl-8b-thinking", "displayName": "Qwen: Qwen3 VL 8B Thinking", "metadata": { "canonicalSlug": "qwen/qwen3-vl-8b-thinking", "createdAt": "2025-10-14T17:42:26.000Z", "huggingFaceId": "Qwen/Qwen3-VL-8B-Thinking", "links": { "details": "/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3-vl-embedding-8b", "provider": "alibaba", "model": "qwen3-vl-embedding-8b", "displayName": "Qwen3-VL Embedding 8B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "stackit" ], "aliases": [ "stackit/Qwen/Qwen3-VL-Embedding-8B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "Qwen/Qwen3-VL-Embedding-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.09 } } ] }, "metadata": { "displayNames": [ "Qwen3-VL Embedding 8B" ], "families": [ "qwen" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "Qwen/Qwen3-VL-Embedding-8B", "modelKey": "Qwen/Qwen3-VL-Embedding-8B", "displayName": "Qwen3-VL Embedding 8B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-05", "openWeights": true, "releaseDate": "2026-02-05" } } ] }, { "id": "alibaba/qwen3-vl-flash", "provider": "alibaba", "model": "qwen3-vl-flash", "displayName": "Qwen3 VL Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/qwen3-vl-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 32000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0044, "input": 0.022, "output": 0.215 } } ] }, "metadata": { "displayNames": [ "Qwen3 VL Flash" ], "families": [ "qwen" ], "releaseDate": "2025-10-09", "lastUpdated": "2025-10-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-flash", "modelKey": "qwen3-vl-flash", "displayName": "Qwen3 VL Flash", "family": "qwen", "metadata": { "lastUpdated": "2025-10-09", "openWeights": false, "releaseDate": "2025-10-09" } } ] }, { "id": "alibaba/qwen3-vl-instruct", "provider": "alibaba", "model": "qwen3-vl-instruct", "displayName": "Qwen3 VL Instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/qwen3-vl-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 129024, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-vl-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "Qwen3 VL Instruct" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-vl-instruct", "modelKey": "alibaba/qwen3-vl-instruct", "displayName": "Qwen3 VL Instruct", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } } ] }, { "id": "alibaba/qwen3-vl-plus", "provider": "alibaba", "model": "qwen3-vl-plus", "displayName": "Qwen3-VL Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "dashscope", "iflowcn", "llmgateway" ], "aliases": [ "alibaba-cn/qwen3-vl-plus", "alibaba/qwen3-vl-plus", "dashscope/qwen3-vl-plus", "iflowcn/qwen3-vl-plus", "llmgateway/qwen3-vl-plus" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 262144, "inputTokens": 260096, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.143353, "output": 1.433525, "reasoningOutput": 4.300576 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.6, "reasoningOutput": 4.8 } }, { "source": "models.dev", "provider": "iflowcn", "model": "qwen3-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3-vl-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.6, "reasoningOutput": 4.8 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3-vl-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen3-VL Plus", "Qwen3-VL-Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-plus", "modelKey": "qwen3-vl-plus", "displayName": "Qwen3-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3-vl-plus", "modelKey": "qwen3-vl-plus", "displayName": "Qwen3-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "qwen3-vl-plus", "modelKey": "qwen3-vl-plus", "displayName": "Qwen3-VL-Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3-vl-plus", "modelKey": "qwen3-vl-plus", "displayName": "Qwen3-VL Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3-vl-plus", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3-vl-thinking", "provider": "alibaba", "model": "qwen3-vl-thinking", "displayName": "Qwen3 VL Thinking", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/qwen3-vl-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3-vl-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 4 } } ] }, "metadata": { "displayNames": [ "Qwen3 VL Thinking" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3-vl-thinking", "modelKey": "alibaba/qwen3-vl-thinking", "displayName": "Qwen3 VL Thinking", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-24", "openWeights": true, "releaseDate": "2025-09-24" } } ] }, { "id": "alibaba/qwen3-vl:235b", "provider": "alibaba", "model": "qwen3-vl:235b", "displayName": "qwen3-vl:235b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/qwen3-vl:235b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-vl:235b" ], "families": [ "qwen" ], "statuses": [ "deprecated" ], "releaseDate": "2025-09-22", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3-vl:235b", "modelKey": "qwen3-vl:235b", "displayName": "qwen3-vl:235b", "family": "qwen", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-09-22" } } ] }, { "id": "alibaba/qwen3-vl:235b-instruct", "provider": "alibaba", "model": "qwen3-vl:235b-instruct", "displayName": "qwen3-vl:235b-instruct", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/qwen3-vl:235b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3-vl:235b-instruct" ], "families": [ "qwen" ], "statuses": [ "deprecated" ], "releaseDate": "2025-09-22", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3-vl:235b-instruct", "modelKey": "qwen3-vl:235b-instruct", "displayName": "qwen3-vl:235b-instruct", "family": "qwen", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-09-22" } } ] }, { "id": "alibaba/qwen3.5-122b", "provider": "alibaba", "model": "qwen3.5-122b", "displayName": "Qwen3.5-122B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "regolo-ai" ], "aliases": [ "regolo-ai/qwen3.5-122b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "regolo-ai", "model": "qwen3.5-122b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "Qwen3.5-122B" ], "families": [ "qwen" ], "releaseDate": "2026-02-01", "lastUpdated": "2026-02-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen3.5-122b", "modelKey": "qwen3.5-122b", "displayName": "Qwen3.5-122B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01" } } ] }, { "id": "alibaba/qwen3.5-122b-a10b", "provider": "alibaba", "model": "qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "cortecs", "kilo", "mixlayer", "nano-gpt", "nearai", "novita-ai", "nvidia", "openrouter", "orcarouter", "siliconflow-cn" ], "aliases": [ "alibaba/qwen3.5-122b-a10b", "cortecs/qwen3.5-122b-a10b", "kilo/qwen/qwen3.5-122b-a10b", "mixlayer/qwen/qwen3.5-122b-a10b", "nano-gpt/TEE/qwen3.5-122b-a10b", "nano-gpt/qwen3.5-122b-a10b", "nearai/Qwen/Qwen3.5-122B-A10B", "novita-ai/qwen/qwen3.5-122b-a10b", "nvidia/qwen/qwen3.5-122b-a10b", "openrouter/qwen/qwen3.5-122b-a10b", "orcarouter/qwen/qwen3.5-122b-a10b", "siliconflow-cn/Qwen/Qwen3.5-122B-A10B" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 3.2 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.444, "output": 3.106 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 2.08 } }, { "source": "models.dev", "provider": "mixlayer", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 3.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.36, "output": 2.88 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.46, "output": 3.68 } }, { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3.5-122B-A10B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 3.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 3.2 } }, { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 2.08 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.917 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-122B-A10B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 2.32 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-122b-a10b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-122b-a10b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.26, "output": 2.08 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3.5-122B-A10B", "Qwen3.5 122B A10B", "Qwen3.5 122B A10B TEE", "Qwen3.5 122B-A10B", "Qwen3.5-122B-A10B", "Qwen: Qwen3.5-122B-A10B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2026-01", "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-122b-a10b", "modelKey": "qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3.5-122b-a10b", "modelKey": "qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B A10B", "family": "qwen", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-24", "openWeights": true, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen: Qwen3.5-122B-A10B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mixlayer", "providerName": "Mixlayer", "providerApi": "https://models.mixlayer.ai/v1", "providerDoc": "https://docs.mixlayer.com", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-122b-a10b", "modelKey": "qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B A10B", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen3.5-122b-a10b", "modelKey": "TEE/qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B A10B TEE", "metadata": { "lastUpdated": "2026-05-26", "openWeights": false, "releaseDate": "2026-05-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3.5-122B-A10B", "modelKey": "Qwen/Qwen3.5-122B-A10B", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen3.5-122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-26", "openWeights": true, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.5-122b-a10b", "modelKey": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen3.5 122B-A10B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-122B-A10B", "modelKey": "Qwen/Qwen3.5-122B-A10B", "displayName": "Qwen/Qwen3.5-122B-A10B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-26", "openWeights": true, "releaseDate": "2026-02-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-122b-a10b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-122b-a10b", "displayName": "Qwen: Qwen3.5-122B-A10B", "metadata": { "canonicalSlug": "qwen/qwen3.5-122b-a10b-20260224", "createdAt": "2026-02-25T21:09:49.000Z", "huggingFaceId": "Qwen/Qwen3.5-122B-A10B", "links": { "details": "/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-122b-a10b:thinking", "provider": "alibaba", "model": "qwen3.5-122b-a10b:thinking", "displayName": "Qwen3.5 122B A10B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-122b-a10b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 260096, "inputTokens": 260096, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-122b-a10b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.36, "output": 2.88 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 122B A10B Thinking" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-122b-a10b:thinking", "modelKey": "qwen3.5-122b-a10b:thinking", "displayName": "Qwen3.5 122B A10B Thinking", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } } ] }, { "id": "alibaba/qwen3.5-27b", "provider": "alibaba", "model": "qwen3.5-27b", "displayName": "Qwen3.5 27B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "kilo", "mixlayer", "nano-gpt", "novita-ai", "openrouter", "orcarouter", "siliconflow-cn" ], "aliases": [ "alibaba/qwen3.5-27b", "kilo/qwen/qwen3.5-27b", "mixlayer/qwen/qwen3.5-27b", "nano-gpt/TEE/qwen3.5-27b", "nano-gpt/qwen3.5-27b", "novita-ai/qwen/qwen3.5-27b", "openrouter/qwen/qwen3.5-27b", "orcarouter/qwen/qwen3.5-27b", "siliconflow-cn/Qwen/Qwen3.5-27B" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.4 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.195, "output": 1.56 } }, { "source": "models.dev", "provider": "mixlayer", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 2.16 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.195, "output": 1.56 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.086, "output": 0.688 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-27B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 2.09 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-27b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-27b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.195, "output": 1.56 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3.5-27B", "Qwen3.5 27B", "Qwen3.5 27B TEE", "Qwen3.5-27B", "Qwen: Qwen3.5-27B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-27b", "modelKey": "qwen3.5-27b", "displayName": "Qwen3.5 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-27b", "modelKey": "qwen/qwen3.5-27b", "displayName": "Qwen: Qwen3.5-27B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mixlayer", "providerName": "Mixlayer", "providerApi": "https://models.mixlayer.ai/v1", "providerDoc": "https://docs.mixlayer.com", "model": "qwen/qwen3.5-27b", "modelKey": "qwen/qwen3.5-27b", "displayName": "Qwen3.5 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-27b", "modelKey": "qwen3.5-27b", "displayName": "Qwen3.5 27B", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen3.5-27b", "modelKey": "TEE/qwen3.5-27b", "displayName": "Qwen3.5 27B TEE", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3.5-27b", "modelKey": "qwen/qwen3.5-27b", "displayName": "Qwen3.5-27B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-26", "openWeights": true, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-27b", "modelKey": "qwen/qwen3.5-27b", "displayName": "Qwen3.5 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.5-27b", "modelKey": "qwen/qwen3.5-27b", "displayName": "Qwen3.5 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-27B", "modelKey": "Qwen/Qwen3.5-27B", "displayName": "Qwen/Qwen3.5-27B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2026-02-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-27b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-27b" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-27b", "displayName": "Qwen: Qwen3.5-27B", "metadata": { "canonicalSlug": "qwen/qwen3.5-27b-20260224", "createdAt": "2026-02-25T21:10:10.000Z", "huggingFaceId": "Qwen/Qwen3.5-27B", "links": { "details": "/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-27b-anko", "provider": "alibaba", "model": "qwen3.5-27b-anko", "displayName": "Qwen3.5 27B Anko", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Anko" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Anko", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Anko" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Anko", "modelKey": "Qwen3.5-27B-Anko", "displayName": "Qwen3.5 27B Anko", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-derestricted", "displayName": "Qwen3.5 27B BlueStar Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar Derestricted" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-Derestricted", "modelKey": "Qwen3.5-27B-BlueStar-Derestricted", "displayName": "Qwen3.5 27B BlueStar Derestricted", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-derestricted-lite", "displayName": "Qwen3.5 27B BlueStar Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar Derestricted Lite" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-Derestricted-Lite", "modelKey": "Qwen3.5-27B-BlueStar-Derestricted-Lite", "displayName": "Qwen3.5 27B BlueStar Derestricted Lite", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-v2-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-v2-derestricted", "displayName": "Qwen3.5 27B BlueStar v2 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-v2-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-v2-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar v2 Derestricted" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-v2-Derestricted", "modelKey": "Qwen3.5-27B-BlueStar-v2-Derestricted", "displayName": "Qwen3.5 27B BlueStar v2 Derestricted", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-v2-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-v2-derestricted-lite", "displayName": "Qwen3.5 27B BlueStar v2 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-v2-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar v2 Derestricted Lite" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite", "modelKey": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite", "displayName": "Qwen3.5 27B BlueStar v2 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-v3-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-v3-derestricted", "displayName": "Qwen3.5 27B BlueStar v3 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-v3-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar v3 Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-v3-Derestricted", "modelKey": "Qwen3.5-27B-BlueStar-v3-Derestricted", "displayName": "Qwen3.5 27B BlueStar v3 Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-bluestar-v3-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-bluestar-v3-derestricted-lite", "displayName": "Qwen3.5 27B BlueStar v3 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B BlueStar v3 Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite", "modelKey": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite", "displayName": "Qwen3.5 27B BlueStar v3 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-derestricted", "displayName": "Qwen3.5 27B Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Derestricted" ], "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Derestricted", "modelKey": "Qwen3.5-27B-Derestricted", "displayName": "Qwen3.5 27B Derestricted", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "alibaba/qwen3.5-27b-earica-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-earica-derestricted", "displayName": "Qwen3.5 27B earica Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-earica-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-earica-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B earica Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-earica-Derestricted", "modelKey": "Qwen3.5-27B-earica-Derestricted", "displayName": "Qwen3.5 27B earica Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-earica-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-earica-derestricted-lite", "displayName": "Qwen3.5 27B earica Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-earica-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-earica-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B earica Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-earica-Derestricted-Lite", "modelKey": "Qwen3.5-27B-earica-Derestricted-Lite", "displayName": "Qwen3.5 27B earica Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-infracelestial", "provider": "alibaba", "model": "qwen3.5-27b-infracelestial", "displayName": "Qwen3.5 27B Infracelestial", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Infracelestial" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Infracelestial", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Infracelestial" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Infracelestial", "modelKey": "Qwen3.5-27B-Infracelestial", "displayName": "Qwen3.5 27B Infracelestial", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-marvin-dpo-v2-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-marvin-dpo-v2-derestricted", "displayName": "Qwen3.5 27B Marvin DPO V2 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Marvin-DPO-V2-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Marvin DPO V2 Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted", "modelKey": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted", "displayName": "Qwen3.5 27B Marvin DPO V2 Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-marvin-dpo-v2-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-marvin-dpo-v2-derestricted-lite", "displayName": "Qwen3.5 27B Marvin DPO V2 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Marvin DPO V2 Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite", "displayName": "Qwen3.5 27B Marvin DPO V2 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-marvin-v2-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-marvin-v2-derestricted", "displayName": "Qwen3.5 27B Marvin V2 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Marvin-V2-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Marvin-V2-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Marvin V2 Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Marvin-V2-Derestricted", "modelKey": "Qwen3.5-27B-Marvin-V2-Derestricted", "displayName": "Qwen3.5 27B Marvin V2 Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-marvin-v2-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-marvin-v2-derestricted-lite", "displayName": "Qwen3.5 27B Marvin V2 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Marvin-V2-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Marvin V2 Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite", "displayName": "Qwen3.5 27B Marvin V2 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-musica-v1", "provider": "alibaba", "model": "qwen3.5-27b-musica-v1", "displayName": "Qwen3.5 27B Musica v1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Musica-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Musica-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Musica v1" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Musica-v1", "modelKey": "Qwen3.5-27B-Musica-v1", "displayName": "Qwen3.5 27B Musica v1", "metadata": { "lastUpdated": "2026-03-27", "openWeights": false, "releaseDate": "2026-03-27" } } ] }, { "id": "alibaba/qwen3.5-27b-nanovel-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-nanovel-derestricted", "displayName": "Qwen3.5 27B NaNovel Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-NaNovel-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-NaNovel-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B NaNovel Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-NaNovel-Derestricted", "modelKey": "Qwen3.5-27B-NaNovel-Derestricted", "displayName": "Qwen3.5 27B NaNovel Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-nanovel-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-nanovel-derestricted-lite", "displayName": "Qwen3.5 27B NaNovel Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-NaNovel-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-NaNovel-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B NaNovel Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-NaNovel-Derestricted-Lite", "modelKey": "Qwen3.5-27B-NaNovel-Derestricted-Lite", "displayName": "Qwen3.5 27B NaNovel Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-omega-evolution-v2.0-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-omega-evolution-v2.0-derestricted", "displayName": "Qwen3.5 27B Omega Evolution v2.0 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Omega Evolution v2.0 Derestricted" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted", "modelKey": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted", "displayName": "Qwen3.5 27B Omega Evolution v2.0 Derestricted", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-omega-evolution-v2.0-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-omega-evolution-v2.0-derestricted-lite", "displayName": "Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite", "displayName": "Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-omega-evolution-v2.2-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-omega-evolution-v2.2-derestricted", "displayName": "Qwen3.5 27B Omega Evolution v2.2 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Omega Evolution v2.2 Derestricted" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted", "modelKey": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted", "displayName": "Qwen3.5 27B Omega Evolution v2.2 Derestricted", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "alibaba/qwen3.5-27b-omega-evolution-v2.2-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-omega-evolution-v2.2-derestricted-lite", "displayName": "Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite", "displayName": "Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "alibaba/qwen3.5-27b-queen-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-queen-derestricted", "displayName": "Qwen3.5 27B Queen Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Queen-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Queen-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Queen Derestricted" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Queen-Derestricted", "modelKey": "Qwen3.5-27B-Queen-Derestricted", "displayName": "Qwen3.5 27B Queen Derestricted", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-queen-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-queen-derestricted-lite", "displayName": "Qwen3.5 27B Queen Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Queen-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Queen-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Queen Derestricted Lite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Queen-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Queen-Derestricted-Lite", "displayName": "Qwen3.5 27B Queen Derestricted Lite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-rprmax-v1", "provider": "alibaba", "model": "qwen3.5-27b-rprmax-v1", "displayName": "Qwen3.5 27B RpRMax v1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-RpRMax-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-RpRMax-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B RpRMax v1" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-RpRMax-v1", "modelKey": "Qwen3.5-27B-RpRMax-v1", "displayName": "Qwen3.5 27B RpRMax v1", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "alibaba/qwen3.5-27b-vivid-durian", "provider": "alibaba", "model": "qwen3.5-27b-vivid-durian", "displayName": "Qwen3.5 27B Vivid Durian", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Vivid-Durian" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Vivid-Durian", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Vivid Durian" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Vivid-Durian", "modelKey": "Qwen3.5-27B-Vivid-Durian", "displayName": "Qwen3.5 27B Vivid Durian", "metadata": { "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "alibaba/qwen3.5-27b-writer-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-writer-derestricted", "displayName": "Qwen3.5 27B Writer Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Writer-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Writer-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Writer Derestricted" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Writer-Derestricted", "modelKey": "Qwen3.5-27B-Writer-Derestricted", "displayName": "Qwen3.5 27B Writer Derestricted", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-writer-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-writer-derestricted-lite", "displayName": "Qwen3.5 27B Writer Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Writer-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Writer-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Writer Derestricted Lite" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Writer-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Writer-Derestricted-Lite", "displayName": "Qwen3.5 27B Writer Derestricted Lite", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-writer-v2-derestricted", "provider": "alibaba", "model": "qwen3.5-27b-writer-v2-derestricted", "displayName": "Qwen3.5 27B Writer V2 Derestricted", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Writer-V2-Derestricted" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Writer-V2-Derestricted", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Writer V2 Derestricted" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Writer-V2-Derestricted", "modelKey": "Qwen3.5-27B-Writer-V2-Derestricted", "displayName": "Qwen3.5 27B Writer V2 Derestricted", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b-writer-v2-derestricted-lite", "provider": "alibaba", "model": "qwen3.5-27b-writer-v2-derestricted-lite", "displayName": "Qwen3.5 27B Writer V2 Derestricted Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Qwen3.5-27B-Writer-V2-Derestricted-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Qwen3.5-27B-Writer-V2-Derestricted-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Writer V2 Derestricted Lite" ], "releaseDate": "2026-04-06", "lastUpdated": "2026-04-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Qwen3.5-27B-Writer-V2-Derestricted-Lite", "modelKey": "Qwen3.5-27B-Writer-V2-Derestricted-Lite", "displayName": "Qwen3.5 27B Writer V2 Derestricted Lite", "metadata": { "lastUpdated": "2026-04-06", "openWeights": false, "releaseDate": "2026-04-06" } } ] }, { "id": "alibaba/qwen3.5-27b:thinking", "provider": "alibaba", "model": "qwen3.5-27b:thinking", "displayName": "Qwen3.5 27B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-27b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 260096, "inputTokens": 260096, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-27b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 2.16 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 27B Thinking" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-27b:thinking", "modelKey": "qwen3.5-27b:thinking", "displayName": "Qwen3.5 27B Thinking", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } } ] }, { "id": "alibaba/qwen3.5-35b-a3b", "provider": "alibaba", "model": "qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B-A3B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "deepinfra", "kilo", "mixlayer", "nano-gpt", "novita-ai", "openrouter", "orcarouter", "siliconflow-cn" ], "aliases": [ "alibaba/qwen3.5-35b-a3b", "deepinfra/Qwen/Qwen3.5-35B-A3B", "kilo/qwen/qwen3.5-35b-a3b", "mixlayer/qwen/qwen3.5-35b-a3b", "nano-gpt/qwen3.5-35b-a3b", "novita-ai/qwen/qwen3.5-35b-a3b", "openrouter/qwen/qwen3.5-35b-a3b", "orcarouter/qwen/qwen3.5-35b-a3b", "siliconflow-cn/Qwen/Qwen3.5-35B-A3B" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "deepinfra", "model": "Qwen/Qwen3.5-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.14, "output": 1 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1625, "output": 1.3 } }, { "source": "models.dev", "provider": "mixlayer", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.225, "output": 1.8 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.057, "output": 0.459 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "output": 1.86 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-35b-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-35b-a3b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 1 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 35B A3B", "Qwen/Qwen3.5-35B-A3B", "Qwen3.5 35B A3B", "Qwen3.5 35B-A3B", "Qwen3.5-35B-A3B", "Qwen: Qwen3.5-35B-A3B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-35b-a3b", "modelKey": "qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "Qwen/Qwen3.5-35B-A3B", "modelKey": "Qwen/Qwen3.5-35B-A3B", "displayName": "Qwen 3.5 35B A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-35b-a3b", "modelKey": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen: Qwen3.5-35B-A3B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mixlayer", "providerName": "Mixlayer", "providerApi": "https://models.mixlayer.ai/v1", "providerDoc": "https://docs.mixlayer.com", "model": "qwen/qwen3.5-35b-a3b", "modelKey": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-35b-a3b", "modelKey": "qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B A3B", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3.5-35b-a3b", "modelKey": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen3.5-35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-26", "openWeights": true, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-35b-a3b", "modelKey": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.5-35b-a3b", "modelKey": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen3.5 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-23", "openWeights": true, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-35B-A3B", "modelKey": "Qwen/Qwen3.5-35B-A3B", "displayName": "Qwen/Qwen3.5-35B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2026-02-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-35b-a3b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-35b-a3b", "displayName": "Qwen: Qwen3.5-35B-A3B", "metadata": { "canonicalSlug": "qwen/qwen3.5-35b-a3b-20260224", "createdAt": "2026-02-25T21:10:22.000Z", "huggingFaceId": "Qwen/Qwen3.5-35B-A3B", "links": { "details": "/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-35b-a3b:thinking", "provider": "alibaba", "model": "qwen3.5-35b-a3b:thinking", "displayName": "Qwen3.5 35B A3B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-35b-a3b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 260096, "inputTokens": 260096, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-35b-a3b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.225, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 35B A3B Thinking" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-35b-a3b:thinking", "modelKey": "qwen3.5-35b-a3b:thinking", "displayName": "Qwen3.5 35B A3B Thinking", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } } ] }, { "id": "alibaba/qwen3.5-397b-a17b", "provider": "alibaba", "model": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "cortecs", "crof", "deepinfra", "digitalocean", "huggingface", "kilo", "mixlayer", "nano-gpt", "nebius", "novita-ai", "nvidia", "openrouter", "orcarouter", "ovhcloud", "qiniu-ai", "scaleway", "siliconflow-cn", "synthetic", "together_ai", "togetherai", "wafer.ai" ], "aliases": [ "alibaba-cn/qwen3.5-397b-a17b", "alibaba/qwen3.5-397b-a17b", "cortecs/qwen3.5-397b-a17b", "crof/qwen3.5-397b-a17b", "deepinfra/Qwen/Qwen3.5-397B-A17B", "digitalocean/qwen3.5-397b-a17b", "huggingface/Qwen/Qwen3.5-397B-A17B", "kilo/qwen/qwen3.5-397b-a17b", "mixlayer/qwen/qwen3.5-397b-a17b", "nano-gpt/TEE/qwen3.5-397b-a17b", "nano-gpt/qwen/qwen3.5-397b-a17b", "nebius/Qwen/Qwen3.5-397B-A17B", "novita-ai/qwen/qwen3.5-397b-a17b", "nvidia/qwen/qwen3.5-397b-a17b", "openrouter/qwen/qwen3.5-397b-a17b", "orcarouter/qwen/qwen3.5-397b-a17b", "ovhcloud/qwen3.5-397b-a17b", "qiniu-ai/qwen3.5-397b-a17b", "scaleway/qwen3.5-397b-a17b", "siliconflow-cn/Qwen/Qwen3.5-397B-A17B", "synthetic/hf:Qwen/Qwen3.5-397B-A17B", "together_ai/Qwen/Qwen3.5-397B-A17B", "togetherai/Qwen/Qwen3.5-397B-A17B", "wafer.ai/Qwen3.5-397B-A17B" ], "mergedProviderModelRecords": 24, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.43, "output": 2.58, "reasoningOutput": 2.58 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "cortecs", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "crof", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.35, "output": 1.75 } }, { "source": "models.dev", "provider": "deepinfra", "model": "Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 0.45, "output": 3 } }, { "source": "models.dev", "provider": "digitalocean", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 3.5 } }, { "source": "models.dev", "provider": "huggingface", "model": "Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.39, "output": 2.34 } }, { "source": "models.dev", "provider": "mixlayer", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.75, "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "nvidia", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.385, "output": 2.45 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.172, "output": 1.032 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.71, "output": 4.25 } }, { "source": "models.dev", "provider": "scaleway", "model": "qwen3.5-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.74 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "Qwen3.5-397B-A17B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "cacheWrite": 0, "input": 0.43, "output": 2.6 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-397b-a17b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3.5-397B-A17B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-397b-a17b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.385, "output": 2.45 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 397B A17B", "Qwen/Qwen3.5-397B-A17B", "Qwen3.5 397B A17B", "Qwen3.5 397B A17B TEE", "Qwen3.5 397B-A17B", "Qwen3.5-397B-A17B", "Qwen3.5-97B-A17B", "Qwen: Qwen3.5 397B A17B" ], "families": [ "qwen", "qwen3.5" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-16", "lastUpdated": "2026-02-16", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 24 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": true, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-16", "openWeights": true, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "Qwen/Qwen3.5-397B-A17B", "modelKey": "Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen 3.5 397B A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen 3.5 397B A17B", "family": "qwen3.5", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-02-15", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "Qwen/Qwen3.5-397B-A17B", "modelKey": "Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen3.5-397B-A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen: Qwen3.5 397B A17B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mixlayer", "providerName": "Mixlayer", "providerApi": "https://models.mixlayer.ai/v1", "providerDoc": "https://docs.mixlayer.com", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-16", "openWeights": true, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen3.5-397b-a17b", "modelKey": "TEE/qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B TEE", "family": "qwen", "metadata": { "lastUpdated": "2026-02-28", "openWeights": false, "releaseDate": "2026-02-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3.5-397B-A17B", "modelKey": "Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen3.5-397B-A17B", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-07-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5-397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-17", "openWeights": true, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5-397B-A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-16", "openWeights": true, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.5-397b-a17b", "modelKey": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5-397B-A17B", "metadata": { "lastUpdated": "2026-05-18", "openWeights": true, "releaseDate": "2026-05-18", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B", "metadata": { "lastUpdated": "2026-02-22", "openWeights": false, "releaseDate": "2026-02-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "qwen3.5-397b-a17b", "modelKey": "qwen3.5-397b-a17b", "displayName": "Qwen3.5 397B A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-397B-A17B", "modelKey": "Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen/Qwen3.5-397B-A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": true, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:Qwen/Qwen3.5-397B-A17B", "modelKey": "hf:Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen3.5-97B-A17B", "family": "qwen", "status": "beta", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3.5-397B-A17B", "modelKey": "Qwen/Qwen3.5-397B-A17B", "displayName": "Qwen3.5 397B A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-15", "openWeights": true, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "Qwen3.5-397B-A17B", "modelKey": "Qwen3.5-397B-A17B", "displayName": "Qwen3.5-397B-A17B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-397b-a17b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/Qwen/Qwen3.5-397B-A17B", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-397b-a17b", "displayName": "Qwen: Qwen3.5 397B A17B", "metadata": { "canonicalSlug": "qwen/qwen3.5-397b-a17b-20260216", "createdAt": "2026-02-16T06:23:38.000Z", "huggingFaceId": "Qwen/Qwen3.5-397B-A17B", "links": { "details": "/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-397b-a17b-fast", "provider": "alibaba", "model": "qwen3.5-397b-a17b-fast", "displayName": "Qwen3.5-397B-A17B-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/Qwen/Qwen3.5-397B-A17B-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "Qwen/Qwen3.5-397B-A17B-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.75, "input": 0.6, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "Qwen3.5-397B-A17B-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-15", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "Qwen/Qwen3.5-397B-A17B-fast", "modelKey": "Qwen/Qwen3.5-397B-A17B-fast", "displayName": "Qwen3.5-397B-A17B-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-07-15", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.5-397b-a17b-fp8", "provider": "alibaba", "model": "qwen3.5-397b-a17b-fp8", "displayName": "Qwen3.5 397B A17B FP8", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262128, "outputTokens": 262128, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "Qwen/Qwen3.5-397B-A17B-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69, "output": 4.14 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 397B A17B FP8" ], "families": [ "qwen" ], "releaseDate": "2026-02-01", "lastUpdated": "2026-02-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "Qwen/Qwen3.5-397B-A17B-FP8", "modelKey": "Qwen/Qwen3.5-397B-A17B-FP8", "displayName": "Qwen3.5 397B A17B FP8", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.5-397b-a17b-tee", "provider": "alibaba", "model": "qwen3.5-397b-a17b-tee", "displayName": "Qwen3.5 397B A17B TEE", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/Qwen/Qwen3.5-397B-A17B-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3.5-397B-A17B-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.195, "input": 0.39, "output": 2.34 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 397B A17B TEE" ], "families": [ "qwen" ], "releaseDate": "2026-02-15", "lastUpdated": "2026-02-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3.5-397B-A17B-TEE", "modelKey": "Qwen/Qwen3.5-397B-A17B-TEE", "displayName": "Qwen3.5 397B A17B TEE", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.5-397b-a17b-thinking", "provider": "alibaba", "model": "qwen3.5-397b-a17b-thinking", "displayName": "Qwen3.5 397B A17B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen/qwen3.5-397b-a17b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 258048, "inputTokens": 258048, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3.5-397b-a17b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 397B A17B Thinking" ], "releaseDate": "2026-02-16", "lastUpdated": "2026-02-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3.5-397b-a17b-thinking", "modelKey": "qwen/qwen3.5-397b-a17b-thinking", "displayName": "Qwen3.5 397B A17B Thinking", "metadata": { "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } } ] }, { "id": "alibaba/qwen3.5-397b-fast", "provider": "alibaba", "model": "qwen3.5-397b-fast", "displayName": "Qwen3.5 397B Fast", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/qwen3.5-397b-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262128, "outputTokens": 262128, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "qwen3.5-397b-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69, "output": 4.14 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 397B Fast" ], "families": [ "qwen" ], "releaseDate": "2026-02-01", "lastUpdated": "2026-02-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "qwen3.5-397b-fast", "modelKey": "qwen3.5-397b-fast", "displayName": "Qwen3.5 397B Fast", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01" } } ] }, { "id": "alibaba/qwen3.5-4b", "provider": "alibaba", "model": "qwen3.5-4b", "displayName": "Qwen/Qwen3.5-4B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/Qwen/Qwen3.5-4B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-4B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3.5-4B" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-4B", "modelKey": "Qwen/Qwen3.5-4B", "displayName": "Qwen/Qwen3.5-4B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-03", "openWeights": true, "releaseDate": "2026-03-03" } } ] }, { "id": "alibaba/qwen3.5-9b", "provider": "alibaba", "model": "qwen3.5-9b", "displayName": "Qwen3.5 9B", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "crof", "kilo", "mixlayer", "nano-gpt", "openrouter", "ovhcloud", "regolo-ai", "siliconflow-cn", "togetherai" ], "aliases": [ "crof/qwen3.5-9b", "kilo/qwen/qwen3.5-9b", "mixlayer/qwen/qwen3.5-9b", "nano-gpt/qwen/qwen3.5-9b", "openrouter/qwen/qwen3.5-9b", "ovhcloud/qwen3.5-9b", "regolo-ai/qwen3.5-9b", "siliconflow-cn/Qwen/Qwen3.5-9B", "togetherai/Qwen/Qwen3.5-9B" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.008, "input": 0.04, "output": 0.15 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.15 } }, { "source": "models.dev", "provider": "mixlayer", "model": "qwen/qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.15 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.15 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.18 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "qwen3.5-9b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.5-9B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 1.74 } }, { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3.5-9B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-9b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3.5-9B", "Qwen3.5 9B", "Qwen3.5-9B", "Qwen: Qwen3.5-9B" ], "families": [ "qwen", "qwen3.5" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-03-13", "lastUpdated": "2026-03-13", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "qwen3.5-9b", "modelKey": "qwen3.5-9b", "displayName": "Qwen3.5 9B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-13", "openWeights": true, "releaseDate": "2026-03-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-9b", "modelKey": "qwen/qwen3.5-9b", "displayName": "Qwen: Qwen3.5-9B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-03-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mixlayer", "providerName": "Mixlayer", "providerApi": "https://models.mixlayer.ai/v1", "providerDoc": "https://docs.mixlayer.com", "model": "qwen/qwen3.5-9b", "modelKey": "qwen/qwen3.5-9b", "displayName": "Qwen3.5 9B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3.5-9b", "modelKey": "qwen/qwen3.5-9b", "displayName": "Qwen3.5 9B", "metadata": { "lastUpdated": "2026-03-10", "openWeights": false, "releaseDate": "2026-03-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-9b", "modelKey": "qwen/qwen3.5-9b", "displayName": "Qwen3.5-9B", "family": "qwen3.5", "metadata": { "lastUpdated": "2026-03-10", "openWeights": true, "releaseDate": "2026-03-10", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3.5-9b", "modelKey": "qwen3.5-9b", "displayName": "Qwen3.5-9B", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "qwen3.5-9b", "modelKey": "qwen3.5-9b", "displayName": "Qwen3.5-9B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-01", "openWeights": true, "releaseDate": "2026-02-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.5-9B", "modelKey": "Qwen/Qwen3.5-9B", "displayName": "Qwen/Qwen3.5-9B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-03-03", "openWeights": true, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3.5-9B", "modelKey": "Qwen/Qwen3.5-9B", "displayName": "Qwen3.5 9B", "family": "qwen", "metadata": { "lastUpdated": "2026-03-03", "openWeights": true, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-9b", "displayName": "Qwen: Qwen3.5-9B", "metadata": { "canonicalSlug": "qwen/qwen3.5-9b-20260310", "createdAt": "2026-03-10T14:19:56.000Z", "huggingFaceId": "Qwen/Qwen3.5-9B", "links": { "details": "/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-flash", "provider": "alibaba", "model": "qwen3.5-flash", "displayName": "Qwen3.5 Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn", "nano-gpt", "vercel", "zenmux" ], "aliases": [ "alibaba-cn/qwen3.5-flash", "nano-gpt/qwen3.5-flash", "vercel/alibaba/qwen3.5-flash", "zenmux/qwen/qwen3.5-flash" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1020000, "inputTokens": 991808, "outputTokens": 1020000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.172, "output": 1.72, "reasoningOutput": 1.72 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.001, "cacheWrite": 0.125, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Qwen 3.5 Flash", "Qwen3.5 Flash" ], "families": [ "qwen" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-flash", "modelKey": "qwen3.5-flash", "displayName": "Qwen3.5 Flash", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-23", "openWeights": false, "releaseDate": "2026-02-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-flash", "modelKey": "qwen3.5-flash", "displayName": "Qwen3.5 Flash", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.5-flash", "modelKey": "alibaba/qwen3.5-flash", "displayName": "Qwen 3.5 Flash", "family": "qwen", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3.5-flash", "modelKey": "qwen/qwen3.5-flash", "displayName": "Qwen3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "alibaba/qwen3.5-flash-02-23", "provider": "alibaba", "model": "qwen3.5-flash-02-23", "displayName": "Qwen3.5-Flash", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen3.5-flash-02-23", "openrouter/qwen/qwen3.5-flash-02-23" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-flash-02-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-flash-02-23", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.065, "output": 0.26 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-flash-02-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-flash-02-23", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.065, "output": 0.26 } } ] }, "metadata": { "displayNames": [ "Qwen3.5-Flash", "Qwen: Qwen3.5-Flash" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-flash-02-23", "modelKey": "qwen/qwen3.5-flash-02-23", "displayName": "Qwen: Qwen3.5-Flash", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-flash-02-23", "modelKey": "qwen/qwen3.5-flash-02-23", "displayName": "Qwen3.5-Flash", "family": "qwen", "metadata": { "lastUpdated": "2026-02-25", "openWeights": false, "releaseDate": "2026-02-25", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-flash-02-23", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-flash-02-23", "displayName": "Qwen: Qwen3.5-Flash", "metadata": { "canonicalSlug": "qwen/qwen3.5-flash-20260224", "createdAt": "2026-02-25T21:09:36.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-flash:thinking", "provider": "alibaba", "model": "qwen3.5-flash:thinking", "displayName": "Qwen3.5 Flash Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-flash:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 991808, "inputTokens": 991808, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-flash:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Flash Thinking" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-flash:thinking", "modelKey": "qwen3.5-flash:thinking", "displayName": "Qwen3.5 Flash Thinking", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } } ] }, { "id": "alibaba/qwen3.5-omni-flash", "provider": "alibaba", "model": "qwen3.5-omni-flash", "displayName": "Qwen3.5 Omni Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-omni-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 49152, "inputTokens": 49152, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-omni-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Omni Flash" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-03-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-omni-flash", "modelKey": "qwen3.5-omni-flash", "displayName": "Qwen3.5 Omni Flash", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } } ] }, { "id": "alibaba/qwen3.5-omni-plus", "provider": "alibaba", "model": "qwen3.5-omni-plus", "displayName": "Qwen3.5 Omni Plus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.5-omni-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 983616, "inputTokens": 983616, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.5-omni-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Omni Plus" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-03-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.5-omni-plus", "modelKey": "qwen3.5-omni-plus", "displayName": "Qwen3.5 Omni Plus", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } } ] }, { "id": "alibaba/qwen3.5-plus", "provider": "alibaba", "model": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "dashscope", "meganova", "nano-gpt", "opencode", "opencode-go", "orcarouter", "vercel", "zenmux" ], "aliases": [ "alibaba-cn/qwen3.5-plus", "alibaba-coding-plan-cn/qwen3.5-plus", "alibaba-coding-plan/qwen3.5-plus", "alibaba/qwen3.5-plus", "dashscope/qwen3.5-plus", "meganova/Qwen/Qwen3.5-Plus", "nano-gpt/qwen/qwen3.5-plus", "opencode-go/qwen3.5-plus", "opencode/qwen3.5-plus", "orcarouter/qwen/qwen3.5-plus", "vercel/alibaba/qwen3.5-plus", "zenmux/qwen/qwen3.5-plus" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 1000000, "inputTokens": 991808, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.573, "output": 3.44, "reasoningOutput": 3.44 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2.4, "reasoningOutput": 2.4 } }, { "source": "models.dev", "provider": "meganova", "model": "Qwen/Qwen3.5-Plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2.4, "reasoningOutput": 2.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2.4 } }, { "source": "models.dev", "provider": "opencode-go", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.25, "input": 0.2, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode", "model": "qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.25, "input": 0.2, "output": 1.2 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.115, "output": 0.688, "reasoningOutput": 2.4 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "cacheWrite": 0.5, "input": 0.4, "output": 2.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3.5-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 4.8 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwen3.5-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Qwen 3.5 Plus", "Qwen3.5 Plus" ], "families": [ "qwen", "qwen3.5" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-16", "lastUpdated": "2026-02-16", "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "Qwen/Qwen3.5-Plus", "modelKey": "Qwen/Qwen3.5-Plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02", "openWeights": false, "releaseDate": "2026-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3.5-plus", "modelKey": "qwen/qwen3.5-plus", "displayName": "Qwen3.5 Plus", "metadata": { "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen3.5", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.5-plus", "modelKey": "qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen3.5", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.5-plus", "modelKey": "qwen/qwen3.5-plus", "displayName": "Qwen3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.5-plus", "modelKey": "alibaba/qwen3.5-plus", "displayName": "Qwen 3.5 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3.5-plus", "modelKey": "qwen/qwen3.5-plus", "displayName": "Qwen3.5 Plus", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwen3.5-plus", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/qwen3.5-plus-02-15", "provider": "alibaba", "model": "qwen3.5-plus-02-15", "displayName": "Qwen3.5 Plus 2026-02-15", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen3.5-plus-02-15", "openrouter/qwen/qwen3.5-plus-02-15" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-plus-02-15", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 1.56 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-plus-02-15", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 1.56 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-plus-02-15", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2.4 }, "extra": { "input_cost_per_token_above_256k_tokens": 5e-7, "output_cost_per_token_above_256k_tokens": 0.000003 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-plus-02-15", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.26, "output": 1.56 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Plus 2026-02-15", "Qwen: Qwen3.5 Plus 2026-02-15" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-15", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-plus-02-15", "modelKey": "qwen/qwen3.5-plus-02-15", "displayName": "Qwen: Qwen3.5 Plus 2026-02-15", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-plus-02-15", "modelKey": "qwen/qwen3.5-plus-02-15", "displayName": "Qwen3.5 Plus 2026-02-15", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.5-plus-02-15", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-plus-02-15", "displayName": "Qwen: Qwen3.5 Plus 2026-02-15", "metadata": { "canonicalSlug": "qwen/qwen3.5-plus-20260216", "createdAt": "2026-02-16T08:10:16.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-plus-20260420", "provider": "alibaba", "model": "qwen3.5-plus-20260420", "displayName": "Qwen: Qwen3.5 Plus 2026-04-20", "family": "qwen3.5", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/qwen/qwen3.5-plus-20260420", "openrouter/qwen/qwen3.5-plus-20260420" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.5-plus-20260420", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.5-plus-20260420", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.375, "input": 0.3, "output": 1.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.5-plus-20260420", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 0.375, "input": 0.3, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Plus 2026-04-20", "Qwen: Qwen3.5 Plus 2026-04-20" ], "families": [ "qwen3.5" ], "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.5-plus-20260420", "modelKey": "qwen/qwen3.5-plus-20260420", "displayName": "Qwen: Qwen3.5 Plus 2026-04-20", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.5-plus-20260420", "modelKey": "qwen/qwen3.5-plus-20260420", "displayName": "Qwen3.5 Plus 2026-04-20", "family": "qwen3.5", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.5-plus-20260420", "displayName": "Qwen: Qwen3.5 Plus 2026-04-20", "metadata": { "canonicalSlug": "qwen/qwen3.5-plus-20260420", "createdAt": "2026-04-27T03:42:48.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.5-plus-thinking", "provider": "alibaba", "model": "qwen3.5-plus-thinking", "displayName": "Qwen3.5 Plus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen/qwen3.5-plus-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 983616, "inputTokens": 983616, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwen3.5-plus-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 Plus Thinking" ], "releaseDate": "2026-02-16", "lastUpdated": "2026-02-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwen3.5-plus-thinking", "modelKey": "qwen/qwen3.5-plus-thinking", "displayName": "Qwen3.5 Plus Thinking", "metadata": { "lastUpdated": "2026-02-16", "openWeights": false, "releaseDate": "2026-02-16" } } ] }, { "id": "alibaba/qwen3.5:397b", "provider": "alibaba", "model": "qwen3.5:397b", "displayName": "qwen3.5:397b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/qwen3.5:397b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "qwen3.5:397b" ], "families": [ "qwen" ], "releaseDate": "2026-02-15", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "qwen3.5:397b", "modelKey": "qwen3.5:397b", "displayName": "qwen3.5:397b", "family": "qwen", "metadata": { "lastUpdated": "2026-02-17", "openWeights": true, "releaseDate": "2026-02-15", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.6-27b", "provider": "alibaba", "model": "qwen3.6-27b", "displayName": "Qwen3.6 27B", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba", "crof", "kilo", "nano-gpt", "openrouter", "ovhcloud", "routing-run", "vercel" ], "aliases": [ "alibaba/qwen3.6-27b", "crof/qwen3.6-27b", "kilo/qwen/qwen3.6-27b", "nano-gpt/alibaba/qwen3.6-27b", "openrouter/qwen/qwen3.6-27b", "ovhcloud/qwen3.6-27b", "routing-run/route/qwen3.6-27b", "vercel/alibaba/qwen3.6-27b" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 262144, "inputTokens": 260096, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "models.dev", "provider": "crof", "model": "qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.325, "output": 3.25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "alibaba/qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.203, "output": 2.24 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2885, "output": 3.17 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.47, "output": 3.19 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.3 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.6-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.6-27b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2885, "output": 3.17 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 27B", "Qwen3.6 27B", "Qwen3.6-27B", "Qwen: Qwen3.6 27B" ], "families": [ "qwen", "qwen3.6" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-27b", "modelKey": "qwen3.6-27b", "displayName": "Qwen3.6 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "qwen3.6-27b", "modelKey": "qwen3.6-27b", "displayName": "Qwen3.6 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.6-27b", "modelKey": "qwen/qwen3.6-27b", "displayName": "Qwen: Qwen3.6 27B", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "alibaba/qwen3.6-27b", "modelKey": "alibaba/qwen3.6-27b", "displayName": "Qwen3.6 27B", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.6-27b", "modelKey": "qwen/qwen3.6-27b", "displayName": "Qwen3.6 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3.6-27b", "modelKey": "qwen3.6-27b", "displayName": "Qwen3.6-27B", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/qwen3.6-27b", "modelKey": "route/qwen3.6-27b", "displayName": "Qwen3.6 27B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.6-27b", "modelKey": "alibaba/qwen3.6-27b", "displayName": "Qwen 3.6 27B", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-22", "openWeights": false, "releaseDate": "2026-04-22" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.6-27b", "displayName": "Qwen: Qwen3.6 27B", "metadata": { "canonicalSlug": "qwen/qwen3.6-27b-20260422", "createdAt": "2026-04-27T01:57:44.000Z", "huggingFaceId": "Qwen/Qwen3.6-27B", "links": { "details": "/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262140, "max_completion_tokens": 262140, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.6-27b-202k", "provider": "alibaba", "model": "qwen3.6-27b-202k", "displayName": "Qwen3.6 27B 202K", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/qwen3.6-27b-202k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/qwen3.6-27b-202k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.3 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 27B 202K" ], "families": [ "qwen" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/qwen3.6-27b-202k", "modelKey": "route/qwen3.6-27b-202k", "displayName": "Qwen3.6 27B 202K", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "alibaba/qwen3.6-27b-tee", "provider": "alibaba", "model": "qwen3.6-27b-tee", "displayName": "Qwen3.6 27B TEE", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/Qwen/Qwen3.6-27B-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3.6-27B-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0975, "input": 0.195, "output": 1.56 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 27B TEE" ], "families": [ "qwen" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3.6-27B-TEE", "modelKey": "Qwen/Qwen3.6-27B-TEE", "displayName": "Qwen3.6 27B TEE", "family": "qwen", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.6-27b:thinking", "provider": "alibaba", "model": "qwen3.6-27b:thinking", "displayName": "Qwen3.6 27B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/alibaba/qwen3.6-27b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 260096, "inputTokens": 260096, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "alibaba/qwen3.6-27b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.203, "output": 2.24 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 27B Thinking" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "alibaba/qwen3.6-27b:thinking", "modelKey": "alibaba/qwen3.6-27b:thinking", "displayName": "Qwen3.6 27B Thinking", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "alibaba/qwen3.6-35b-a3b", "provider": "alibaba", "model": "qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba", "deepinfra", "kilo", "llmgateway", "nano-gpt", "neuralwatt", "openrouter", "orcarouter", "scaleway", "siliconflow-cn", "wafer.ai" ], "aliases": [ "alibaba/qwen3.6-35b-a3b", "deepinfra/Qwen/Qwen3.6-35B-A3B", "kilo/qwen/qwen3.6-35b-a3b", "llmgateway/qwen3.6-35b-a3b", "nano-gpt/qwen/Qwen3.6-35B-A3B", "neuralwatt/Qwen/Qwen3.6-35B-A3B", "openrouter/qwen/qwen3.6-35b-a3b", "orcarouter/qwen/qwen3.6-35b-a3b", "scaleway/qwen3.6-35b-a3b", "siliconflow-cn/Qwen/Qwen3.6-35B-A3B", "wafer.ai/Qwen3.6-35B-A3B" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba", "model": "qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.248, "output": 1.485 } }, { "source": "models.dev", "provider": "deepinfra", "model": "Qwen/Qwen3.6-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.95 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1612, "input": 0.1612, "output": 0.96525 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.248, "output": 1.485 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3.6-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.112, "output": 0.8 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "Qwen/Qwen3.6-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.15 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.248, "output": 1.485 } }, { "source": "models.dev", "provider": "scaleway", "model": "qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/Qwen3.6-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "output": 1.86 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "Qwen3.6-35B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0, "input": 0.15, "output": 1 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.6-35b-a3b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 1 } } ] }, "metadata": { "displayNames": [ "Qwen/Qwen3.6-35B-A3B", "Qwen3.6 35B A3B", "Qwen3.6 35B-A3B", "Qwen3.6-35B-A3B", "Qwen: Qwen3.6 35B A3B" ], "families": [ "qwen", "qwen3.6" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-35b-a3b", "modelKey": "qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "Qwen/Qwen3.6-35B-A3B", "modelKey": "Qwen/Qwen3.6-35B-A3B", "displayName": "Qwen3.6 35B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.6-35b-a3b", "modelKey": "qwen/qwen3.6-35b-a3b", "displayName": "Qwen: Qwen3.6 35B A3B", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3.6-35b-a3b", "modelKey": "qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3.6-35B-A3B", "modelKey": "qwen/Qwen3.6-35B-A3B", "displayName": "Qwen3.6 35B A3B", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "Qwen/Qwen3.6-35B-A3B", "modelKey": "Qwen/Qwen3.6-35B-A3B", "displayName": "Qwen3.6 35B A3B", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.6-35b-a3b", "modelKey": "qwen/qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.6-35b-a3b", "modelKey": "qwen/qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B-A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "qwen3.6-35b-a3b", "modelKey": "qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B A3B", "family": "qwen", "status": "beta", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-22", "openWeights": true, "releaseDate": "2026-05-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/Qwen3.6-35B-A3B", "modelKey": "Qwen/Qwen3.6-35B-A3B", "displayName": "Qwen/Qwen3.6-35B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "Qwen3.6-35B-A3B", "modelKey": "Qwen3.6-35B-A3B", "displayName": "Qwen3.6-35B-A3B", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-30", "openWeights": true, "releaseDate": "2026-05-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.6-35b-a3b", "displayName": "Qwen: Qwen3.6 35B A3B", "metadata": { "canonicalSlug": "qwen/qwen3.6-35b-a3b-20260415", "createdAt": "2026-04-27T03:24:15.000Z", "huggingFaceId": "Qwen/Qwen3.6-35B-A3B", "links": { "details": "/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.6-35b-a3b-fp8", "provider": "alibaba", "model": "qwen3.6-35b-a3b-fp8", "displayName": "Qwen 3.6 35B A3B FP8", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nearai" ], "aliases": [ "nearai/Qwen/Qwen3.6-35B-A3B-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nearai", "model": "Qwen/Qwen3.6-35B-A3B-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.056, "input": 0.17, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 35B A3B FP8" ], "families": [ "qwen" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "Qwen/Qwen3.6-35B-A3B-FP8", "modelKey": "Qwen/Qwen3.6-35B-A3B-FP8", "displayName": "Qwen 3.6 35B A3B FP8", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "alibaba/qwen3.6-35b-a3b-uncensored", "provider": "alibaba", "model": "qwen3.6-35b-a3b-uncensored", "displayName": "Qwen3.6 35B A3B Uncensored TEE", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/qwen3.6-35b-a3b-uncensored" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/qwen3.6-35b-a3b-uncensored", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 35B A3B Uncensored TEE" ], "releaseDate": "2026-05-23", "lastUpdated": "2026-05-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/qwen3.6-35b-a3b-uncensored", "modelKey": "TEE/qwen3.6-35b-a3b-uncensored", "displayName": "Qwen3.6 35B A3B Uncensored TEE", "metadata": { "lastUpdated": "2026-05-23", "openWeights": false, "releaseDate": "2026-05-23" } } ] }, { "id": "alibaba/qwen3.6-35b-a3b:thinking", "provider": "alibaba", "model": "qwen3.6-35b-a3b:thinking", "displayName": "Qwen3.6 35B A3B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen/Qwen3.6-35B-A3B:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/Qwen3.6-35B-A3B:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.112, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 35B A3B Thinking" ], "releaseDate": "2026-04-19", "lastUpdated": "2026-04-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/Qwen3.6-35B-A3B:thinking", "modelKey": "qwen/Qwen3.6-35B-A3B:thinking", "displayName": "Qwen3.6 35B A3B Thinking", "metadata": { "lastUpdated": "2026-04-19", "openWeights": false, "releaseDate": "2026-04-19" } } ] }, { "id": "alibaba/qwen3.6-35b-fast", "provider": "alibaba", "model": "qwen3.6-35b-fast", "displayName": "Qwen3.6 35B Fast", "family": "qwen3.6", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/qwen3.6-35b-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131056, "outputTokens": 131056, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "qwen3.6-35b-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 35B Fast" ], "families": [ "qwen3.6" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "qwen3.6-35b-fast", "modelKey": "qwen3.6-35b-fast", "displayName": "Qwen3.6 35B Fast", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01" } } ] }, { "id": "alibaba/qwen3.6-flash", "provider": "alibaba", "model": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "sources": [ "models.dev", "openrouter" ], "providers": [ "aihubmix", "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "kilo", "nano-gpt", "openrouter" ], "aliases": [ "aihubmix/qwen3.6-flash", "alibaba-cn/qwen3.6-flash", "alibaba-coding-plan-cn/qwen3.6-flash", "alibaba-coding-plan/qwen3.6-flash", "alibaba-token-plan-cn/qwen3.6-flash", "alibaba-token-plan/qwen3.6-flash", "alibaba/qwen3.6-flash", "kilo/qwen/qwen3.6-flash", "nano-gpt/alibaba/qwen3.6-flash", "openrouter/qwen/qwen3.6-flash" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0169, "cacheWrite": 0.21125, "input": 0.17, "output": 1.01 }, "tiered": { "contextOver200K": { "input": 0.68, "output": 4.06, "cache_read": 0.0676, "cache_write": 0.845 }, "tiers": [ { "input": 0.68, "output": 4.06, "cache_read": 0.0676, "cache_write": 0.845, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.3125, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "alibaba/qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.19, "output": 1.16 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.6-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 0.234375, "input": 0.1875, "output": 1.125 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 Flash", "Qwen: Qwen3.6 Flash" ], "families": [ "qwen3.6" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-flash", "modelKey": "qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.6-flash", "modelKey": "qwen/qwen3.6-flash", "displayName": "Qwen: Qwen3.6 Flash", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "alibaba/qwen3.6-flash", "modelKey": "alibaba/qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.6-flash", "modelKey": "qwen/qwen3.6-flash", "displayName": "Qwen3.6 Flash", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.6-flash", "displayName": "Qwen: Qwen3.6 Flash", "metadata": { "canonicalSlug": "qwen/qwen3.6-flash", "createdAt": "2026-04-27T03:42:42.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.6-flash/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.6-max-preview", "provider": "alibaba", "model": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "aihubmix", "alibaba", "alibaba-cn", "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "aihubmix/qwen3.6-max-preview", "alibaba-cn/qwen3.6-max-preview", "alibaba/qwen3.6-max-preview", "kilo/qwen/qwen3.6-max-preview", "llmgateway/qwen3.6-max-preview", "nano-gpt/qwen3.6-max-preview", "openrouter/qwen/qwen3.6-max-preview" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1268, "cacheWrite": 1.585, "input": 1.27, "output": 7.61 }, "tiered": { "tiers": [ { "input": 2.11, "output": 12.67, "cache_read": 0.2112, "cache_write": 2.64, "tier": { "size": 128000 } } ] } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.132, "input": 1.32, "output": 7.9 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "cacheWrite": 1.625, "input": 1.3, "output": 7.8 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 1.3, "input": 1.04, "output": 6.24 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "cacheWrite": 1.625, "input": 1.3, "output": 7.8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.3, "output": 7.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.6-max-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 1.3, "input": 1.04, "output": 6.24 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.6-max-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 1.3, "input": 1.04, "output": 6.24 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 Max Preview", "Qwen: Qwen3.6 Max Preview" ], "families": [ "qwen", "qwen3.6" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-05-09", "lastUpdated": "2026-05-09", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "qwen3.6-max-preview", "modelKey": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen3.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-09", "openWeights": false, "releaseDate": "2026-05-09", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-max-preview", "modelKey": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-max-preview", "modelKey": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.6-max-preview", "modelKey": "qwen/qwen3.6-max-preview", "displayName": "Qwen: Qwen3.6 Max Preview", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3.6-max-preview", "modelKey": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.6-max-preview", "modelKey": "qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen3.6", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.6-max-preview", "modelKey": "qwen/qwen3.6-max-preview", "displayName": "Qwen3.6 Max Preview", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 131072 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.6-max-preview", "displayName": "Qwen: Qwen3.6 Max Preview", "metadata": { "canonicalSlug": "qwen/qwen3.6-max-preview-20260420", "createdAt": "2026-04-27T03:24:02.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.6-plus", "provider": "alibaba", "model": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "kilo", "llmgateway", "opencode", "opencode-go", "openrouter", "orcarouter", "togetherai", "vercel", "zenmux" ], "aliases": [ "aihubmix/qwen3.6-plus", "alibaba-cn/qwen3.6-plus", "alibaba-coding-plan-cn/qwen3.6-plus", "alibaba-coding-plan/qwen3.6-plus", "alibaba-token-plan-cn/qwen3.6-plus", "alibaba-token-plan/qwen3.6-plus", "alibaba/qwen3.6-plus", "kilo/qwen/qwen3.6-plus", "llmgateway/qwen3.6-plus", "opencode-go/qwen3.6-plus", "opencode/qwen3.6-plus", "openrouter/qwen/qwen3.6-plus", "orcarouter/qwen/qwen3.6-plus", "togetherai/Qwen/Qwen3.6-Plus", "vercel/alibaba/qwen3.6-plus", "zenmux/qwen/qwen3.6-plus" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 65536, "outputTokens": 500000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0282, "cacheWrite": 0.3525, "input": 0.28, "output": 1.69 }, "tiered": { "contextOver200K": { "input": 1.13, "output": 6.77, "cache_read": 0.1128, "cache_write": 1.41 }, "tiers": [ { "input": 1.13, "output": 6.77, "cache_read": 0.1128, "cache_write": 1.41, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0325, "cacheWrite": 0.40625, "input": 0.325, "output": 1.95 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "opencode-go", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.40625, "input": 0.325, "output": 1.95 } }, { "source": "models.dev", "provider": "orcarouter", "model": "qwen/qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3.6-Plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 0.625, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3.6-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/qwen/qwen3.6-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.325, "output": 1.95 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.6-plus", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 0.40625, "input": 0.325, "output": 1.95 } } ] }, "metadata": { "displayNames": [ "Qwen 3.6 Plus", "Qwen3.6 Plus", "Qwen3.6-Plus", "Qwen: Qwen3.6 Plus" ], "families": [ "qwen", "qwen3.6" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-05-09", "lastUpdated": "2026-05-09", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen3.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-09", "openWeights": false, "releaseDate": "2026-05-09", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.6-plus", "modelKey": "qwen/qwen3.6-plus", "displayName": "Qwen: Qwen3.6 Plus", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen3.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.6-plus", "modelKey": "qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen3.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.6-plus", "modelKey": "qwen/qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 81920 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "qwen/qwen3.6-plus", "modelKey": "qwen/qwen3.6-plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3.6-Plus", "modelKey": "Qwen/Qwen3.6-Plus", "displayName": "Qwen3.6 Plus", "family": "qwen", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-04-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.6-plus", "modelKey": "alibaba/qwen3.6-plus", "displayName": "Qwen 3.6 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3.6-plus", "modelKey": "qwen/qwen3.6-plus", "displayName": "Qwen3.6-Plus", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/qwen/qwen3.6-plus", "mode": "chat", "metadata": { "source": "https://openrouter.ai/qwen/qwen3.6-plus" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.6-plus", "displayName": "Qwen: Qwen3.6 Plus", "metadata": { "canonicalSlug": "qwen/qwen3.6-plus-04-02", "createdAt": "2026-04-02T12:39:17.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.6-plus-free", "provider": "alibaba", "model": "qwen3.6-plus-free", "displayName": "Qwen3.6 Plus Free", "family": "qwen-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/qwen3.6-plus-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "qwen3.6-plus-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 Plus Free" ], "families": [ "qwen-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.6-plus-free", "modelKey": "qwen3.6-plus-free", "displayName": "Qwen3.6 Plus Free", "family": "qwen-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 81920 } ] } } ] }, { "id": "alibaba/qwen3.7-max", "provider": "alibaba", "model": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "kilo", "llmgateway", "nano-gpt", "novita-ai", "opencode-go", "openrouter", "togetherai", "vercel", "wafer.ai", "zenmux" ], "aliases": [ "alibaba-cn/qwen3.7-max", "alibaba-coding-plan-cn/qwen3.7-max", "alibaba-coding-plan/qwen3.7-max", "alibaba-token-plan-cn/qwen3.7-max", "alibaba-token-plan/qwen3.7-max", "alibaba/qwen3.7-max", "kilo/qwen/qwen3.7-max", "llmgateway/qwen3.7-max", "nano-gpt/qwen3.7-max", "novita-ai/qwen/qwen3.7-max", "opencode-go/qwen3.7-max", "openrouter/qwen/qwen3.7-max", "togetherai/Qwen/Qwen3.7-Max", "vercel/alibaba/qwen3.7-max", "wafer.ai/qwen3.7-max", "zenmux/qwen/qwen3.7-max" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 500000, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "kilo", "model": "qwen/qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1625, "cacheWrite": 2.03125, "input": 1.625, "output": 4.875 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "qwen/qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 1.5625, "input": 1.25, "output": 3.75 } }, { "source": "models.dev", "provider": "opencode-go", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 1.5625, "input": 1.25, "output": 3.75 } }, { "source": "models.dev", "provider": "togetherai", "model": "Qwen/Qwen3.7-Max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 3.75 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 1.5625, "input": 1.25, "output": 3.75 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 0, "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3.7-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 3.125, "input": 2.5, "output": 7.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.7-max", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 1.5625, "input": 1.25, "output": 3.75 } } ] }, "metadata": { "displayNames": [ "Qwen 3.7 Max", "Qwen3.7 Max", "Qwen3.7-Max", "Qwen: Qwen3.7 Max" ], "families": [ "qwen", "qwen3.7-max" ], "releaseDate": "2026-05-21", "lastUpdated": "2026-05-21", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "qwen/qwen3.7-max", "modelKey": "qwen/qwen3.7-max", "displayName": "Qwen: Qwen3.7 Max", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "qwen/qwen3.7-max", "modelKey": "qwen/qwen3.7-max", "displayName": "Qwen3.7-Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen3.7-max", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.7-max", "modelKey": "qwen/qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "Qwen/Qwen3.7-Max", "modelKey": "Qwen/Qwen3.7-Max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-06-15", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.7-max", "modelKey": "alibaba/qwen3.7-max", "displayName": "Qwen 3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "qwen3.7-max", "modelKey": "qwen3.7-max", "displayName": "Qwen3.7-Max", "family": "qwen3.7-max", "metadata": { "lastUpdated": "2026-05-30", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3.7-max", "modelKey": "qwen/qwen3.7-max", "displayName": "Qwen3.7 Max", "family": "qwen", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.7-max", "displayName": "Qwen: Qwen3.7 Max", "metadata": { "canonicalSlug": "qwen/qwen3.7-max-20260520", "createdAt": "2026-05-21T15:21:01.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.7-max-20260520/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.7-max:thinking", "provider": "alibaba", "model": "qwen3.7-max:thinking", "displayName": "Qwen3.7 Max Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.7-max:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.7-max:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Qwen3.7 Max Thinking" ], "releaseDate": "2026-05-21", "lastUpdated": "2026-05-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.7-max:thinking", "modelKey": "qwen3.7-max:thinking", "displayName": "Qwen3.7 Max Thinking", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21" } } ] }, { "id": "alibaba/qwen3.7-plus", "provider": "alibaba", "model": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "llmgateway", "nano-gpt", "opencode-go", "openrouter", "vercel", "zenmux" ], "aliases": [ "alibaba-cn/qwen3.7-plus", "alibaba-coding-plan-cn/qwen3.7-plus", "alibaba-coding-plan/qwen3.7-plus", "alibaba-token-plan-cn/qwen3.7-plus", "alibaba-token-plan/qwen3.7-plus", "alibaba/qwen3.7-plus", "llmgateway/qwen3.7-plus", "nano-gpt/qwen3.7-plus", "opencode-go/qwen3.7-plus", "openrouter/qwen/qwen3.7-plus", "vercel/alibaba/qwen3.7-plus", "zenmux/qwen/qwen3.7-plus" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 1000000, "inputTokens": 991808, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 128000 } } ] } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.2, "cache_write": 2.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 0.5, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "opencode-go", "model": "qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "cacheWrite": 0.5, "input": 0.4, "output": 1.6 }, "tiered": { "contextOver200K": { "input": 1.2, "output": 4.8, "cache_read": 0.12, "cache_write": 1.5 }, "tiers": [ { "input": 1.2, "output": 4.8, "cache_read": 0.12, "cache_write": 1.5, "tier": { "size": 256000 } } ] } }, { "source": "models.dev", "provider": "openrouter", "model": "qwen/qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.064, "cacheWrite": 0.4, "input": 0.32, "output": 1.28 } }, { "source": "models.dev", "provider": "vercel", "model": "alibaba/qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 0.5, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "zenmux", "model": "qwen/qwen3.7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 0.5, "input": 0.4, "output": 1.6 }, "tiered": { "contextOver200K": { "input": 1.2, "output": 4.8, "cache_read": 0.24, "cache_write": 1.5 }, "tiers": [ { "input": 1.2, "output": 4.8, "cache_read": 0.24, "cache_write": 1.5, "tier": { "size": 256000 } } ] } }, { "source": "openrouter", "provider": "openrouter", "model": "qwen/qwen3.7-plus", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.064, "cacheWrite": 0.4, "input": 0.32, "output": 1.28 } } ] }, "metadata": { "displayNames": [ "Qwen 3.7 Plus", "Qwen3.7 Plus", "Qwen: Qwen3.7 Plus" ], "families": [ "qwen", "qwen3.7-plus" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-06-02", "lastUpdated": "2026-06-02", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-04", "openWeights": false, "releaseDate": "2026-06-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "metadata": { "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "qwen3.7-plus", "modelKey": "qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen3.7-plus", "metadata": { "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "qwen/qwen3.7-plus", "modelKey": "qwen/qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/qwen3.7-plus", "modelKey": "alibaba/qwen3.7-plus", "displayName": "Qwen 3.7 Plus", "family": "qwen3.7-plus", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1, "max": 262144 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "qwen/qwen3.7-plus", "modelKey": "qwen/qwen3.7-plus", "displayName": "Qwen3.7 Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "qwen/qwen3.7-plus", "displayName": "Qwen: Qwen3.7 Plus", "metadata": { "canonicalSlug": "qwen/qwen3.7-plus-20260602", "createdAt": "2026-06-03T13:03:03.000Z", "links": { "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "alibaba/qwen3.7-plus:thinking", "provider": "alibaba", "model": "qwen3.7-plus:thinking", "displayName": "Qwen3.7 Plus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen3.7-plus:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 983616, "inputTokens": 983616, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen3.7-plus:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "Qwen3.7 Plus Thinking" ], "releaseDate": "2026-06-01", "lastUpdated": "2026-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen3.7-plus:thinking", "modelKey": "qwen3.7-plus:thinking", "displayName": "Qwen3.7 Plus Thinking", "metadata": { "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-06-01" } } ] }, { "id": "alibaba/qwen35-397b-a17b", "provider": "alibaba", "model": "qwen35-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/qwen35-397b-a17b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "qwen35-397b-a17b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "Qwen3.5 397B-A17B" ], "families": [ "qwen" ], "releaseDate": "2026-02-15", "lastUpdated": "2026-02-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwen35-397b-a17b", "modelKey": "qwen35-397b-a17b", "displayName": "Qwen3.5 397B-A17B", "family": "qwen", "metadata": { "lastUpdated": "2026-02-15", "openWeights": true, "releaseDate": "2026-02-15" } } ] }, { "id": "alibaba/qwen3guard-gen-0.6b", "provider": "alibaba", "model": "qwen3guard-gen-0.6b", "displayName": "Qwen3Guard Gen 0.6B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "chutes", "ovhcloud" ], "aliases": [ "chutes/Qwen/Qwen3Guard-Gen-0.6B", "ovhcloud/qwen3guard-gen-0.6b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "Qwen/Qwen3Guard-Gen-0.6B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.01, "output": 0.0109 } } ] }, "metadata": { "displayNames": [ "Qwen3Guard Gen 0.6B", "Qwen3Guard-Gen-0.6B" ], "families": [ "qwen" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "Qwen/Qwen3Guard-Gen-0.6B", "modelKey": "Qwen/Qwen3Guard-Gen-0.6B", "displayName": "Qwen3Guard Gen 0.6B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3guard-gen-0.6b", "modelKey": "qwen3guard-gen-0.6b", "displayName": "Qwen3Guard-Gen-0.6B", "metadata": { "lastUpdated": "2026-01-22", "openWeights": true, "releaseDate": "2026-01-22" } } ] }, { "id": "alibaba/qwen3guard-gen-8b", "provider": "alibaba", "model": "qwen3guard-gen-8b", "displayName": "Qwen3Guard-Gen-8B", "sources": [ "models.dev" ], "providers": [ "ovhcloud" ], "aliases": [ "ovhcloud/qwen3guard-gen-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Qwen3Guard-Gen-8B" ], "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "qwen3guard-gen-8b", "modelKey": "qwen3guard-gen-8b", "displayName": "Qwen3Guard-Gen-8B", "metadata": { "lastUpdated": "2026-01-22", "openWeights": true, "releaseDate": "2026-01-22" } } ] }, { "id": "alibaba/qwen3p7-plus", "provider": "alibaba", "model": "qwen3p7-plus", "displayName": "Qwen 3.7 Plus", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/qwen3p7-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/qwen3p7-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "Qwen 3.7 Plus" ], "families": [ "qwen" ], "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/qwen3p7-plus", "modelKey": "accounts/fireworks/models/qwen3p7-plus", "displayName": "Qwen 3.7 Plus", "family": "qwen", "metadata": { "lastUpdated": "2026-06-12", "openWeights": false, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1 } ] } } ] }, { "id": "alibaba/qwenlong-l1-32b", "provider": "alibaba", "model": "qwenlong-l1-32b", "displayName": "QwenLong L1 32B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Tongyi-Zhiwen/QwenLong-L1-32B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Tongyi-Zhiwen/QwenLong-L1-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13999999999999999, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "QwenLong L1 32B" ], "families": [ "qwen" ], "releaseDate": "2025-01-25", "lastUpdated": "2025-01-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Tongyi-Zhiwen/QwenLong-L1-32B", "modelKey": "Tongyi-Zhiwen/QwenLong-L1-32B", "displayName": "QwenLong L1 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } } ] }, { "id": "alibaba/qwq-32b", "provider": "alibaba", "model": "qwq-32b", "displayName": "QwQ 32B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "alibaba-cn", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "fireworks_ai", "hyperbolic", "nano-gpt", "nebius", "nscale", "sambanova", "siliconflow", "siliconflow-cn" ], "aliases": [ "abacus/Qwen/QwQ-32B", "alibaba-cn/qwq-32b", "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b", "cloudflare-workers-ai/@cf/qwen/qwq-32b", "deepinfra/Qwen/QwQ-32B", "fireworks_ai/accounts/fireworks/models/qwq-32b", "hyperbolic/Qwen/QwQ-32B", "nano-gpt/qwq-32b", "nebius/Qwen/QwQ-32B", "nscale/Qwen/QwQ-32B", "sambanova/QwQ-32B", "siliconflow-cn/Qwen/QwQ-32B", "siliconflow/Qwen/QwQ-32B" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "Qwen/QwQ-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "qwq-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/qwen/qwq-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 1 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/qwen/qwq-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "qwq-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25599999, "output": 0.30499999 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Qwen/QwQ-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.58 } }, { "source": "models.dev", "provider": "siliconflow", "model": "Qwen/QwQ-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.58 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Qwen/QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwq-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/Qwen/QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/Qwen/QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.45 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/Qwen/QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.2 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1 } } ] }, "metadata": { "displayNames": [ "QwQ 32B", "Qwen/QwQ-32B", "Qwen: QwQ 32B", "Qwq 32B" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-11-28", "lastUpdated": "2024-11-28", "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "Qwen/QwQ-32B", "modelKey": "Qwen/QwQ-32B", "displayName": "QwQ 32B", "family": "qwen", "metadata": { "lastUpdated": "2024-11-28", "openWeights": true, "releaseDate": "2024-11-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwq-32b", "modelKey": "qwq-32b", "displayName": "QwQ 32B", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-12", "openWeights": true, "releaseDate": "2024-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/qwen/qwq-32b", "modelKey": "workers-ai/@cf/qwen/qwq-32b", "displayName": "QwQ 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/qwen/qwq-32b", "modelKey": "@cf/qwen/qwq-32b", "displayName": "Qwq 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-03-05", "openWeights": true, "releaseDate": "2025-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwq-32b", "modelKey": "qwq-32b", "displayName": "Qwen: QwQ 32B", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/QwQ-32B", "modelKey": "Qwen/QwQ-32B", "displayName": "Qwen/QwQ-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-03-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Qwen/QwQ-32B", "modelKey": "Qwen/QwQ-32B", "displayName": "Qwen/QwQ-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-03-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Qwen/QwQ-32B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/qwq-32b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/Qwen/QwQ-32B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/Qwen/QwQ-32B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/Qwen/QwQ-32B", "mode": "chat", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/QwQ-32B", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "alibaba/qwq-32b-preview", "provider": "alibaba", "model": "qwq-32b-preview", "displayName": "Qwen QwQ 32B Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qwen/qwq-32b-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qwen/qwq-32b-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Qwen QwQ 32B Preview" ], "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qwen/qwq-32b-preview", "modelKey": "qwen/qwq-32b-preview", "displayName": "Qwen QwQ 32B Preview", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } } ] }, { "id": "alibaba/qwq-plus", "provider": "alibaba", "model": "qwq-plus", "displayName": "QwQ Plus", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba", "alibaba-cn", "dashscope", "llmgateway" ], "aliases": [ "alibaba-cn/qwq-plus", "alibaba/qwq-plus", "dashscope/qwq-plus", "llmgateway/qwq-plus" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 98304, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "qwq-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.23, "output": 0.574 } }, { "source": "models.dev", "provider": "alibaba", "model": "qwq-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "qwq-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "litellm", "provider": "dashscope", "model": "dashscope/qwq-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "QwQ Plus" ], "families": [ "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-03-05", "lastUpdated": "2025-03-05", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwq-plus", "modelKey": "qwq-plus", "displayName": "QwQ Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-05", "openWeights": false, "releaseDate": "2025-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba", "providerName": "Alibaba", "providerApi": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "qwq-plus", "modelKey": "qwq-plus", "displayName": "QwQ Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-05", "openWeights": false, "releaseDate": "2025-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "qwq-plus", "modelKey": "qwq-plus", "displayName": "QwQ Plus", "family": "qwen", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-05", "openWeights": false, "releaseDate": "2025-03-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dashscope", "model": "dashscope/qwq-plus", "mode": "chat", "metadata": { "source": "https://www.alibabacloud.com/help/en/model-studio/models" } } ] }, { "id": "alibaba/wan-v2-6", "provider": "alibaba", "model": "wan-v2-6", "displayName": "Wan 2.6", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/wanx/wan-v2-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan 2.6" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "wanx/wan-v2-6", "modelKey": "wanx/wan-v2-6", "displayName": "Wan 2.6", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } } ] }, { "id": "alibaba/wan-v2.5-t2v-preview", "provider": "alibaba", "model": "wan-v2.5-t2v-preview", "displayName": "Wan v2.5 Text-to-Video Preview", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.5-t2v-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.5 Text-to-Video Preview" ], "families": [ "o" ], "releaseDate": "2025-09-24", "lastUpdated": "2025-09-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.5-t2v-preview", "modelKey": "alibaba/wan-v2.5-t2v-preview", "displayName": "Wan v2.5 Text-to-Video Preview", "family": "o", "metadata": { "lastUpdated": "2025-09-24", "openWeights": false, "releaseDate": "2025-09-24" } } ] }, { "id": "alibaba/wan-v2.6-i2v", "provider": "alibaba", "model": "wan-v2.6-i2v", "displayName": "Wan v2.6 Image-to-Video", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.6-i2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.6 Image-to-Video" ], "families": [ "o" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.6-i2v", "modelKey": "alibaba/wan-v2.6-i2v", "displayName": "Wan v2.6 Image-to-Video", "family": "o", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "alibaba/wan-v2.6-i2v-flash", "provider": "alibaba", "model": "wan-v2.6-i2v-flash", "displayName": "Wan v2.6 Image-to-Video Flash", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.6-i2v-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.6 Image-to-Video Flash" ], "families": [ "o" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.6-i2v-flash", "modelKey": "alibaba/wan-v2.6-i2v-flash", "displayName": "Wan v2.6 Image-to-Video Flash", "family": "o", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "alibaba/wan-v2.6-r2v", "provider": "alibaba", "model": "wan-v2.6-r2v", "displayName": "Wan v2.6 Reference-to-Video", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.6-r2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.6 Reference-to-Video" ], "families": [ "o" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.6-r2v", "modelKey": "alibaba/wan-v2.6-r2v", "displayName": "Wan v2.6 Reference-to-Video", "family": "o", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "alibaba/wan-v2.6-r2v-flash", "provider": "alibaba", "model": "wan-v2.6-r2v-flash", "displayName": "Wan v2.6 Reference-to-Video Flash", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.6-r2v-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.6 Reference-to-Video Flash" ], "families": [ "o" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.6-r2v-flash", "modelKey": "alibaba/wan-v2.6-r2v-flash", "displayName": "Wan v2.6 Reference-to-Video Flash", "family": "o", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "alibaba/wan-v2.6-t2v", "provider": "alibaba", "model": "wan-v2.6-t2v", "displayName": "Wan v2.6 Text-to-Video", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/alibaba/wan-v2.6-t2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Wan v2.6 Text-to-Video" ], "families": [ "o" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "alibaba/wan-v2.6-t2v", "modelKey": "alibaba/wan-v2.6-t2v", "displayName": "Wan v2.6 Text-to-Video", "family": "o", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "amazon-bedrock/amazon.nova-2-lite-v1:0", "provider": "amazon-bedrock", "model": "amazon.nova-2-lite-v1:0", "displayName": "Nova 2 Lite", "family": "nova", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "amazon.nova-2-lite-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 2.75 } } ] }, "metadata": { "displayNames": [ "Nova 2 Lite" ], "families": [ "nova" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "amazon.nova-2-lite-v1:0", "modelKey": "amazon.nova-2-lite-v1:0", "displayName": "Nova 2 Lite", "family": "nova", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon-bedrock/amazon.nova-lite-v1:0", "provider": "amazon-bedrock", "model": "amazon.nova-lite-v1:0", "displayName": "Nova Lite", "family": "nova-lite", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/amazon.nova-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "amazon.nova-lite-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Nova Lite" ], "families": [ "nova-lite" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "amazon.nova-lite-v1:0", "modelKey": "amazon.nova-lite-v1:0", "displayName": "Nova Lite", "family": "nova-lite", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } } ] }, { "id": "amazon-bedrock/amazon.nova-micro-v1:0", "provider": "amazon-bedrock", "model": "amazon.nova-micro-v1:0", "displayName": "Nova Micro", "family": "nova-micro", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/amazon.nova-micro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "amazon.nova-micro-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.00875, "input": 0.035, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Nova Micro" ], "families": [ "nova-micro" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "amazon.nova-micro-v1:0", "modelKey": "amazon.nova-micro-v1:0", "displayName": "Nova Micro", "family": "nova-micro", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } } ] }, { "id": "amazon-bedrock/amazon.nova-pro-v1:0", "provider": "amazon-bedrock", "model": "amazon.nova-pro-v1:0", "displayName": "Nova Pro", "family": "nova-pro", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "amazon.nova-pro-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.8, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "Nova Pro" ], "families": [ "nova-pro" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "amazon.nova-pro-v1:0", "modelKey": "amazon.nova-pro-v1:0", "displayName": "Nova Pro", "family": "nova-pro", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } } ] }, { "id": "amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon-bedrock", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "modelKey": "anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "Claude Opus 4.1", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.1" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "modelKey": "anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-opus-4-5-20251101-v1:0", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "modelKey": "anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-opus-4-6-v1", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-6-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-opus-4-6-v1", "modelKey": "anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-opus-4-7", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-opus-4-7", "modelKey": "anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-opus-4-8", "modelKey": "anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "anthropic.claude-sonnet-4-6", "modelKey": "anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon-bedrock", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (AU)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 (AU)" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "modelKey": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (AU)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/au.anthropic.claude-opus-4-6-v1", "provider": "amazon-bedrock", "model": "au.anthropic.claude-opus-4-6-v1", "displayName": "AU Anthropic Claude Opus 4.6", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/au.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "au.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.65, "cacheWrite": 20.625, "input": 16.5, "output": 82.5 } } ] }, "metadata": { "displayNames": [ "AU Anthropic Claude Opus 4.6" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "au.anthropic.claude-opus-4-6-v1", "modelKey": "au.anthropic.claude-opus-4-6-v1", "displayName": "AU Anthropic Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/au.anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "au.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (AU)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/au.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "au.anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 (AU)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "au.anthropic.claude-opus-4-8", "modelKey": "au.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (AU)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (AU)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (AU)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (AU)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/au.anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "au.anthropic.claude-sonnet-4-6", "displayName": "AU Anthropic Claude Sonnet 4.6", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/au.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "au.anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 } } ] }, "metadata": { "displayNames": [ "AU Anthropic Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08", "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "au.anthropic.claude-sonnet-4-6", "modelKey": "au.anthropic.claude-sonnet-4-6", "displayName": "AU Anthropic Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/deepseek.r1-v1:0", "provider": "amazon-bedrock", "model": "deepseek.r1-v1:0", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/deepseek.r1-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "deepseek.r1-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "displayNames": [ "DeepSeek-R1" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "lastUpdated": "2025-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "deepseek.r1-v1:0", "modelKey": "deepseek.r1-v1:0", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": false, "releaseDate": "2025-01-20" } } ] }, { "id": "amazon-bedrock/deepseek.v3-v1:0", "provider": "amazon-bedrock", "model": "deepseek.v3-v1:0", "displayName": "DeepSeek-V3.1", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/deepseek.v3-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 81920, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "deepseek.v3-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 1.68 } } ] }, "metadata": { "displayNames": [ "DeepSeek-V3.1" ], "families": [ "deepseek" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "deepseek.v3-v1:0", "modelKey": "deepseek.v3-v1:0", "displayName": "DeepSeek-V3.1", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-09-18", "openWeights": true, "releaseDate": "2025-09-18" } } ] }, { "id": "amazon-bedrock/deepseek.v3.2", "provider": "amazon-bedrock", "model": "deepseek.v3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/deepseek.v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 81920, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "deepseek.v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.62, "output": 1.85 } } ] }, "metadata": { "displayNames": [ "DeepSeek-V3.2" ], "families": [ "deepseek" ], "knowledgeCutoff": "2024-07", "releaseDate": "2026-02-06", "lastUpdated": "2026-02-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "deepseek.v3.2", "modelKey": "deepseek.v3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2026-02-06", "openWeights": true, "releaseDate": "2026-02-06" } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-fable-5", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (EU)", "family": "claude-fable", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.1, "cacheWrite": 13.75, "input": 11, "output": 55 } } ] }, "metadata": { "displayNames": [ "Claude Fable 5 (EU)" ], "families": [ "claude-fable" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-fable-5", "modelKey": "eu.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (EU)", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (EU)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 (EU)" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "modelKey": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (EU)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (EU)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5 (EU)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "modelKey": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (EU)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-opus-4-6-v1", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (EU)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6 (EU)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-opus-4-6-v1", "modelKey": "eu.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (EU)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-opus-4-7", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (EU)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 (EU)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-opus-4-7", "modelKey": "eu.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (EU)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (EU)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 (EU)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-opus-4-8", "modelKey": "eu.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (EU)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (EU)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (EU)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (EU)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/eu.anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (EU)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/eu.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "eu.anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 (EU)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "eu.anthropic.claude-sonnet-4-6", "modelKey": "eu.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (EU)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-fable-5", "provider": "amazon-bedrock", "model": "global.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (Global)", "family": "claude-fable", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } } ] }, "metadata": { "displayNames": [ "Claude Fable 5 (Global)" ], "families": [ "claude-fable" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-fable-5", "modelKey": "global.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (Global)", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon-bedrock", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (Global)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 (Global)" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "modelKey": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (Global)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (Global)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5 (Global)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "modelKey": "global.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (Global)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-opus-4-6-v1", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (Global)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6 (Global)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-opus-4-6-v1", "modelKey": "global.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (Global)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-opus-4-7", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (Global)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 (Global)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-opus-4-7", "modelKey": "global.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (Global)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (Global)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 (Global)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-opus-4-8", "modelKey": "global.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (Global)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (Global)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (Global)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (Global)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/global.anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "global.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (Global)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/global.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "global.anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 (Global)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "global.anthropic.claude-sonnet-4-6", "modelKey": "global.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (Global)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/google.gemma-3-12b-it", "provider": "amazon-bedrock", "model": "google.gemma-3-12b-it", "displayName": "Google Gemma 3 12B", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/google.gemma-3-12b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "google.gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049999999999999996, "output": 0.09999999999999999 } } ] }, "metadata": { "displayNames": [ "Google Gemma 3 12B" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-12", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "google.gemma-3-12b-it", "modelKey": "google.gemma-3-12b-it", "displayName": "Google Gemma 3 12B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "amazon-bedrock/google.gemma-3-27b-it", "provider": "amazon-bedrock", "model": "google.gemma-3-27b-it", "displayName": "Google Gemma 3 27B Instruct", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/google.gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "google.gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Google Gemma 3 27B Instruct" ], "families": [ "gemma" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-27", "lastUpdated": "2025-07-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "google.gemma-3-27b-it", "modelKey": "google.gemma-3-27b-it", "displayName": "Google Gemma 3 27B Instruct", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-27", "openWeights": true, "releaseDate": "2025-07-27" } } ] }, { "id": "amazon-bedrock/google.gemma-3-4b-it", "provider": "amazon-bedrock", "model": "google.gemma-3-4b-it", "displayName": "Gemma 3 4B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/google.gemma-3-4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "google.gemma-3-4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.08 } } ] }, "metadata": { "displayNames": [ "Gemma 3 4B IT" ], "families": [ "gemma" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "google.gemma-3-4b-it", "modelKey": "google.gemma-3-4b-it", "displayName": "Gemma 3 4B IT", "family": "gemma", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "amazon-bedrock/jp.anthropic.claude-opus-4-7", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (JP)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/jp.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 (JP)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "jp.anthropic.claude-opus-4-7", "modelKey": "jp.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (JP)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/jp.anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (JP)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/jp.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 (JP)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "jp.anthropic.claude-opus-4-8", "modelKey": "jp.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (JP)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (JP)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (JP)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (JP)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/jp.anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (JP)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/jp.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "jp.anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 (JP)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "jp.anthropic.claude-sonnet-4-6", "modelKey": "jp.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (JP)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/meta.llama3-1-70b-instruct-v1:0", "provider": "amazon-bedrock", "model": "meta.llama3-1-70b-instruct-v1:0", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/meta.llama3-1-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "meta.llama3-1-70b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "meta.llama3-1-70b-instruct-v1:0", "modelKey": "meta.llama3-1-70b-instruct-v1:0", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "amazon-bedrock/meta.llama3-1-8b-instruct-v1:0", "provider": "amazon-bedrock", "model": "meta.llama3-1-8b-instruct-v1:0", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/meta.llama3-1-8b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "meta.llama3-1-8b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.22 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "meta.llama3-1-8b-instruct-v1:0", "modelKey": "meta.llama3-1-8b-instruct-v1:0", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "amazon-bedrock/meta.llama3-3-70b-instruct-v1:0", "provider": "amazon-bedrock", "model": "meta.llama3-3-70b-instruct-v1:0", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/meta.llama3-3-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "meta.llama3-3-70b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "meta.llama3-3-70b-instruct-v1:0", "modelKey": "meta.llama3-3-70b-instruct-v1:0", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } } ] }, { "id": "amazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0", "provider": "amazon-bedrock", "model": "meta.llama4-maverick-17b-instruct-v1:0", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "meta.llama4-maverick-17b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.97 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "meta.llama4-maverick-17b-instruct-v1:0", "modelKey": "meta.llama4-maverick-17b-instruct-v1:0", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "amazon-bedrock/meta.llama4-scout-17b-instruct-v1:0", "provider": "amazon-bedrock", "model": "meta.llama4-scout-17b-instruct-v1:0", "displayName": "Llama 4 Scout 17B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/meta.llama4-scout-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 3500000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "meta.llama4-scout-17b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.66 } } ] }, "metadata": { "displayNames": [ "Llama 4 Scout 17B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "meta.llama4-scout-17b-instruct-v1:0", "modelKey": "meta.llama4-scout-17b-instruct-v1:0", "displayName": "Llama 4 Scout 17B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "amazon-bedrock/moonshot.kimi-k2-thinking", "provider": "amazon-bedrock", "model": "moonshot.kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/moonshot.kimi-k2-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262143, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "interleaved": true, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "moonshot.kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking" ], "families": [ "kimi-thinking" ], "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "moonshot.kimi-k2-thinking", "modelKey": "moonshot.kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } } ] }, { "id": "amazon-bedrock/moonshotai.kimi-k2.5", "provider": "amazon-bedrock", "model": "moonshotai.kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/moonshotai.kimi-k2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262143, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "interleaved": true, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "moonshotai.kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5" ], "families": [ "kimi" ], "releaseDate": "2026-02-06", "lastUpdated": "2026-02-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "moonshotai.kimi-k2.5", "modelKey": "moonshotai.kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi", "metadata": { "lastUpdated": "2026-02-06", "openWeights": true, "releaseDate": "2026-02-06" } } ] }, { "id": "amazon-bedrock/nvidia.nemotron-nano-12b-v2", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-12b-v2", "displayName": "NVIDIA Nemotron Nano 12B v2 VL BF16", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/nvidia.nemotron-nano-12b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-12b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron Nano 12B v2 VL BF16" ], "families": [ "nemotron" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "nvidia.nemotron-nano-12b-v2", "modelKey": "nvidia.nemotron-nano-12b-v2", "displayName": "NVIDIA Nemotron Nano 12B v2 VL BF16", "family": "nemotron", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "amazon-bedrock/nvidia.nemotron-nano-3-30b", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-3-30b", "displayName": "NVIDIA Nemotron Nano 3 30B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/nvidia.nemotron-nano-3-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-3-30b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron Nano 3 30B" ], "families": [ "nemotron" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "nvidia.nemotron-nano-3-30b", "modelKey": "nvidia.nemotron-nano-3-30b", "displayName": "NVIDIA Nemotron Nano 3 30B", "family": "nemotron", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } } ] }, { "id": "amazon-bedrock/nvidia.nemotron-nano-9b-v2", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-9b-v2", "displayName": "NVIDIA Nemotron Nano 9B v2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/nvidia.nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "nvidia.nemotron-nano-9b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.23 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron Nano 9B v2" ], "families": [ "nemotron" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "nvidia.nemotron-nano-9b-v2", "modelKey": "nvidia.nemotron-nano-9b-v2", "displayName": "NVIDIA Nemotron Nano 9B v2", "family": "nemotron", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "amazon-bedrock/nvidia.nemotron-super-3-120b", "provider": "amazon-bedrock", "model": "nvidia.nemotron-super-3-120b", "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/nvidia.nemotron-super-3-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "nvidia.nemotron-super-3-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Super 120B A12B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "nvidia.nemotron-super-3-120b", "modelKey": "nvidia.nemotron-super-3-120b", "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "amazon-bedrock/openai.gpt-5.4", "provider": "amazon-bedrock", "model": "openai.gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-5.4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 2.75, "output": 16.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-5.4", "modelKey": "openai.gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-5.5", "provider": "amazon-bedrock", "model": "openai.gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-5.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 5.5, "output": 33 } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-5.5", "modelKey": "openai.gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-120b", "provider": "amazon-bedrock", "model": "openai.gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "gpt-oss-120b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-120b", "modelKey": "openai.gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-120b-1:0", "provider": "amazon-bedrock", "model": "openai.gpt-oss-120b-1:0", "displayName": "gpt-oss-120b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-120b-1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-120b-1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "gpt-oss-120b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-120b-1:0", "modelKey": "openai.gpt-oss-120b-1:0", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-20b", "provider": "amazon-bedrock", "model": "openai.gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "gpt-oss-20b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-20b", "modelKey": "openai.gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-20b-1:0", "provider": "amazon-bedrock", "model": "openai.gpt-oss-20b-1:0", "displayName": "gpt-oss-20b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-20b-1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-20b-1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "gpt-oss-20b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-20b-1:0", "modelKey": "openai.gpt-oss-20b-1:0", "displayName": "gpt-oss-20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-safeguard-120b", "provider": "amazon-bedrock", "model": "openai.gpt-oss-safeguard-120b", "displayName": "GPT OSS Safeguard 120B", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-safeguard-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-safeguard-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "GPT OSS Safeguard 120B" ], "families": [ "gpt-oss" ], "releaseDate": "2025-10-29", "lastUpdated": "2025-10-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-safeguard-120b", "modelKey": "openai.gpt-oss-safeguard-120b", "displayName": "GPT OSS Safeguard 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-10-29", "openWeights": false, "releaseDate": "2025-10-29" } } ] }, { "id": "amazon-bedrock/openai.gpt-oss-safeguard-20b", "provider": "amazon-bedrock", "model": "openai.gpt-oss-safeguard-20b", "displayName": "GPT OSS Safeguard 20B", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/openai.gpt-oss-safeguard-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "openai.gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "GPT OSS Safeguard 20B" ], "families": [ "gpt-oss" ], "releaseDate": "2025-10-29", "lastUpdated": "2025-10-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "openai.gpt-oss-safeguard-20b", "modelKey": "openai.gpt-oss-safeguard-20b", "displayName": "GPT OSS Safeguard 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-10-29", "openWeights": false, "releaseDate": "2025-10-29" } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-fable-5", "provider": "amazon-bedrock", "model": "us.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (US)", "family": "claude-fable", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } } ] }, "metadata": { "displayNames": [ "Claude Fable 5 (US)" ], "families": [ "claude-fable" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-fable-5", "modelKey": "us.anthropic.claude-fable-5", "displayName": "Claude Fable 5 (US)", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon-bedrock", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (US)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 (US)" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "modelKey": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "Claude Haiku 4.5 (US)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "Claude Opus 4.1 (US)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.1 (US)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "modelKey": "us.anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "Claude Opus 4.1 (US)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (US)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5 (US)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "modelKey": "us.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "Claude Opus 4.5 (US)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-opus-4-6-v1", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (US)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6 (US)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-opus-4-6-v1", "modelKey": "us.anthropic.claude-opus-4-6-v1", "displayName": "Claude Opus 4.6 (US)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-opus-4-7", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (US)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 (US)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-opus-4-7", "modelKey": "us.anthropic.claude-opus-4-7", "displayName": "Claude Opus 4.7 (US)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-opus-4-8", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (US)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 (US)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-opus-4-8", "modelKey": "us.anthropic.claude-opus-4-8", "displayName": "Claude Opus 4.8 (US)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon-bedrock", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (US)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (US)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "modelKey": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "Claude Sonnet 4.5 (US)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.anthropic.claude-sonnet-4-6", "provider": "amazon-bedrock", "model": "us.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (US)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.anthropic.claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 (US)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.anthropic.claude-sonnet-4-6", "modelKey": "us.anthropic.claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6 (US)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "amazon-bedrock/us.deepseek.r1-v1:0", "provider": "amazon-bedrock", "model": "us.deepseek.r1-v1:0", "displayName": "DeepSeek-R1 (US)", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.deepseek.r1-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.deepseek.r1-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "displayNames": [ "DeepSeek-R1 (US)" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "lastUpdated": "2025-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.deepseek.r1-v1:0", "modelKey": "us.deepseek.r1-v1:0", "displayName": "DeepSeek-R1 (US)", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } } ] }, { "id": "amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0", "provider": "amazon-bedrock", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "displayName": "Llama 4 Maverick 17B Instruct (US)", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.97 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17B Instruct (US)" ], "families": [ "llama" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "modelKey": "us.meta.llama4-maverick-17b-instruct-v1:0", "displayName": "Llama 4 Maverick 17B Instruct (US)", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0", "provider": "amazon-bedrock", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "displayName": "Llama 4 Scout 17B Instruct (US)", "family": "llama", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 3500000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.66 } } ] }, "metadata": { "displayNames": [ "Llama 4 Scout 17B Instruct (US)" ], "families": [ "llama" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "modelKey": "us.meta.llama4-scout-17b-instruct-v1:0", "displayName": "Llama 4 Scout 17B Instruct (US)", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "amazon-bedrock/writer.palmyra-x4-v1:0", "provider": "amazon-bedrock", "model": "writer.palmyra-x4-v1:0", "displayName": "Palmyra X4", "family": "palmyra", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/writer.palmyra-x4-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 122880, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "writer.palmyra-x4-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Palmyra X4" ], "families": [ "palmyra" ], "releaseDate": "2025-04-28", "lastUpdated": "2025-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "writer.palmyra-x4-v1:0", "modelKey": "writer.palmyra-x4-v1:0", "displayName": "Palmyra X4", "family": "palmyra", "metadata": { "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2025-04-28" } } ] }, { "id": "amazon-bedrock/writer.palmyra-x5-v1:0", "provider": "amazon-bedrock", "model": "writer.palmyra-x5-v1:0", "displayName": "Palmyra X5", "family": "palmyra", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/writer.palmyra-x5-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1040000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "writer.palmyra-x5-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 6 } } ] }, "metadata": { "displayNames": [ "Palmyra X5" ], "families": [ "palmyra" ], "releaseDate": "2025-04-28", "lastUpdated": "2025-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "writer.palmyra-x5-v1:0", "modelKey": "writer.palmyra-x5-v1:0", "displayName": "Palmyra X5", "family": "palmyra", "metadata": { "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2025-04-28" } } ] }, { "id": "amazon-bedrock/zai.glm-4.7", "provider": "amazon-bedrock", "model": "zai.glm-4.7", "displayName": "GLM-4.7", "family": "glm", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/zai.glm-4.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "zai.glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "GLM-4.7" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "zai.glm-4.7", "modelKey": "zai.glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } } ] }, { "id": "amazon-bedrock/zai.glm-4.7-flash", "provider": "amazon-bedrock", "model": "zai.glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/zai.glm-4.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "zai.glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM-4.7-Flash" ], "families": [ "glm-flash" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "zai.glm-4.7-flash", "modelKey": "zai.glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } } ] }, { "id": "amazon-bedrock/zai.glm-5", "provider": "amazon-bedrock", "model": "zai.glm-5", "displayName": "GLM-5", "family": "glm", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/zai.glm-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 101376, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "zai.glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM-5" ], "families": [ "glm" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "zai.glm-5", "modelKey": "zai.glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "amazon/ai21.j2-mid-v1", "provider": "amazon", "model": "ai21.j2-mid-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ai21.j2-mid-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "ai21.j2-mid-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 12.5, "output": 12.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "ai21.j2-mid-v1", "mode": "chat" } ] }, { "id": "amazon/ai21.j2-ultra-v1", "provider": "amazon", "model": "ai21.j2-ultra-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ai21.j2-ultra-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "ai21.j2-ultra-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 18.8, "output": 18.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "ai21.j2-ultra-v1", "mode": "chat" } ] }, { "id": "amazon/ai21.jamba-1-5-large-v1:0", "provider": "amazon", "model": "ai21.jamba-1-5-large-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ai21.jamba-1-5-large-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "ai21.jamba-1-5-large-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "ai21.jamba-1-5-large-v1:0", "mode": "chat" } ] }, { "id": "amazon/ai21.jamba-1-5-mini-v1:0", "provider": "amazon", "model": "ai21.jamba-1-5-mini-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ai21.jamba-1-5-mini-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "ai21.jamba-1-5-mini-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "ai21.jamba-1-5-mini-v1:0", "mode": "chat" } ] }, { "id": "amazon/ai21.jamba-instruct-v1:0", "provider": "amazon", "model": "ai21.jamba-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ai21.jamba-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 70000, "inputTokens": 70000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "ai21.jamba-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "ai21.jamba-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/amazon.nova-2-multimodal-embeddings-v1:0", "provider": "amazon", "model": "amazon.nova-2-multimodal-embeddings-v1:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.nova-2-multimodal-embeddings-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8172, "inputTokens": 8172, "maxTokens": 8172, "outputTokens": 8172, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.nova-2-multimodal-embeddings-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.135, "output": 0 }, "perImage": { "input": 0.00006 }, "perAudioSecond": { "input": 0.00014 }, "perVideoSecond": { "input": 0.0007 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.nova-2-multimodal-embeddings-v1:0", "mode": "embedding", "metadata": { "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0" } } ] }, { "id": "amazon/amazon.nova-canvas-v1:0", "provider": "amazon", "model": "amazon.nova-canvas-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0", "bedrock/amazon.nova-canvas-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2600, "inputTokens": 2600, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "imageEditing": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } }, { "source": "litellm", "provider": "bedrock", "model": "amazon.nova-canvas-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.nova-canvas-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/amazon.nova-pro-v1:0", "provider": "amazon", "model": "amazon.nova-pro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-gov-east-1/amazon.nova-pro-v1:0", "bedrock/us-gov-west-1/amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.96, "output": 3.84 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.96, "output": 3.84 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.nova-pro-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.nova-pro-v1:0", "mode": "chat" } ] }, { "id": "amazon/amazon.rerank-v1:0", "provider": "amazon", "model": "amazon.rerank-v1:0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.rerank-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxDocumentChunksPerQuery": 100, "maxQueryTokens": 32000, "maxTokens": 32000, "maxTokensPerDocumentChunk": 512, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.rerank-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.001 }, "extra": { "max_document_chunks_per_query": 100, "max_tokens_per_document_chunk": 512 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.rerank-v1:0", "mode": "rerank" } ] }, { "id": "amazon/amazon.titan-embed-image-v1", "provider": "amazon", "model": "amazon.titan-embed-image-v1", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-embed-image-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128, "inputTokens": 128, "maxTokens": 128, "outputTokens": 128, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-embed-image-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0 }, "perImage": { "input": 0.00006 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-embed-image-v1", "mode": "embedding", "metadata": { "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1" } } ] }, { "id": "amazon/amazon.titan-embed-text-v1", "provider": "amazon", "model": "amazon.titan-embed-text-v1", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-embed-text-v1", "bedrock/us-gov-east-1/amazon.titan-embed-text-v1", "bedrock/us-gov-west-1/amazon.titan-embed-text-v1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-embed-text-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-embed-text-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-embed-text-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-embed-text-v1", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-embed-text-v1", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-embed-text-v1", "mode": "embedding" } ] }, { "id": "amazon/amazon.titan-embed-text-v2:0", "provider": "amazon", "model": "amazon.titan-embed-text-v2:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-embed-text-v2:0", "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0", "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-embed-text-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-embed-text-v2:0", "mode": "embedding", "metadata": { "providerSpecificEntry": { "bedrock_invocation_schema": "titan_v2" } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0", "mode": "embedding" } ] }, { "id": "amazon/amazon.titan-image-generator-v1", "provider": "amazon", "model": "amazon.titan-image-generator-v1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-image-generator-v1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-image-generator-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0, "output": 0.008, "outputAbove512x512": 0.01, "outputAbove512x512Premium": 0.012, "outputPremium": 0.01 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-image-generator-v1", "mode": "image_generation" } ] }, { "id": "amazon/amazon.titan-image-generator-v2", "provider": "amazon", "model": "amazon.titan-image-generator-v2", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-image-generator-v2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-image-generator-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0, "output": 0.008, "outputAbove1024x1024": 0.01, "outputAbove1024x1024Premium": 0.012, "outputPremium": 0.01 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-image-generator-v2", "mode": "image_generation" } ] }, { "id": "amazon/amazon.titan-image-generator-v2:0", "provider": "amazon", "model": "amazon.titan-image-generator-v2:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-image-generator-v2:0" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-image-generator-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0, "output": 0.008, "outputAbove1024x1024": 0.01, "outputAbove1024x1024Premium": 0.012, "outputPremium": 0.01 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-image-generator-v2:0", "mode": "image_generation" } ] }, { "id": "amazon/amazon.titan-text-express-v1", "provider": "amazon", "model": "amazon.titan-text-express-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-text-express-v1", "bedrock/us-gov-east-1/amazon.titan-text-express-v1", "bedrock/us-gov-west-1/amazon.titan-text-express-v1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 42000, "inputTokens": 42000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-text-express-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.3, "output": 1.7 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-express-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.3, "output": 1.7 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-express-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.3, "output": 1.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-text-express-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-express-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-express-v1", "mode": "chat" } ] }, { "id": "amazon/amazon.titan-text-lite-v1", "provider": "amazon", "model": "amazon.titan-text-lite-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-text-lite-v1", "bedrock/us-gov-east-1/amazon.titan-text-lite-v1", "bedrock/us-gov-west-1/amazon.titan-text-lite-v1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 42000, "inputTokens": 42000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-text-lite-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.4 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-lite-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.4 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-lite-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-text-lite-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-lite-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-lite-v1", "mode": "chat" } ] }, { "id": "amazon/amazon.titan-text-premier-v1:0", "provider": "amazon", "model": "amazon.titan-text-premier-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/amazon.titan-text-premier-v1:0", "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0", "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 42000, "inputTokens": 42000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "amazon.titan-text-premier-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "amazon.titan-text-premier-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-5-haiku-20241022-v1:0", "provider": "amazon", "model": "anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-5-haiku-20241022-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-5-sonnet-20240620-v1:0", "provider": "amazon", "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0", "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "metadata": { "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-5-sonnet-20241022-v2:0", "provider": "amazon", "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-7-sonnet-20240620-v1:0", "provider": "amazon", "model": "anthropic.claude-3-7-sonnet-20240620-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-7-sonnet-20240620-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-7-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-7-sonnet-20240620-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-7-sonnet-20250219-v1:0", "provider": "amazon", "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-haiku-20240307-v1:0", "provider": "amazon", "model": "anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-haiku-20240307-v1:0", "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.3125, "input": 0.25, "output": 1.25 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-opus-20240229-v1:0", "provider": "amazon", "model": "anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-opus-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-opus-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-opus-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-3-sonnet-20240229-v1:0", "provider": "amazon", "model": "anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-3-sonnet-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-3-sonnet-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "amazon", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.12, "cacheWrite": 1.5, "input": 1.2, "output": 6 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000024 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.12, "cacheWrite": 1.5, "input": 1.2, "output": 6 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000024 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "amazon/anthropic.claude-instant-v1", "provider": "amazon", "model": "anthropic.claude-instant-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-instant-v1", "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "bedrock/ap-northeast-1/anthropic.claude-instant-v1", "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "bedrock/eu-central-1/anthropic.claude-instant-v1", "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1", "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1", "bedrock/us-east-1/anthropic.claude-instant-v1", "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1", "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1", "bedrock/us-west-2/anthropic.claude-instant-v1" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 100000, "inputTokens": 100000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.01475 }, "extra": { "input_cost_per_second": 0.01475 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.008194 }, "extra": { "input_cost_per_second": 0.008194 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.23, "output": 7.55 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.01635 }, "extra": { "input_cost_per_second": 0.01635 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.009083 }, "extra": { "input_cost_per_second": 0.009083 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.48, "output": 8.38 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.011 }, "extra": { "input_cost_per_second": 0.011 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00611 }, "extra": { "input_cost_per_second": 0.00611 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.011 }, "extra": { "input_cost_per_second": 0.011 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00611 }, "extra": { "input_cost_per_second": 0.00611 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-instant-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-instant-v1", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-mythos-preview", "provider": "amazon", "model": "anthropic.claude-mythos-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-mythos-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-mythos-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-mythos-preview", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "amazon", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000072 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000072 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-v1", "provider": "amazon", "model": "anthropic.claude-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-v1", "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1", "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1", "bedrock/ap-northeast-1/anthropic.claude-v1", "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1", "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1", "bedrock/eu-central-1/anthropic.claude-v1", "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1", "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1", "bedrock/us-east-1/anthropic.claude-v1", "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1", "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1", "bedrock/us-west-2/anthropic.claude-v1" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 100000, "inputTokens": 100000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0455 }, "extra": { "input_cost_per_second": 0.0455 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.02527 }, "extra": { "input_cost_per_second": 0.02527 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0415 }, "extra": { "input_cost_per_second": 0.0415 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.02305 }, "extra": { "input_cost_per_second": 0.02305 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0175 }, "extra": { "input_cost_per_second": 0.0175 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00972 }, "extra": { "input_cost_per_second": 0.00972 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0175 }, "extra": { "input_cost_per_second": 0.0175 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00972 }, "extra": { "input_cost_per_second": 0.00972 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-v1", "mode": "chat" } ] }, { "id": "amazon/anthropic.claude-v2:1", "provider": "amazon", "model": "anthropic.claude-v2:1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/anthropic.claude-v2:1", "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "bedrock/ap-northeast-1/anthropic.claude-v2:1", "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1", "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1", "bedrock/eu-central-1/anthropic.claude-v2:1", "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1", "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1", "bedrock/us-east-1/anthropic.claude-v2:1", "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1", "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1", "bedrock/us-west-2/anthropic.claude-v2:1" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 100000, "inputTokens": 100000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0455 }, "extra": { "input_cost_per_second": 0.0455 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.02527 }, "extra": { "input_cost_per_second": 0.02527 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0415 }, "extra": { "input_cost_per_second": 0.0415 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.02305 }, "extra": { "input_cost_per_second": 0.02305 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0175 }, "extra": { "input_cost_per_second": 0.0175 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00972 }, "extra": { "input_cost_per_second": 0.00972 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0175 }, "extra": { "input_cost_per_second": 0.0175 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.00972 }, "extra": { "input_cost_per_second": 0.00972 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-v2:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/anthropic.claude-v2:1", "mode": "chat" } ] }, { "id": "amazon/apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "provider": "amazon", "model": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/apac.anthropic.claude-3-5-sonnet-20240620-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" } ] }, { "id": "amazon/apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "provider": "amazon", "model": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/apac.anthropic.claude-3-5-sonnet-20241022-v2:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat" } ] }, { "id": "amazon/apac.anthropic.claude-3-haiku-20240307-v1:0", "provider": "amazon", "model": "apac.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/apac.anthropic.claude-3-haiku-20240307-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "apac.anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.3125, "input": 0.25, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "apac.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" } ] }, { "id": "amazon/apac.anthropic.claude-3-sonnet-20240229-v1:0", "provider": "amazon", "model": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/apac.anthropic.claude-3-sonnet-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/claude-sonnet-4-5-20250929-v1:0", "provider": "amazon", "model": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000072 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000072 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "amazon/cohere.command-light-text-v14", "provider": "amazon", "model": "cohere.command-light-text-v14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/*/1-month-commitment/cohere.command-light-text-v14", "bedrock/*/6-month-commitment/cohere.command-light-text-v14", "bedrock/cohere.command-light-text-v14" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/*/1-month-commitment/cohere.command-light-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.001902 }, "extra": { "input_cost_per_second": 0.001902 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/*/6-month-commitment/cohere.command-light-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0011416 }, "extra": { "input_cost_per_second": 0.0011416 } }, { "source": "litellm", "provider": "bedrock", "model": "cohere.command-light-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/*/1-month-commitment/cohere.command-light-text-v14", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/*/6-month-commitment/cohere.command-light-text-v14", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.command-light-text-v14", "mode": "chat" } ] }, { "id": "amazon/cohere.command-r-plus-v1:0", "provider": "amazon", "model": "cohere.command-r-plus-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.command-r-plus-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.command-r-plus-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.command-r-plus-v1:0", "mode": "chat" } ] }, { "id": "amazon/cohere.command-r-v1:0", "provider": "amazon", "model": "cohere.command-r-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.command-r-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.command-r-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.command-r-v1:0", "mode": "chat" } ] }, { "id": "amazon/cohere.command-text-v14", "provider": "amazon", "model": "cohere.command-text-v14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/*/1-month-commitment/cohere.command-text-v14", "bedrock/*/6-month-commitment/cohere.command-text-v14", "bedrock/cohere.command-text-v14" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/*/1-month-commitment/cohere.command-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.011 }, "extra": { "input_cost_per_second": 0.011 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/*/6-month-commitment/cohere.command-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0066027 }, "extra": { "input_cost_per_second": 0.0066027 } }, { "source": "litellm", "provider": "bedrock", "model": "cohere.command-text-v14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/*/1-month-commitment/cohere.command-text-v14", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/*/6-month-commitment/cohere.command-text-v14", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.command-text-v14", "mode": "chat" } ] }, { "id": "amazon/cohere.embed-english-v3", "provider": "amazon", "model": "cohere.embed-english-v3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.embed-english-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.embed-english-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.embed-english-v3", "mode": "embedding" } ] }, { "id": "amazon/cohere.embed-multilingual-v3", "provider": "amazon", "model": "cohere.embed-multilingual-v3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.embed-multilingual-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.embed-multilingual-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.embed-multilingual-v3", "mode": "embedding" } ] }, { "id": "amazon/cohere.embed-v4:0", "provider": "amazon", "model": "cohere.embed-v4:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.embed-v4:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.embed-v4:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.embed-v4:0", "mode": "embedding" } ] }, { "id": "amazon/cohere.rerank-v3-5:0", "provider": "amazon", "model": "cohere.rerank-v3-5:0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/cohere.rerank-v3-5:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxDocumentChunksPerQuery": 100, "maxQueryTokens": 32000, "maxTokens": 32000, "maxTokensPerDocumentChunk": 512, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "cohere.rerank-v3-5:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 }, "extra": { "max_document_chunks_per_query": 100, "max_tokens_per_document_chunk": 512 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "cohere.rerank-v3-5:0", "mode": "rerank" } ] }, { "id": "amazon/deepseek.v3.2", "provider": "amazon", "model": "deepseek.v3.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/deepseek.v3.2", "bedrock/ap-south-1/deepseek.v3.2", "bedrock/ap-southeast-3/deepseek.v3.2", "bedrock/eu-north-1/deepseek.v3.2", "bedrock/sa-east-1/deepseek.v3.2", "bedrock/us-east-1/deepseek.v3.2", "bedrock/us-east-2/deepseek.v3.2", "bedrock/us-west-2/deepseek.v3.2" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-3/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-north-1/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 1.85 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 1.85 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 1.85 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-3/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-north-1/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "amazon/eu.anthropic.claude-3-5-haiku-20241022-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-5-haiku-20241022-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.3125, "input": 0.25, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-5-sonnet-20240620-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "provider": "amazon", "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-5-sonnet-20241022-v2:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-7-sonnet-20250219-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-haiku-20240307-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-haiku-20240307-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.3125, "input": 0.25, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-opus-20240229-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-opus-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-opus-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.anthropic.claude-3-sonnet-20240229-v1:0", "provider": "amazon", "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.anthropic.claude-3-sonnet-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.meta.llama3-2-1b-instruct-v1:0", "provider": "amazon", "model": "eu.meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.meta.llama3-2-1b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.meta.llama3-2-1b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.13 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.meta.llama3-2-1b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.meta.llama3-2-3b-instruct-v1:0", "provider": "amazon", "model": "eu.meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.meta.llama3-2-3b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.meta.llama3-2-3b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.19, "output": 0.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.meta.llama3-2-3b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/eu.twelvelabs.marengo-embed-2-7-v1:0", "provider": "amazon", "model": "eu.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.twelvelabs.marengo-embed-2-7-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.twelvelabs.marengo-embed-2-7-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 70, "output": 0 }, "perImage": { "input": 0.0001 }, "perAudioSecond": { "input": 0.00014 }, "perVideoSecond": { "input": 0.0007 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding" } ] }, { "id": "amazon/eu.twelvelabs.pegasus-1-2-v1:0", "provider": "amazon", "model": "eu.twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu.twelvelabs.pegasus-1-2-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "eu.twelvelabs.pegasus-1-2-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 7.5 }, "perVideoSecond": { "input": 0.00049 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "eu.twelvelabs.pegasus-1-2-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama2-13b-chat-v1", "provider": "amazon", "model": "meta.llama2-13b-chat-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama2-13b-chat-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama2-13b-chat-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama2-13b-chat-v1", "mode": "chat" } ] }, { "id": "amazon/meta.llama2-70b-chat-v1", "provider": "amazon", "model": "meta.llama2-70b-chat-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama2-70b-chat-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama2-70b-chat-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.95, "output": 2.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama2-70b-chat-v1", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-1-405b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-1-405b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-1-405b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-1-405b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.32, "output": 16 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-1-405b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-1-70b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-1-70b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-1-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-1-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.99, "output": 0.99 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-1-70b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-1-8b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-1-8b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-1-8b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-1-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.22 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-1-8b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-2-11b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-2-11b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-2-11b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-2-11b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.35 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-2-11b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-2-1b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-2-1b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-2-1b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-2-1b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-2-3b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-2-3b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-2-3b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-2-3b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-2-90b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-2-90b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/meta.llama3-2-90b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-2-90b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-2-90b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-70b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0", "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0", "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0", "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0", "bedrock/meta.llama3-70b-instruct-v1:0", "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0", "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0", "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0", "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0", "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.18, "output": 4.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.05, "output": 4.03 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.86, "output": 3.78 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.45, "output": 4.55 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 4.45, "output": 5.88 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.65, "output": 3.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.65, "output": 3.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.65, "output": 3.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.65, "output": 3.5 } }, { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.65, "output": 3.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-70b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/meta.llama3-8b-instruct-v1:0", "provider": "amazon", "model": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0", "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0", "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0", "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0", "bedrock/meta.llama3-8b-instruct-v1:0", "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0", "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0", "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0", "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0", "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 0.72 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.69 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.32, "output": 0.65 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.39, "output": 0.78 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.01 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.65 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.65 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.6 } }, { "source": "litellm", "provider": "bedrock", "model": "meta.llama3-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "meta.llama3-8b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/minimax.minimax-m2.1", "provider": "amazon", "model": "minimax.minimax-m2.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/minimax.minimax-m2.1", "bedrock/ap-south-1/minimax.minimax-m2.1", "bedrock/ap-southeast-3/minimax.minimax-m2.1", "bedrock/eu-central-1/minimax.minimax-m2.1", "bedrock/eu-north-1/minimax.minimax-m2.1", "bedrock/eu-south-1/minimax.minimax-m2.1", "bedrock/eu-west-1/minimax.minimax-m2.1", "bedrock/eu-west-2/minimax.minimax-m2.1", "bedrock/sa-east-1/minimax.minimax-m2.1", "bedrock/us-east-1/minimax.minimax-m2.1", "bedrock/us-east-2/minimax.minimax-m2.1", "bedrock/us-west-2/minimax.minimax-m2.1" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 196000, "inputTokens": 196000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-3/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-north-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-south-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-2/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.47, "output": 1.86 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-3/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-north-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-south-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-2/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "amazon/minimax.minimax-m2.5", "provider": "amazon", "model": "minimax.minimax-m2.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/minimax.minimax-m2.5", "bedrock/ap-south-1/minimax.minimax-m2.5", "bedrock/ap-southeast-2/minimax.minimax-m2.5", "bedrock/ap-southeast-3/minimax.minimax-m2.5", "bedrock/eu-central-1/minimax.minimax-m2.5", "bedrock/eu-north-1/minimax.minimax-m2.5", "bedrock/eu-south-1/minimax.minimax-m2.5", "bedrock/eu-west-1/minimax.minimax-m2.5", "bedrock/eu-west-2/minimax.minimax-m2.5", "bedrock/sa-east-1/minimax.minimax-m2.5", "bedrock/us-east-1/minimax.minimax-m2.5", "bedrock/us-east-2/minimax.minimax-m2.5", "bedrock/us-west-2/minimax.minimax-m2.5" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-2/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.309, "output": 1.236 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-3/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-north-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-south-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-2/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.47, "output": 1.86 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.36, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-2/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-3/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-north-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-south-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-2/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "amazon/mistral.mistral-7b-instruct-v0:2", "provider": "amazon", "model": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2", "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2", "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.26 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2", "mode": "chat" } ] }, { "id": "amazon/mistral.mistral-large-2402-v1:0", "provider": "amazon", "model": "mistral.mistral-large-2402-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0", "bedrock/us-east-1/mistral.mistral-large-2402-v1:0", "bedrock/us-west-2/mistral.mistral-large-2402-v1:0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10.4, "output": 31.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mistral-large-2402-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mistral-large-2402-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mistral-large-2402-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mistral-large-2402-v1:0", "mode": "chat" } ] }, { "id": "amazon/mistral.mixtral-8x7b-instruct-v0:1", "provider": "amazon", "model": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.59, "output": 0.91 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 0.7 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat" } ] }, { "id": "amazon/moonshotai.kimi-k2-thinking", "provider": "amazon", "model": "moonshotai.kimi-k2-thinking", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking", "bedrock/ap-south-1/moonshotai.kimi-k2-thinking", "bedrock/moonshotai.kimi-k2-thinking", "bedrock/sa-east-1/moonshotai.kimi-k2-thinking", "bedrock/us-east-1/moonshotai.kimi-k2-thinking", "bedrock/us-east-2/moonshotai.kimi-k2-thinking", "bedrock/us-west-2/moonshotai.kimi-k2-thinking" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.73, "output": 3.03 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.71, "output": 2.94 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.73, "output": 3.03 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.73, "output": 3.03 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/moonshotai.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/moonshotai.kimi-k2-thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/moonshotai.kimi-k2-thinking", "mode": "chat" } ] }, { "id": "amazon/moonshotai.kimi-k2.5", "provider": "amazon", "model": "moonshotai.kimi-k2.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/moonshotai.kimi-k2.5", "bedrock/ap-south-1/moonshotai.kimi-k2.5", "bedrock/ap-southeast-3/moonshotai.kimi-k2.5", "bedrock/eu-north-1/moonshotai.kimi-k2.5", "bedrock/moonshotai.kimi-k2.5", "bedrock/sa-east-1/moonshotai.kimi-k2.5", "bedrock/us-east-1/moonshotai.kimi-k2.5", "bedrock/us-east-2/moonshotai.kimi-k2.5", "bedrock/us-west-2/moonshotai.kimi-k2.5" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": false, "reasoning": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 3.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 3.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-3/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 3.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-north-1/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 3.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3.03 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 3.6 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-3/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-north-1/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "amazon/nova-2", "provider": "amazon", "model": "nova-2", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-atc", "provider": "amazon", "model": "nova-2-atc", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-atc" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-atc", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-atc", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-automotive", "provider": "amazon", "model": "nova-2-automotive", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-automotive" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-automotive", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-automotive", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-conversationalai", "provider": "amazon", "model": "nova-2-conversationalai", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-conversationalai" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-conversationalai", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-conversationalai", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-drivethru", "provider": "amazon", "model": "nova-2-drivethru", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-drivethru" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-drivethru", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-drivethru", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-finance", "provider": "amazon", "model": "nova-2-finance", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-finance" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-finance", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-finance", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-general", "provider": "amazon", "model": "nova-2-general", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-general" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-general", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-general", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-lite", "provider": "amazon", "model": "nova-2-lite", "displayName": "Nova 2 Lite", "family": "nova", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/amazon/nova-2-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "amazon/nova-2-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Nova 2 Lite" ], "families": [ "nova" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "amazon/nova-2-lite", "modelKey": "amazon/nova-2-lite", "displayName": "Nova 2 Lite", "family": "nova", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "amazon/nova-2-lite-v1", "provider": "amazon", "model": "nova-2-lite-v1", "displayName": "Amazon: Nova 2 Lite", "family": "nova", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "nova", "openrouter" ], "aliases": [ "kilo/amazon/nova-2-lite-v1", "nano-gpt/amazon/nova-2-lite-v1", "nova/nova-2-lite-v1", "openrouter/amazon/nova-2-lite-v1" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 65535, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "amazon/nova-2-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "amazon/nova-2-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5099999999999999, "output": 4.25 } }, { "source": "models.dev", "provider": "nova", "model": "nova-2-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0, "reasoningOutput": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "amazon/nova-2-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "amazon/nova-2-lite-v1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Amazon Nova 2 Lite", "Amazon: Nova 2 Lite", "Nova 2 Lite" ], "families": [ "nova", "nova-lite" ], "releaseDate": "2024-12-01", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "amazon/nova-2-lite-v1", "modelKey": "amazon/nova-2-lite-v1", "displayName": "Amazon: Nova 2 Lite", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "amazon/nova-2-lite-v1", "modelKey": "amazon/nova-2-lite-v1", "displayName": "Amazon Nova 2 Lite", "family": "nova", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nova", "providerName": "Nova", "providerApi": "https://api.nova.amazon.com/v1", "providerDoc": "https://nova.amazon.com/dev/documentation", "model": "nova-2-lite-v1", "modelKey": "nova-2-lite-v1", "displayName": "Nova 2 Lite", "family": "nova-lite", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "amazon/nova-2-lite-v1", "modelKey": "amazon/nova-2-lite-v1", "displayName": "Nova 2 Lite", "family": "nova", "metadata": { "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "amazon/nova-2-lite-v1", "displayName": "Amazon: Nova 2 Lite", "metadata": { "canonicalSlug": "amazon/nova-2-lite-v1", "createdAt": "2025-12-02T17:31:12.000Z", "links": { "details": "/api/v1/models/amazon/nova-2-lite-v1/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Nova", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65535, "is_moderated": true } } } ] }, { "id": "amazon/nova-2-meeting", "provider": "amazon", "model": "nova-2-meeting", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-meeting" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-meeting", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-meeting", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-phonecall", "provider": "amazon", "model": "nova-2-phonecall", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-phonecall" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-phonecall", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-phonecall", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-pro-v1", "provider": "amazon", "model": "nova-2-pro-v1", "displayName": "Nova 2 Pro", "family": "nova-pro", "sources": [ "models.dev" ], "providers": [ "nova" ], "aliases": [ "nova/nova-2-pro-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nova", "model": "nova-2-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0, "reasoningOutput": 0 } } ] }, "metadata": { "displayNames": [ "Nova 2 Pro" ], "families": [ "nova-pro" ], "releaseDate": "2025-12-03", "lastUpdated": "2026-01-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nova", "providerName": "Nova", "providerApi": "https://api.nova.amazon.com/v1", "providerDoc": "https://nova.amazon.com/dev/documentation", "model": "nova-2-pro-v1", "modelKey": "nova-2-pro-v1", "displayName": "Nova 2 Pro", "family": "nova-pro", "metadata": { "lastUpdated": "2026-01-03", "openWeights": false, "releaseDate": "2025-12-03" } } ] }, { "id": "amazon/nova-2-video", "provider": "amazon", "model": "nova-2-video", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-video" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-video", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-video", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-2-voicemail", "provider": "amazon", "model": "nova-2-voicemail", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-2-voicemail" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-2-voicemail", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-2-voicemail", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-3", "provider": "amazon", "model": "nova-3", "displayName": "Deepgram Nova 3", "family": "nova", "mode": "audio_transcription", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "deepgram" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/deepgram/nova-3", "deepgram/nova-3" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/deepgram/nova-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "displayNames": [ "Deepgram Nova 3" ], "families": [ "nova" ], "modes": [ "audio_transcription" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/deepgram/nova-3", "modelKey": "workers-ai/@cf/deepgram/nova-3", "displayName": "Deepgram Nova 3", "family": "nova", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-3", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-3-general", "provider": "amazon", "model": "nova-3-general", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-3-general" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-3-general", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-3-general", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-3-medical", "provider": "amazon", "model": "nova-3-medical", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-3-medical" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-3-medical", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00008667 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-3-medical", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", "original_pricing_per_minute": 0.0052 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-general", "provider": "amazon", "model": "nova-general", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-general" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-general", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-general", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-lite", "provider": "amazon", "model": "nova-lite", "displayName": "Nova Lite", "family": "nova-lite", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/amazon/nova-lite", "vercel_ai_gateway/amazon/nova-lite" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "amazon/nova-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.06, "output": 0.24 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Nova Lite" ], "families": [ "nova-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "amazon/nova-lite", "modelKey": "amazon/nova-lite", "displayName": "Nova Lite", "family": "nova-lite", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-lite", "mode": "chat" } ] }, { "id": "amazon/nova-lite-v1", "provider": "amazon", "model": "nova-lite-v1", "displayName": "Amazon: Nova Lite 1.0", "family": "nova-lite", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "amazon_nova", "kilo", "nano-gpt", "openrouter" ], "aliases": [ "amazon_nova/amazon-nova/nova-lite-v1", "kilo/amazon/nova-lite-v1", "nano-gpt/amazon/nova-lite-v1", "openrouter/amazon/nova-lite-v1" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "amazon/nova-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.24 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "amazon/nova-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0595, "output": 0.238 } }, { "source": "models.dev", "provider": "openrouter", "model": "amazon/nova-lite-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.24 } }, { "source": "litellm", "provider": "amazon_nova", "model": "amazon-nova/nova-lite-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } }, { "source": "openrouter", "provider": "openrouter", "model": "amazon/nova-lite-v1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Amazon Nova Lite 1.0", "Amazon: Nova Lite 1.0", "Nova Lite 1.0" ], "families": [ "nova-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-12-06", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "amazon/nova-lite-v1", "modelKey": "amazon/nova-lite-v1", "displayName": "Amazon: Nova Lite 1.0", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "amazon/nova-lite-v1", "modelKey": "amazon/nova-lite-v1", "displayName": "Amazon Nova Lite 1.0", "family": "nova-lite", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "amazon/nova-lite-v1", "modelKey": "amazon/nova-lite-v1", "displayName": "Nova Lite 1.0", "family": "nova-lite", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "amazon_nova", "model": "amazon-nova/nova-lite-v1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "amazon/nova-lite-v1", "displayName": "Amazon: Nova Lite 1.0", "metadata": { "canonicalSlug": "amazon/nova-lite-v1", "createdAt": "2024-12-05T22:22:43.000Z", "knowledgeCutoff": "2024-10-31", "links": { "details": "/api/v1/models/amazon/nova-lite-v1/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "tokenizer": "Nova", "topProvider": { "context_length": 300000, "max_completion_tokens": 5120, "is_moderated": true } } } ] }, { "id": "amazon/nova-micro", "provider": "amazon", "model": "nova-micro", "displayName": "Nova Micro", "family": "nova-micro", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/amazon/nova-micro", "vercel_ai_gateway/amazon/nova-micro" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "amazon/nova-micro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.00875, "input": 0.035, "output": 0.14 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-micro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Nova Micro" ], "families": [ "nova-micro" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "amazon/nova-micro", "modelKey": "amazon/nova-micro", "displayName": "Nova Micro", "family": "nova-micro", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-micro", "mode": "chat" } ] }, { "id": "amazon/nova-micro-v1", "provider": "amazon", "model": "nova-micro-v1", "displayName": "Amazon: Nova Micro 1.0", "family": "nova-micro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "amazon_nova", "kilo", "nano-gpt", "openrouter" ], "aliases": [ "amazon_nova/amazon-nova/nova-micro-v1", "kilo/amazon/nova-micro-v1", "nano-gpt/amazon/nova-micro-v1", "openrouter/amazon/nova-micro-v1" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "amazon/nova-micro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.035, "output": 0.14 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "amazon/nova-micro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0357, "output": 0.1394 } }, { "source": "models.dev", "provider": "openrouter", "model": "amazon/nova-micro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.035, "output": 0.14 } }, { "source": "litellm", "provider": "amazon_nova", "model": "amazon-nova/nova-micro-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.14 } }, { "source": "openrouter", "provider": "openrouter", "model": "amazon/nova-micro-v1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Amazon Nova Micro 1.0", "Amazon: Nova Micro 1.0", "Nova Micro 1.0" ], "families": [ "nova-micro" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-12-06", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "amazon/nova-micro-v1", "modelKey": "amazon/nova-micro-v1", "displayName": "Amazon: Nova Micro 1.0", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "amazon/nova-micro-v1", "modelKey": "amazon/nova-micro-v1", "displayName": "Amazon Nova Micro 1.0", "family": "nova-micro", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "amazon/nova-micro-v1", "modelKey": "amazon/nova-micro-v1", "displayName": "Nova Micro 1.0", "family": "nova-micro", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "amazon_nova", "model": "amazon-nova/nova-micro-v1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "amazon/nova-micro-v1", "displayName": "Amazon: Nova Micro 1.0", "metadata": { "canonicalSlug": "amazon/nova-micro-v1", "createdAt": "2024-12-05T22:20:37.000Z", "knowledgeCutoff": "2024-10-31", "links": { "details": "/api/v1/models/amazon/nova-micro-v1/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "tokenizer": "Nova", "topProvider": { "context_length": 128000, "max_completion_tokens": 5120, "is_moderated": true } } } ] }, { "id": "amazon/nova-phonecall", "provider": "amazon", "model": "nova-phonecall", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova-phonecall" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova-phonecall", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova-phonecall", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "amazon/nova-premier-v1", "provider": "amazon", "model": "nova-premier-v1", "displayName": "Amazon: Nova Premier 1.0", "family": "nova", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "amazon_nova", "kilo", "openrouter" ], "aliases": [ "amazon_nova/amazon-nova/nova-premier-v1", "kilo/amazon/nova-premier-v1", "openrouter/amazon/nova-premier-v1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 10000, "outputTokens": 32000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "amazon/nova-premier-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 12.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "amazon/nova-premier-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.625, "input": 2.5, "output": 12.5 } }, { "source": "litellm", "provider": "amazon_nova", "model": "amazon-nova/nova-premier-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 12.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "amazon/nova-premier-v1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.625, "input": 2.5, "output": 12.5 } } ] }, "metadata": { "displayNames": [ "Amazon: Nova Premier 1.0", "Nova Premier 1.0" ], "families": [ "nova" ], "modes": [ "chat" ], "releaseDate": "2025-11-01", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "amazon/nova-premier-v1", "modelKey": "amazon/nova-premier-v1", "displayName": "Amazon: Nova Premier 1.0", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "amazon/nova-premier-v1", "modelKey": "amazon/nova-premier-v1", "displayName": "Nova Premier 1.0", "family": "nova", "metadata": { "lastUpdated": "2025-10-31", "openWeights": false, "releaseDate": "2025-10-31" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "amazon_nova", "model": "amazon-nova/nova-premier-v1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "amazon/nova-premier-v1", "displayName": "Amazon: Nova Premier 1.0", "metadata": { "canonicalSlug": "amazon/nova-premier-v1", "createdAt": "2025-10-31T22:38:52.000Z", "links": { "details": "/api/v1/models/amazon/nova-premier-v1/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "tokenizer": "Nova", "topProvider": { "context_length": 1000000, "max_completion_tokens": 32000, "is_moderated": true } } } ] }, { "id": "amazon/nova-pro", "provider": "amazon", "model": "nova-pro", "displayName": "Nova Pro", "family": "nova-pro", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/amazon/nova-pro", "vercel_ai_gateway/amazon/nova-pro" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "amazon/nova-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.8, "output": 3.2 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "Nova Pro" ], "families": [ "nova-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "amazon/nova-pro", "modelKey": "amazon/nova-pro", "displayName": "Nova Pro", "family": "nova-pro", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/nova-pro", "mode": "chat" } ] }, { "id": "amazon/nova-pro-v1", "provider": "amazon", "model": "nova-pro-v1", "displayName": "Nova Pro 1.0", "family": "nova-pro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "amazon_nova", "cortecs", "kilo", "nano-gpt", "openrouter" ], "aliases": [ "amazon_nova/amazon-nova/nova-pro-v1", "cortecs/nova-pro-v1", "kilo/amazon/nova-pro-v1", "nano-gpt/amazon/nova-pro-v1", "openrouter/amazon/nova-pro-v1" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "nova-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.016, "output": 4.061 } }, { "source": "models.dev", "provider": "kilo", "model": "amazon/nova-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 3.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "amazon/nova-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7989999999999999, "output": 3.1959999999999997 } }, { "source": "models.dev", "provider": "openrouter", "model": "amazon/nova-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 3.2 } }, { "source": "litellm", "provider": "amazon_nova", "model": "amazon-nova/nova-pro-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 3.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "amazon/nova-pro-v1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "Amazon Nova Pro 1.0", "Amazon: Nova Pro 1.0", "Nova Pro 1.0" ], "families": [ "nova-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "nova-pro-v1", "modelKey": "nova-pro-v1", "displayName": "Nova Pro 1.0", "family": "nova-pro", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "amazon/nova-pro-v1", "modelKey": "amazon/nova-pro-v1", "displayName": "Amazon: Nova Pro 1.0", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "amazon/nova-pro-v1", "modelKey": "amazon/nova-pro-v1", "displayName": "Amazon Nova Pro 1.0", "family": "nova-pro", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "amazon/nova-pro-v1", "modelKey": "amazon/nova-pro-v1", "displayName": "Nova Pro 1.0", "family": "nova-pro", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "amazon_nova", "model": "amazon-nova/nova-pro-v1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "amazon/nova-pro-v1", "displayName": "Amazon: Nova Pro 1.0", "metadata": { "canonicalSlug": "amazon/nova-pro-v1", "createdAt": "2024-12-05T22:05:03.000Z", "knowledgeCutoff": "2024-10-31", "links": { "details": "/api/v1/models/amazon/nova-pro-v1/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ], "tokenizer": "Nova", "topProvider": { "context_length": 300000, "max_completion_tokens": 5120, "is_moderated": true } } } ] }, { "id": "amazon/qwen.qwen3-coder-next", "provider": "amazon", "model": "qwen.qwen3-coder-next", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/ap-northeast-1/qwen.qwen3-coder-next", "bedrock/ap-south-1/qwen.qwen3-coder-next", "bedrock/ap-southeast-3/qwen.qwen3-coder-next", "bedrock/eu-central-1/qwen.qwen3-coder-next", "bedrock/eu-south-1/qwen.qwen3-coder-next", "bedrock/eu-west-1/qwen.qwen3-coder-next", "bedrock/eu-west-2/qwen.qwen3-coder-next", "bedrock/sa-east-1/qwen.qwen3-coder-next", "bedrock/us-east-1/qwen.qwen3-coder-next", "bedrock/us-east-2/qwen.qwen3-coder-next", "bedrock/us-west-2/qwen.qwen3-coder-next" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-northeast-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-south-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/ap-southeast-3/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-central-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-south-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/eu-west-2/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.78, "output": 1.86 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/sa-east-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.44 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-2/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/qwen.qwen3-coder-next", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-northeast-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-south-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/ap-southeast-3/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-central-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-south-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/eu-west-2/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/sa-east-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-2/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/qwen.qwen3-coder-next", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "amazon/stability.sd3-5-large-v1:0", "provider": "amazon", "model": "stability.sd3-5-large-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.sd3-5-large-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.sd3-5-large-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.sd3-5-large-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/stability.sd3-large-v1:0", "provider": "amazon", "model": "stability.sd3-large-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.sd3-large-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.sd3-large-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.sd3-large-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-conservative-upscale-v1:0", "provider": "amazon", "model": "stability.stable-conservative-upscale-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-conservative-upscale-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-conservative-upscale-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.4 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-conservative-upscale-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-creative-upscale-v1:0", "provider": "amazon", "model": "stability.stable-creative-upscale-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-creative-upscale-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-creative-upscale-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.6 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-creative-upscale-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-diffusion-xl-v0", "provider": "amazon", "model": "stability.stable-diffusion-xl-v0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/512-x-512/50-steps/stability.stable-diffusion-xl-v0", "bedrock/512-x-512/max-steps/stability.stable-diffusion-xl-v0", "bedrock/max-x-max/50-steps/stability.stable-diffusion-xl-v0", "bedrock/max-x-max/max-steps/stability.stable-diffusion-xl-v0" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "512-x-512/50-steps/stability.stable-diffusion-xl-v0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.018 } }, { "source": "litellm", "provider": "bedrock", "model": "512-x-512/max-steps/stability.stable-diffusion-xl-v0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.036 } }, { "source": "litellm", "provider": "bedrock", "model": "max-x-max/50-steps/stability.stable-diffusion-xl-v0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.036 } }, { "source": "litellm", "provider": "bedrock", "model": "max-x-max/max-steps/stability.stable-diffusion-xl-v0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.072 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "512-x-512/50-steps/stability.stable-diffusion-xl-v0", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "512-x-512/max-steps/stability.stable-diffusion-xl-v0", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "max-x-max/50-steps/stability.stable-diffusion-xl-v0", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "max-x-max/max-steps/stability.stable-diffusion-xl-v0", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-diffusion-xl-v1", "provider": "amazon", "model": "stability.stable-diffusion-xl-v1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/1024-x-1024/50-steps/stability.stable-diffusion-xl-v1", "bedrock/1024-x-1024/max-steps/stability.stable-diffusion-xl-v1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } }, { "source": "litellm", "provider": "bedrock", "model": "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-fast-upscale-v1:0", "provider": "amazon", "model": "stability.stable-fast-upscale-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-fast-upscale-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-fast-upscale-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.03 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-fast-upscale-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-control-sketch-v1:0", "provider": "amazon", "model": "stability.stable-image-control-sketch-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-control-sketch-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-control-sketch-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-control-sketch-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-control-structure-v1:0", "provider": "amazon", "model": "stability.stable-image-control-structure-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-control-structure-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-control-structure-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-control-structure-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-core-v1:0", "provider": "amazon", "model": "stability.stable-image-core-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-core-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-core-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-core-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-image-core-v1:1", "provider": "amazon", "model": "stability.stable-image-core-v1:1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-core-v1:1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-core-v1:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-core-v1:1", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-image-erase-object-v1:0", "provider": "amazon", "model": "stability.stable-image-erase-object-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-erase-object-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-erase-object-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-erase-object-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-inpaint-v1:0", "provider": "amazon", "model": "stability.stable-image-inpaint-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-inpaint-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-inpaint-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-inpaint-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-remove-background-v1:0", "provider": "amazon", "model": "stability.stable-image-remove-background-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-remove-background-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-remove-background-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-remove-background-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-search-recolor-v1:0", "provider": "amazon", "model": "stability.stable-image-search-recolor-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-search-recolor-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-search-recolor-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-search-recolor-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-search-replace-v1:0", "provider": "amazon", "model": "stability.stable-image-search-replace-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-search-replace-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-search-replace-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-search-replace-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-style-guide-v1:0", "provider": "amazon", "model": "stability.stable-image-style-guide-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-style-guide-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-style-guide-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.07 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-style-guide-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-image-ultra-v1:0", "provider": "amazon", "model": "stability.stable-image-ultra-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-ultra-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-ultra-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.14 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-ultra-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-image-ultra-v1:1", "provider": "amazon", "model": "stability.stable-image-ultra-v1:1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-image-ultra-v1:1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-image-ultra-v1:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.14 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-image-ultra-v1:1", "mode": "image_generation" } ] }, { "id": "amazon/stability.stable-outpaint-v1:0", "provider": "amazon", "model": "stability.stable-outpaint-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-outpaint-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-outpaint-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-outpaint-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/stability.stable-style-transfer-v1:0", "provider": "amazon", "model": "stability.stable-style-transfer-v1:0", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/stability.stable-style-transfer-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "stability.stable-style-transfer-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_edit" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "stability.stable-style-transfer-v1:0", "mode": "image_edit" } ] }, { "id": "amazon/titan-embed-text-v2", "provider": "amazon", "model": "titan-embed-text-v2", "displayName": "Titan Text Embeddings V2", "family": "titan-embed", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/amazon/titan-embed-text-v2", "vercel_ai_gateway/amazon/titan-embed-text-v2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 0, "maxTokens": 0, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/titan-embed-text-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "displayNames": [ "Titan Text Embeddings V2" ], "families": [ "titan-embed" ], "modes": [ "chat" ], "releaseDate": "2024-04-01", "lastUpdated": "2024-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "amazon/titan-embed-text-v2", "modelKey": "amazon/titan-embed-text-v2", "displayName": "Titan Text Embeddings V2", "family": "titan-embed", "metadata": { "lastUpdated": "2024-04", "openWeights": false, "releaseDate": "2024-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/amazon/titan-embed-text-v2", "mode": "chat" } ] }, { "id": "amazon/twelvelabs.marengo-embed-2-7-v1:0", "provider": "amazon", "model": "twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/twelvelabs.marengo-embed-2-7-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "twelvelabs.marengo-embed-2-7-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 70, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding" } ] }, { "id": "amazon/twelvelabs.pegasus-1-2-v1:0", "provider": "amazon", "model": "twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/twelvelabs.pegasus-1-2-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "twelvelabs.pegasus-1-2-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 7.5 }, "perVideoSecond": { "input": 0.00049 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "twelvelabs.pegasus-1-2-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.amazon.nova-canvas-v1:0", "provider": "amazon", "model": "us.amazon.nova-canvas-v1:0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.amazon.nova-canvas-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2600, "inputTokens": 2600, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageEditing": true, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.amazon.nova-canvas-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.amazon.nova-canvas-v1:0", "mode": "image_generation" } ] }, { "id": "amazon/us.anthropic.claude-3-5-haiku-20241022-v1:0", "provider": "amazon", "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.anthropic.claude-3-5-sonnet-20240620-v1:0", "provider": "amazon", "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-5-sonnet-20240620-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.anthropic.claude-3-5-sonnet-20241022-v2:0", "provider": "amazon", "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat" } ] }, { "id": "amazon/us.anthropic.claude-3-haiku-20240307-v1:0", "provider": "amazon", "model": "us.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-haiku-20240307-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-haiku-20240307-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.3125, "input": 0.25, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.anthropic.claude-3-opus-20240229-v1:0", "provider": "amazon", "model": "us.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-opus-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-opus-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.anthropic.claude-3-sonnet-20240229-v1:0", "provider": "amazon", "model": "us.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.anthropic.claude-3-sonnet-20240229-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-1-405b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-1-405b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-1-405b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-1-405b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.32, "output": 16 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-1-405b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-1-70b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-1-70b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-1-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-1-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.99, "output": 0.99 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-1-70b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-1-8b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-1-8b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-1-8b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-1-8b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.22 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-1-8b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-2-11b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-2-11b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-2-11b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-2-11b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.35 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-2-11b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-2-1b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-2-1b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-2-1b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-2-1b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-2-3b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-2-3b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-2-3b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-2-3b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.meta.llama3-2-90b-instruct-v1:0", "provider": "amazon", "model": "us.meta.llama3-2-90b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.meta.llama3-2-90b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.meta.llama3-2-90b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.meta.llama3-2-90b-instruct-v1:0", "mode": "chat" } ] }, { "id": "amazon/us.twelvelabs.marengo-embed-2-7-v1:0", "provider": "amazon", "model": "us.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.twelvelabs.marengo-embed-2-7-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "maxTokens": 77, "outputTokens": 77, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.twelvelabs.marengo-embed-2-7-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 70, "output": 0 }, "perImage": { "input": 0.0001 }, "perAudioSecond": { "input": 0.00014 }, "perVideoSecond": { "input": 0.0007 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding" } ] }, { "id": "amazon/us.twelvelabs.pegasus-1-2-v1:0", "provider": "amazon", "model": "us.twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us.twelvelabs.pegasus-1-2-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "us.twelvelabs.pegasus-1-2-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 7.5 }, "perVideoSecond": { "input": 0.00049 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "us.twelvelabs.pegasus-1-2-v1:0", "mode": "chat" } ] }, { "id": "amazon/zai.glm-5", "provider": "amazon", "model": "zai.glm-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/us-east-1/zai.glm-5", "bedrock/us-west-2/zai.glm-5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-east-1/zai.glm-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3.2 } }, { "source": "litellm", "provider": "bedrock", "model": "bedrock/us-west-2/zai.glm-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-east-1/zai.glm-5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "bedrock/us-west-2/zai.glm-5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "anthropic/claude-3-5-haiku", "provider": "anthropic", "model": "claude-3-5-haiku", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "heroku", "llmgateway", "opencode", "vertex_ai-anthropic_models" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3-5-haiku", "heroku/claude-3-5-haiku", "llmgateway/claude-3-5-haiku", "opencode/claude-3-5-haiku", "vertex_ai-anthropic_models/vertex_ai/claude-3-5-haiku" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "assistantPrefill": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3-5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-3-5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-3-5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "litellm", "provider": "heroku", "model": "heroku/claude-3-5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude 3.5 Haiku", "Claude Haiku 3.5", "Claude Haiku 3.5 (latest)" ], "families": [ "claude", "claude-haiku" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3-5-haiku", "modelKey": "anthropic/claude-3-5-haiku", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-3-5-haiku", "modelKey": "claude-3-5-haiku", "displayName": "Claude 3.5 Haiku", "family": "claude", "status": "deprecated", "metadata": { "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-3-5-haiku", "modelKey": "claude-3-5-haiku", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "heroku", "model": "heroku/claude-3-5-haiku", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-haiku", "mode": "chat" } ] }, { "id": "anthropic/claude-3-5-haiku-20241022", "provider": "anthropic", "model": "claude-3-5-haiku-20241022", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "302ai", "anthropic", "nano-gpt" ], "aliases": [ "302ai/claude-3-5-haiku-20241022", "anthropic/claude-3-5-haiku-20241022", "nano-gpt/claude-3-5-haiku-20241022" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-3-5-haiku-20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-3-5-haiku-20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-3-5-haiku-20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 4 } } ] }, "metadata": { "displayNames": [ "Claude 3.5 Haiku", "Claude Haiku 3.5", "claude-3-5-haiku-20241022" ], "families": [ "claude-haiku" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-3-5-haiku-20241022", "modelKey": "claude-3-5-haiku-20241022", "displayName": "claude-3-5-haiku-20241022", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-5-haiku-20241022", "modelKey": "claude-3-5-haiku-20241022", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-3-5-haiku-20241022", "modelKey": "claude-3-5-haiku-20241022", "displayName": "Claude 3.5 Haiku", "metadata": { "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } } ] }, { "id": "anthropic/claude-3-5-haiku-latest", "provider": "anthropic", "model": "claude-3-5-haiku-latest", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "302ai", "anthropic" ], "aliases": [ "302ai/claude-3-5-haiku-latest", "anthropic/claude-3-5-haiku-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-3-5-haiku-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-3-5-haiku-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 3.5 (latest)", "claude-3-5-haiku-latest" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-3-5-haiku-latest", "modelKey": "claude-3-5-haiku-latest", "displayName": "claude-3-5-haiku-latest", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-5-haiku-latest", "modelKey": "claude-3-5-haiku-latest", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } } ] }, { "id": "anthropic/claude-3-5-haiku@20241022", "provider": "anthropic", "model": "claude-3-5-haiku@20241022", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-3-5-haiku@20241022", "google-vertex/claude-3-5-haiku@20241022", "vertex_ai-anthropic_models/vertex_ai/claude-3-5-haiku@20241022" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-3-5-haiku@20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-3-5-haiku@20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-haiku@20241022", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 3.5" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-3-5-haiku@20241022", "modelKey": "claude-3-5-haiku@20241022", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-3-5-haiku@20241022", "modelKey": "claude-3-5-haiku@20241022", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-haiku@20241022", "mode": "chat" } ] }, { "id": "anthropic/claude-3-5-sonnet", "provider": "anthropic", "model": "claude-3-5-sonnet", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake", "vercel_ai_gateway", "vertex_ai-anthropic_models" ], "aliases": [ "snowflake/claude-3-5-sonnet", "vercel_ai_gateway/anthropic/claude-3-5-sonnet", "vertex_ai-anthropic_models/vertex_ai/claude-3-5-sonnet" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "assistantPrefill": true, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-3-5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-3-5-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-5-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-3-5-sonnet-20240620", "provider": "anthropic", "model": "claude-3-5-sonnet-20240620", "displayName": "Claude Sonnet 3.5", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-3-5-sonnet-20240620" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-3-5-sonnet-20240620", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 3.5" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-06-20", "lastUpdated": "2024-06-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-5-sonnet-20240620", "modelKey": "claude-3-5-sonnet-20240620", "displayName": "Claude Sonnet 3.5", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-06-20", "openWeights": false, "releaseDate": "2024-06-20" } } ] }, { "id": "anthropic/claude-3-5-sonnet-20241022", "provider": "anthropic", "model": "claude-3-5-sonnet-20241022", "displayName": "Claude Sonnet 3.5 v2", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anthropic", "llmgateway", "vercel_ai_gateway" ], "aliases": [ "anthropic/claude-3-5-sonnet-20241022", "llmgateway/claude-3-5-sonnet-20241022", "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-3-5-sonnet-20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-3-5-sonnet-20241022", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 3.5 v2" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-5-sonnet-20241022", "modelKey": "claude-3-5-sonnet-20241022", "displayName": "Claude Sonnet 3.5 v2", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-3-5-sonnet-20241022", "modelKey": "claude-3-5-sonnet-20241022", "displayName": "Claude Sonnet 3.5 v2", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022", "mode": "chat" } ] }, { "id": "anthropic/claude-3-5-sonnet-latest", "provider": "anthropic", "model": "claude-3-5-sonnet-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "heroku" ], "aliases": [ "heroku/claude-3-5-sonnet-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "heroku", "model": "heroku/claude-3-5-sonnet-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "heroku", "model": "heroku/claude-3-5-sonnet-latest", "mode": "chat" } ] }, { "id": "anthropic/claude-3-5-sonnet@20240620", "provider": "anthropic", "model": "claude-3-5-sonnet@20240620", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-3-5-sonnet@20240620" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-sonnet@20240620", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-5-sonnet@20240620", "mode": "chat" } ] }, { "id": "anthropic/claude-3-7-sonnet", "provider": "anthropic", "model": "claude-3-7-sonnet", "displayName": "Claude 3.7 Sonnet", "family": "claude", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "heroku", "llmgateway", "requesty", "snowflake", "vercel_ai_gateway" ], "aliases": [ "heroku/claude-3-7-sonnet", "llmgateway/claude-3-7-sonnet", "requesty/anthropic/claude-3-7-sonnet", "snowflake/claude-3-7-sonnet", "vercel_ai_gateway/anthropic/claude-3-7-sonnet" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "promptCaching": true, "responseSchema": true, "vision": true, "assistantPrefill": true, "computerUse": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "claude-3-7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-3-7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "heroku", "model": "heroku/claude-3-7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-3-7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude 3.7 Sonnet", "Claude Sonnet 3.7" ], "families": [ "claude", "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-01", "releaseDate": "2025-02-24", "lastUpdated": "2025-02-24", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-3-7-sonnet", "modelKey": "claude-3-7-sonnet", "displayName": "Claude 3.7 Sonnet", "family": "claude", "metadata": { "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-3-7-sonnet", "modelKey": "anthropic/claude-3-7-sonnet", "displayName": "Claude Sonnet 3.7", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-01", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "heroku", "model": "heroku/claude-3-7-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-3-7-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-7-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-3-7-sonnet-20250219", "provider": "anthropic", "model": "claude-3-7-sonnet-20250219", "displayName": "Claude Sonnet 3.7", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "anthropic", "llmgateway" ], "aliases": [ "abacus/claude-3-7-sonnet-20250219", "anthropic/claude-3-7-sonnet-20250219", "llmgateway/claude-3-7-sonnet-20250219" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "claude-3-7-sonnet-20250219", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-3-7-sonnet-20250219", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-3-7-sonnet-20250219", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-3-7-sonnet-20250219", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 3.7" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "deprecationDate": "2026-02-19", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-3-7-sonnet-20250219", "modelKey": "claude-3-7-sonnet-20250219", "displayName": "Claude Sonnet 3.7", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-7-sonnet-20250219", "modelKey": "claude-3-7-sonnet-20250219", "displayName": "Claude Sonnet 3.7", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-3-7-sonnet-20250219", "modelKey": "claude-3-7-sonnet-20250219", "displayName": "Claude Sonnet 3.7", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-3-7-sonnet-20250219", "mode": "chat", "metadata": { "deprecationDate": "2026-02-19" } } ] }, { "id": "anthropic/claude-3-7-sonnet-latest", "provider": "anthropic", "model": "claude-3-7-sonnet-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/anthropic/claude-3-7-sonnet-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-3-7-sonnet-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "input": 3.3, "output": 16.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-3-7-sonnet-latest", "mode": "chat" } ] }, { "id": "anthropic/claude-3-7-sonnet@20250219", "provider": "anthropic", "model": "claude-3-7-sonnet@20250219", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-3-7-sonnet@20250219" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-7-sonnet@20250219", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-7-sonnet@20250219", "mode": "chat", "metadata": { "deprecationDate": "2026-05-11" } } ] }, { "id": "anthropic/claude-3-haiku", "provider": "anthropic", "model": "claude-3-haiku", "displayName": "Claude 3 Haiku", "family": "claude", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "kilo", "openrouter", "vercel", "vercel_ai_gateway", "vertex_ai-anthropic_models" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3-haiku", "kilo/anthropic/claude-3-haiku", "openrouter/anthropic/claude-3-haiku", "vercel/anthropic/claude-3-haiku", "vercel_ai_gateway/anthropic/claude-3-haiku", "vertex_ai-anthropic_models/vertex_ai/claude-3-haiku" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false, "assistantPrefill": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-3-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-3-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-3-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-3-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.25 }, "perImage": { "input": 0.0004 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-3-haiku", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 3 Haiku", "Claude 3 Haiku", "Claude Haiku 3" ], "families": [ "claude", "claude-haiku" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-13", "lastUpdated": "2024-03-13", "supportedParameters": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3-haiku", "modelKey": "anthropic/claude-3-haiku", "displayName": "Claude Haiku 3", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "openWeights": false, "releaseDate": "2024-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-3-haiku", "modelKey": "anthropic/claude-3-haiku", "displayName": "Anthropic: Claude 3 Haiku", "metadata": { "lastUpdated": "2024-03-07", "openWeights": false, "releaseDate": "2024-03-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-3-haiku", "modelKey": "anthropic/claude-3-haiku", "displayName": "Claude 3 Haiku", "family": "claude", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "openWeights": false, "releaseDate": "2024-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-3-haiku", "modelKey": "anthropic/claude-3-haiku", "displayName": "Claude Haiku 3", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "openWeights": false, "releaseDate": "2024-03-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-3-haiku", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-haiku", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-haiku", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-3-haiku", "displayName": "Anthropic: Claude 3 Haiku", "metadata": { "canonicalSlug": "anthropic/claude-3-haiku", "createdAt": "2024-03-13T00:00:00.000Z", "knowledgeCutoff": "2023-08-31", "links": { "details": "/api/v1/models/anthropic/claude-3-haiku/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "anthropic/claude-3-haiku-20240307", "provider": "anthropic", "model": "claude-3-haiku-20240307", "displayName": "Claude Haiku 3", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anthropic", "helicone" ], "aliases": [ "anthropic/claude-3-haiku-20240307", "helicone/claude-3-haiku-20240307" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-3-haiku-20240307", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-3-haiku-20240307", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-3-haiku-20240307", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 3 Haiku", "Claude Haiku 3" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-13", "lastUpdated": "2024-03-13", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-haiku-20240307", "modelKey": "claude-3-haiku-20240307", "displayName": "Claude Haiku 3", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "openWeights": false, "releaseDate": "2024-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-3-haiku-20240307", "modelKey": "claude-3-haiku-20240307", "displayName": "Anthropic: Claude 3 Haiku", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-03-07", "openWeights": false, "releaseDate": "2024-03-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-3-haiku-20240307", "mode": "chat" } ] }, { "id": "anthropic/claude-3-haiku@20240307", "provider": "anthropic", "model": "claude-3-haiku@20240307", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-3-haiku@20240307" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-haiku@20240307", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-haiku@20240307", "mode": "chat" } ] }, { "id": "anthropic/claude-3-opus", "provider": "anthropic", "model": "claude-3-opus", "displayName": "Claude Opus 3", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "llmgateway", "vercel_ai_gateway", "vertex_ai-anthropic_models" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3-opus", "llmgateway/claude-3-opus", "vercel_ai_gateway/anthropic/claude-3-opus", "vertex_ai-anthropic_models/vertex_ai/claude-3-opus" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "assistantPrefill": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-3-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude 3 Opus", "Claude Opus 3" ], "families": [ "claude", "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-02-29", "lastUpdated": "2024-02-29", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3-opus", "modelKey": "anthropic/claude-3-opus", "displayName": "Claude Opus 3", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-02-29", "openWeights": false, "releaseDate": "2024-02-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-3-opus", "modelKey": "claude-3-opus", "displayName": "Claude 3 Opus", "family": "claude", "metadata": { "lastUpdated": "2024-03-04", "openWeights": false, "releaseDate": "2024-03-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3-opus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-opus", "mode": "chat" } ] }, { "id": "anthropic/claude-3-opus-20240229", "provider": "anthropic", "model": "claude-3-opus-20240229", "displayName": "Claude Opus 3", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-3-opus-20240229" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-3-opus-20240229", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-3-opus-20240229", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "displayNames": [ "Claude Opus 3" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-02-29", "lastUpdated": "2024-02-29", "deprecationDate": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-opus-20240229", "modelKey": "claude-3-opus-20240229", "displayName": "Claude Opus 3", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-02-29", "openWeights": false, "releaseDate": "2024-02-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-3-opus-20240229", "mode": "chat", "metadata": { "deprecationDate": "2026-05-01" } } ] }, { "id": "anthropic/claude-3-opus@20240229", "provider": "anthropic", "model": "claude-3-opus@20240229", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-3-opus@20240229" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-opus@20240229", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-opus@20240229", "mode": "chat" } ] }, { "id": "anthropic/claude-3-sonnet", "provider": "anthropic", "model": "claude-3-sonnet", "displayName": "Claude Sonnet 3", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "vertex_ai-anthropic_models" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3-sonnet", "vertex_ai-anthropic_models/vertex_ai/claude-3-sonnet" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 3" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-04", "lastUpdated": "2024-03-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3-sonnet", "modelKey": "anthropic/claude-3-sonnet", "displayName": "Claude Sonnet 3", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-04", "openWeights": false, "releaseDate": "2024-03-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-3-sonnet-20240229", "provider": "anthropic", "model": "claude-3-sonnet-20240229", "displayName": "Claude Sonnet 3", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-3-sonnet-20240229" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-3-sonnet-20240229", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 0.3, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 3" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-04", "lastUpdated": "2024-03-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-3-sonnet-20240229", "modelKey": "claude-3-sonnet-20240229", "displayName": "Claude Sonnet 3", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-04", "openWeights": false, "releaseDate": "2024-03-04" } } ] }, { "id": "anthropic/claude-3-sonnet@20240229", "provider": "anthropic", "model": "claude-3-sonnet@20240229", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-3-sonnet@20240229" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-sonnet@20240229", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-3-sonnet@20240229", "mode": "chat" } ] }, { "id": "anthropic/claude-3.5-haiku", "provider": "anthropic", "model": "claude-3.5-haiku", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "helicone", "kilo", "openrouter", "qiniu-ai", "replicate", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3.5-haiku", "helicone/claude-3.5-haiku", "kilo/anthropic/claude-3.5-haiku", "openrouter/anthropic/claude-3.5-haiku", "qiniu-ai/claude-3.5-haiku", "replicate/anthropic/claude-3.5-haiku", "vercel/anthropic/claude-3.5-haiku", "vercel_ai_gateway/anthropic/claude-3.5-haiku", "zenmux/anthropic/claude-3.5-haiku" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.7999999999999999, "output": 4 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-3.5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-3.5-haiku", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 3.5 Haiku", "Claude 3.5 Haiku", "Claude Haiku 3.5", "Claude Haiku 3.5 (latest)" ], "families": [ "claude", "claude-haiku" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "supportedParameters": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3.5-haiku", "modelKey": "anthropic/claude-3.5-haiku", "displayName": "Claude Haiku 3.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-3.5-haiku", "modelKey": "claude-3.5-haiku", "displayName": "Anthropic: Claude 3.5 Haiku", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-3.5-haiku", "modelKey": "anthropic/claude-3.5-haiku", "displayName": "Anthropic: Claude 3.5 Haiku", "metadata": { "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-3.5-haiku", "modelKey": "anthropic/claude-3.5-haiku", "displayName": "Claude 3.5 Haiku", "family": "claude", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-11-04", "openWeights": false, "releaseDate": "2024-11-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-3.5-haiku", "modelKey": "claude-3.5-haiku", "displayName": "Claude 3.5 Haiku", "metadata": { "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-3.5-haiku", "modelKey": "anthropic/claude-3.5-haiku", "displayName": "Claude Haiku 3.5", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-3.5-haiku", "modelKey": "anthropic/claude-3.5-haiku", "displayName": "Claude 3.5 Haiku", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2024-11-04", "openWeights": false, "releaseDate": "2024-11-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-3.5-haiku", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.5-haiku", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-3.5-haiku", "displayName": "Anthropic: Claude 3.5 Haiku", "metadata": { "canonicalSlug": "anthropic/claude-3-5-haiku", "createdAt": "2024-11-04T00:00:00.000Z", "knowledgeCutoff": "2024-07-31", "links": { "details": "/api/v1/models/anthropic/claude-3-5-haiku/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 8192, "is_moderated": true } } } ] }, { "id": "anthropic/claude-3.5-sonnet", "provider": "anthropic", "model": "claude-3.5-sonnet", "displayName": "Claude Sonnet 3.5 v2", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "openrouter", "qiniu-ai", "replicate", "vercel_ai_gateway" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-3.5-sonnet", "openrouter/anthropic/claude-3.5-sonnet", "qiniu-ai/claude-3.5-sonnet", "replicate/anthropic/claude-3.5-sonnet", "vercel_ai_gateway/anthropic/claude-3.5-sonnet" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8200, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "promptCaching": true, "responseSchema": true, "systemMessages": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-3.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-3.5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-3.5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.75, "output": 18.75 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude 3.5 Sonnet", "Claude Sonnet 3.5 v2" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-3.5-sonnet", "modelKey": "anthropic/claude-3.5-sonnet", "displayName": "Claude Sonnet 3.5 v2", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-3.5-sonnet", "modelKey": "claude-3.5-sonnet", "displayName": "Claude 3.5 Sonnet", "metadata": { "lastUpdated": "2025-09-09", "openWeights": false, "releaseDate": "2025-09-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-3.5-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-3.5-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.5-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-3.5-sonnet-v2", "provider": "anthropic", "model": "claude-3.5-sonnet-v2", "displayName": "Anthropic: Claude 3.5 Sonnet v2", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/claude-3.5-sonnet-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "claude-3.5-sonnet-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.30000000000000004, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 3.5 Sonnet v2" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-3.5-sonnet-v2", "modelKey": "claude-3.5-sonnet-v2", "displayName": "Anthropic: Claude 3.5 Sonnet v2", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } } ] }, { "id": "anthropic/claude-3.7-sonnet", "provider": "anthropic", "model": "claude-3.7-sonnet", "displayName": "Anthropic: Claude 3.7 Sonnet", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "helicone", "openrouter", "qiniu-ai", "replicate", "vercel_ai_gateway", "zenmux" ], "aliases": [ "helicone/claude-3.7-sonnet", "openrouter/anthropic/claude-3.7-sonnet", "qiniu-ai/claude-3.7-sonnet", "replicate/anthropic/claude-3.7-sonnet", "vercel_ai_gateway/anthropic/claude-3.7-sonnet", "zenmux/anthropic/claude-3.7-sonnet" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "promptCaching": true, "responseSchema": true, "systemMessages": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "claude-3.7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.30000000000000004, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-3.7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-3.7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "perImage": { "input": 0.0048 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-3.7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 3.7 Sonnet", "Claude 3.7 Sonnet" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02", "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-3.7-sonnet", "modelKey": "claude-3.7-sonnet", "displayName": "Anthropic: Claude 3.7 Sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-02", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-3.7-sonnet", "modelKey": "claude-3.7-sonnet", "displayName": "Claude 3.7 Sonnet", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-3.7-sonnet", "modelKey": "anthropic/claude-3.7-sonnet", "displayName": "Claude 3.7 Sonnet", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-3.7-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-3.7-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-3.7-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-4-5-sonnet", "provider": "anthropic", "model": "claude-4-5-sonnet", "displayName": "Claude 4.5 Sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-4-5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-4-5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.259, "output": 16.296 } } ] }, "metadata": { "displayNames": [ "Claude 4.5 Sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-4-5-sonnet", "modelKey": "claude-4-5-sonnet", "displayName": "Claude 4.5 Sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } } ] }, { "id": "anthropic/claude-4-6-sonnet", "provider": "anthropic", "model": "claude-4-6-sonnet", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-4-6-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-4-6-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.59, "output": 17.92 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-4-6-sonnet", "modelKey": "claude-4-6-sonnet", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "anthropic/claude-4-opus", "provider": "anthropic", "model": "claude-4-opus", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra", "snowflake", "vercel_ai_gateway" ], "aliases": [ "deepinfra/anthropic/claude-4-opus", "snowflake/claude-4-opus", "vercel_ai_gateway/anthropic/claude-4-opus" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-4-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 16.5, "output": 82.5 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-4-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-4-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-4-opus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-4-opus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-4-opus", "mode": "chat" } ] }, { "id": "anthropic/claude-4-opus-20250514", "provider": "anthropic", "model": "claude-4-opus-20250514", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-4-opus-20250514" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anthropic", "model": "claude-4-opus-20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-4-opus-20250514", "mode": "chat" } ] }, { "id": "anthropic/claude-4-sonnet", "provider": "anthropic", "model": "claude-4-sonnet", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra", "heroku", "replicate", "snowflake", "vercel_ai_gateway" ], "aliases": [ "deepinfra/anthropic/claude-4-sonnet", "heroku/claude-4-sonnet", "replicate/anthropic/claude-4-sonnet", "snowflake/claude-4-sonnet", "vercel_ai_gateway/anthropic/claude-4-sonnet" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "systemMessages": true, "parallelFunctionCalling": true, "promptCaching": true, "responseSchema": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-4-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.3, "output": 16.5 } }, { "source": "litellm", "provider": "heroku", "model": "heroku/claude-4-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-4-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-4-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-4-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/anthropic/claude-4-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "heroku", "model": "heroku/claude-4-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-4-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-4-sonnet", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-4-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-4-sonnet-20250514", "provider": "anthropic", "model": "claude-4-sonnet-20250514", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-4-sonnet-20250514" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anthropic", "model": "claude-4-sonnet-20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-4-sonnet-20250514", "mode": "chat" } ] }, { "id": "anthropic/claude-4.0-opus", "provider": "anthropic", "model": "claude-4.0-opus", "displayName": "Claude 4.0 Opus", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/claude-4.0-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Claude 4.0 Opus" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.0-opus", "modelKey": "claude-4.0-opus", "displayName": "Claude 4.0 Opus", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "anthropic/claude-4.0-sonnet", "provider": "anthropic", "model": "claude-4.0-sonnet", "displayName": "Claude 4.0 Sonnet", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/claude-4.0-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Claude 4.0 Sonnet" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.0-sonnet", "modelKey": "claude-4.0-sonnet", "displayName": "Claude 4.0 Sonnet", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "anthropic/claude-4.1-opus", "provider": "anthropic", "model": "claude-4.1-opus", "displayName": "Claude 4.1 Opus", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/claude-4.1-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Claude 4.1 Opus" ], "releaseDate": "2025-08-06", "lastUpdated": "2025-08-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.1-opus", "modelKey": "claude-4.1-opus", "displayName": "Claude 4.1 Opus", "metadata": { "lastUpdated": "2025-08-06", "openWeights": false, "releaseDate": "2025-08-06" } } ] }, { "id": "anthropic/claude-4.5-haiku", "provider": "anthropic", "model": "claude-4.5-haiku", "displayName": "Anthropic: Claude 4.5 Haiku", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "helicone", "qiniu-ai", "replicate" ], "aliases": [ "helicone/claude-4.5-haiku", "qiniu-ai/claude-4.5-haiku", "replicate/anthropic/claude-4.5-haiku" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "claude-4.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09999999999999999, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-4.5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 4.5 Haiku", "Claude 4.5 Haiku" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-10", "releaseDate": "2025-10-01", "lastUpdated": "2025-10-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-4.5-haiku", "modelKey": "claude-4.5-haiku", "displayName": "Anthropic: Claude 4.5 Haiku", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2025-10-01", "openWeights": false, "releaseDate": "2025-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.5-haiku", "modelKey": "claude-4.5-haiku", "displayName": "Claude 4.5 Haiku", "metadata": { "lastUpdated": "2025-10-16", "openWeights": false, "releaseDate": "2025-10-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-4.5-haiku", "mode": "chat" } ] }, { "id": "anthropic/claude-4.5-opus", "provider": "anthropic", "model": "claude-4.5-opus", "displayName": "Anthropic: Claude Opus 4.5", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "helicone", "qiniu-ai" ], "aliases": [ "helicone/claude-4.5-opus", "qiniu-ai/claude-4.5-opus" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "claude-4.5-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.5", "Claude 4.5 Opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-11", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-4.5-opus", "modelKey": "claude-4.5-opus", "displayName": "Anthropic: Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.5-opus", "modelKey": "claude-4.5-opus", "displayName": "Claude 4.5 Opus", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } } ] }, { "id": "anthropic/claude-4.5-sonnet", "provider": "anthropic", "model": "claude-4.5-sonnet", "displayName": "Anthropic: Claude Sonnet 4.5", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "helicone", "qiniu-ai", "replicate" ], "aliases": [ "helicone/claude-4.5-sonnet", "qiniu-ai/claude-4.5-sonnet", "replicate/anthropic/claude-4.5-sonnet" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "claude-4.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.30000000000000004, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/anthropic/claude-4.5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Sonnet 4.5", "Claude 4.5 Sonnet" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-4.5-sonnet", "modelKey": "claude-4.5-sonnet", "displayName": "Anthropic: Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "claude-4.5-sonnet", "modelKey": "claude-4.5-sonnet", "displayName": "Claude 4.5 Sonnet", "metadata": { "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/anthropic/claude-4.5-sonnet", "mode": "chat" } ] }, { "id": "anthropic/claude-code", "provider": "anthropic", "model": "claude-code", "displayName": "claude-code", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/poetools/claude-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "claude-code" ], "releaseDate": "2025-11-27", "lastUpdated": "2025-11-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "poetools/claude-code", "modelKey": "poetools/claude-code", "displayName": "claude-code", "metadata": { "lastUpdated": "2025-11-27", "openWeights": false, "releaseDate": "2025-11-27" } } ] }, { "id": "anthropic/claude-fable-5", "provider": "anthropic", "model": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anthropic", "azure", "azure_ai", "cloudflare-ai-gateway", "freemodel", "github-copilot", "opencode", "openrouter", "snowflake-cortex", "venice", "vertex_ai-anthropic_models", "zenmux" ], "aliases": [ "anthropic/claude-fable-5", "azure/claude-fable-5", "azure_ai/claude-fable-5", "cloudflare-ai-gateway/anthropic/claude-fable-5", "freemodel/claude-fable-5", "github-copilot/claude-fable-5", "opencode/claude-fable-5", "openrouter/anthropic/claude-fable-5", "snowflake-cortex/claude-fable-5", "venice/claude-fable-5", "vertex_ai-anthropic_models/vertex_ai/claude-fable-5", "zenmux/anthropic/claude-fable-5" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "adaptiveThinking": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "azure", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "github-copilot", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "models.dev", "provider": "venice", "model": "claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.2, "cacheWrite": 15, "input": 12, "output": 60 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-fable-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-fable-5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Fable 5", "Claude Fable 5" ], "families": [ "claude-fable" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-fable-5", "modelKey": "anthropic/claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-fable-5", "modelKey": "claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-06-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-fable-5", "modelKey": "anthropic/claude-fable-5", "displayName": "Claude Fable 5", "family": "claude-fable", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-fable-5", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1 } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-fable-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-fable-5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-fable-5", "displayName": "Anthropic: Claude Fable 5", "metadata": { "canonicalSlug": "anthropic/claude-5-fable-20260609", "createdAt": "2026-06-09T12:18:35.000Z", "links": { "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-fable-5@default", "provider": "anthropic", "model": "claude-fable-5@default", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-anthropic_models" ], "aliases": [ "vertex_ai-anthropic_models/vertex_ai/claude-fable-5@default" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-fable-5@default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-fable-5@default", "mode": "chat" } ] }, { "id": "anthropic/claude-fable-latest", "provider": "anthropic", "model": "claude-fable-latest", "displayName": "Claude Fable Latest", "family": "claude-fable", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/~anthropic/claude-fable-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "~anthropic/claude-fable-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "openrouter", "provider": "openrouter", "model": "~anthropic/claude-fable-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Fable Latest", "Claude Fable Latest" ], "families": [ "claude-fable" ], "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~anthropic/claude-fable-latest", "modelKey": "~anthropic/claude-fable-latest", "displayName": "Claude Fable Latest", "family": "claude-fable", "metadata": { "lastUpdated": "2026-06-09", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~anthropic/claude-fable-latest", "displayName": "Anthropic: Claude Fable Latest", "metadata": { "canonicalSlug": "~anthropic/claude-fable-latest", "createdAt": "2026-06-09T18:32:24.000Z", "links": { "details": "/api/v1/models/~anthropic/claude-fable-latest/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Router", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-haiku-3", "provider": "anthropic", "model": "claude-haiku-3", "displayName": "Claude-Haiku-3", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/anthropic/claude-haiku-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 189096, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-haiku-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.021, "cacheWrite": 0.26, "input": 0.21, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "Claude-Haiku-3" ], "families": [ "claude-haiku" ], "releaseDate": "2024-03-09", "lastUpdated": "2024-03-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-haiku-3", "modelKey": "anthropic/claude-haiku-3", "displayName": "Claude-Haiku-3", "family": "claude-haiku", "metadata": { "lastUpdated": "2024-03-09", "openWeights": false, "releaseDate": "2024-03-09" } } ] }, { "id": "anthropic/claude-haiku-3.5", "provider": "anthropic", "model": "claude-haiku-3.5", "displayName": "Claude-Haiku-3.5", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/anthropic/claude-haiku-3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 189096, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-haiku-3.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.068, "cacheWrite": 0.85, "input": 0.68, "output": 3.4 } } ] }, "metadata": { "displayNames": [ "Claude-Haiku-3.5" ], "families": [ "claude-haiku" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-haiku-3.5", "modelKey": "anthropic/claude-haiku-3.5", "displayName": "Claude-Haiku-3.5", "family": "claude-haiku", "metadata": { "lastUpdated": "2024-10-01", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "anthropic/claude-haiku-4-5", "provider": "anthropic", "model": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "anthropic", "anyapi", "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "cortecs", "frogbot", "llmgateway", "nearai", "neon", "opencode", "perplexity-agent", "requesty", "snowflake", "snowflake-cortex", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-haiku-4-5", "anthropic/claude-haiku-4-5", "anyapi/anthropic/claude-haiku-4-5", "azure-cognitive-services/claude-haiku-4-5", "azure/claude-haiku-4-5", "azure_ai/claude-haiku-4-5", "cloudflare-ai-gateway/anthropic/claude-haiku-4-5", "cortecs/claude-haiku-4-5", "frogbot/claude-haiku-4-5", "llmgateway/claude-haiku-4-5", "nearai/anthropic/claude-haiku-4-5", "neon/claude-haiku-4-5", "opencode/claude-haiku-4-5", "perplexity-agent/anthropic/claude-haiku-4-5", "requesty/anthropic/claude-haiku-4-5", "snowflake-cortex/claude-haiku-4-5", "snowflake/claude-haiku-4-5", "vertex_ai-anthropic_models/vertex_ai/claude-haiku-4-5" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true, "systemMessages": true, "nativeStreaming": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "azure", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "cortecs", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.09, "output": 5.43 } }, { "source": "models.dev", "provider": "frogbot", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "nearai", "model": "anthropic/claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "neon", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5", "Claude Haiku 4.5 (latest)", "claude-haiku-4-5" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-16", "lastUpdated": "2025-10-16", "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "claude-haiku-4-5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-16", "openWeights": false, "releaseDate": "2025-10-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "anthropic/claude-haiku-4-5", "modelKey": "anthropic/claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-haiku-4-5", "modelKey": "anthropic/claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "anthropic/claude-haiku-4-5", "modelKey": "anthropic/claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-haiku-4-5", "modelKey": "anthropic/claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-haiku-4-5", "modelKey": "anthropic/claude-haiku-4-5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-01", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-haiku-4-5", "modelKey": "claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-haiku-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-haiku-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-haiku-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-haiku-4-5", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5" } } ] }, { "id": "anthropic/claude-haiku-4-5-20251001", "provider": "anthropic", "model": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "freemodel", "helicone", "jiekou", "llmgateway", "merge-gateway", "nano-gpt", "qihang-ai" ], "aliases": [ "302ai/claude-haiku-4-5-20251001", "abacus/claude-haiku-4-5-20251001", "anthropic/claude-haiku-4-5-20251001", "freemodel/claude-haiku-4-5-20251001", "helicone/claude-haiku-4-5-20251001", "jiekou/claude-haiku-4-5-20251001", "llmgateway/claude-haiku-4-5-20251001", "merge-gateway/anthropic/claude-haiku-4-5-20251001", "nano-gpt/claude-haiku-4-5-20251001", "qihang-ai/claude-haiku-4-5-20251001" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09999999999999999, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 4.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.71 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-haiku-4-5-20251001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude 4.5 Haiku (20251001)", "Claude Haiku 4.5", "claude-haiku-4-5-20251001" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-16", "lastUpdated": "2025-10-16", "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "claude-haiku-4-5-20251001", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-16", "openWeights": false, "releaseDate": "2025-10-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Anthropic: Claude 4.5 Haiku (20251001)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2025-10-01", "openWeights": false, "releaseDate": "2025-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "claude-haiku-4-5-20251001", "family": "claude-haiku", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-haiku-4-5-20251001", "modelKey": "anthropic/claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "claude-haiku-4-5-20251001", "modelKey": "claude-haiku-4-5-20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-10-01", "openWeights": false, "releaseDate": "2025-10-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-haiku-4-5-20251001", "mode": "chat" } ] }, { "id": "anthropic/claude-haiku-4-5-20251001-thinking", "provider": "anthropic", "model": "claude-haiku-4-5-20251001-thinking", "displayName": "Claude Haiku 4.5 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-haiku-4-5-20251001-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-haiku-4-5-20251001-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 Thinking" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-haiku-4-5-20251001-thinking", "modelKey": "claude-haiku-4-5-20251001-thinking", "displayName": "Claude Haiku 4.5 Thinking", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } } ] }, { "id": "anthropic/claude-haiku-4-5@20251001", "provider": "anthropic", "model": "claude-haiku-4-5@20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-haiku-4-5@20251001", "google-vertex/claude-haiku-4-5@20251001", "vertex_ai-anthropic_models/vertex_ai/claude-haiku-4-5@20251001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-haiku-4-5@20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-haiku-4-5@20251001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-haiku-4-5@20251001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-haiku-4-5@20251001", "modelKey": "claude-haiku-4-5@20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-haiku-4-5@20251001", "modelKey": "claude-haiku-4-5@20251001", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-haiku-4-5@20251001", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5" } } ] }, { "id": "anthropic/claude-haiku-4.5", "provider": "anthropic", "model": "claude-haiku-4.5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github-copilot", "github_copilot", "kilo", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "github-copilot/claude-haiku-4.5", "github_copilot/claude-haiku-4.5", "kilo/anthropic/claude-haiku-4.5", "openrouter/anthropic/claude-haiku-4.5", "orcarouter/anthropic/claude-haiku-4.5", "poe/anthropic/claude-haiku-4.5", "vercel/anthropic/claude-haiku-4.5", "vercel_ai_gateway/anthropic/claude-haiku-4.5", "zenmux/anthropic/claude-haiku-4.5" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-copilot", "model": "claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.085, "cacheWrite": 1.1, "input": 0.85, "output": 4.3 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-haiku-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-haiku-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-haiku-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-haiku-4.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Haiku 4.5", "Claude Haiku 4.5", "Claude Haiku 4.5 (latest)", "Claude-Haiku-4.5" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-haiku-4.5", "modelKey": "claude-haiku-4.5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Anthropic: Claude Haiku 4.5", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Claude-Haiku-4.5", "family": "claude-haiku", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-haiku-4.5", "modelKey": "anthropic/claude-haiku-4.5", "displayName": "Claude Haiku 4.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-haiku-4.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-haiku-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-haiku-4.5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-haiku-4.5", "displayName": "Anthropic: Claude Haiku 4.5", "metadata": { "canonicalSlug": "anthropic/claude-4.5-haiku-20251001", "createdAt": "2025-10-15T17:00:38.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 64000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-haiku-latest", "provider": "anthropic", "model": "claude-haiku-latest", "displayName": "Anthropic: Claude Haiku Latest", "family": "claude-haiku", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/~anthropic/claude-haiku-latest", "nano-gpt/anthropic/claude-haiku-latest", "openrouter/~anthropic/claude-haiku-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~anthropic/claude-haiku-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-haiku-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 5 } }, { "source": "models.dev", "provider": "openrouter", "model": "~anthropic/claude-haiku-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "openrouter", "provider": "openrouter", "model": "~anthropic/claude-haiku-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic Claude Haiku Latest", "Anthropic: Claude Haiku Latest", "Claude Haiku Latest" ], "families": [ "claude-haiku" ], "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~anthropic/claude-haiku-latest", "modelKey": "~anthropic/claude-haiku-latest", "displayName": "Anthropic: Claude Haiku Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-haiku-latest", "modelKey": "anthropic/claude-haiku-latest", "displayName": "Claude Haiku Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~anthropic/claude-haiku-latest", "modelKey": "~anthropic/claude-haiku-latest", "displayName": "Anthropic Claude Haiku Latest", "family": "claude-haiku", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~anthropic/claude-haiku-latest", "displayName": "Anthropic Claude Haiku Latest", "metadata": { "canonicalSlug": "~anthropic/claude-haiku-latest", "createdAt": "2026-04-27T19:34:52.000Z", "links": { "details": "/api/v1/models/~anthropic/claude-haiku-latest/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Router", "topProvider": { "context_length": 200000, "max_completion_tokens": 64000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-opus-4", "provider": "anthropic", "model": "claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "gmi", "helicone", "kilo", "openrouter", "orcarouter", "poe", "requesty", "vercel", "vercel_ai_gateway", "vertex_ai-anthropic_models", "zenmux" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-opus-4", "gmi/anthropic/claude-opus-4", "helicone/claude-opus-4", "kilo/anthropic/claude-opus-4", "openrouter/anthropic/claude-opus-4", "orcarouter/anthropic/claude-opus-4", "poe/anthropic/claude-opus-4", "requesty/anthropic/claude-opus-4", "vercel/anthropic/claude-opus-4", "vercel_ai_gateway/anthropic/claude-opus-4", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4", "zenmux/anthropic/claude-opus-4" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 409600, "inputTokens": 409600, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.3, "cacheWrite": 16, "input": 13, "output": 64 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/anthropic/claude-opus-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "perImage": { "input": 0.0048 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4", "Claude Opus 4", "Claude Opus 4 (latest)", "Claude-Opus-4" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-opus-4", "modelKey": "claude-opus-4", "displayName": "Anthropic: Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-14", "openWeights": false, "releaseDate": "2025-05-14", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Anthropic: Claude Opus 4", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude-Opus-4", "family": "claude-opus", "metadata": { "lastUpdated": "2025-05-21", "openWeights": false, "releaseDate": "2025-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4", "modelKey": "anthropic/claude-opus-4", "displayName": "Claude Opus 4", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/anthropic/claude-opus-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4", "displayName": "Anthropic: Claude Opus 4", "metadata": { "canonicalSlug": "anthropic/claude-4-opus-20250522", "createdAt": "2025-05-22T16:27:25.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/anthropic/claude-4-opus-20250522/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 32000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus-4-0", "provider": "anthropic", "model": "claude-opus-4-0", "displayName": "Claude Opus 4 (latest)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-opus-4-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4 (latest)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-0", "modelKey": "claude-opus-4-0", "displayName": "Claude Opus 4 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "anthropic/claude-opus-4-1", "provider": "anthropic", "model": "claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anthropic", "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "helicone", "neon", "opencode", "requesty", "vertex_ai-anthropic_models" ], "aliases": [ "anthropic/claude-opus-4-1", "azure-cognitive-services/claude-opus-4-1", "azure/claude-opus-4-1", "azure_ai/claude-opus-4-1", "cloudflare-ai-gateway/anthropic/claude-opus-4-1", "helicone/claude-opus-4-1", "neon/claude-opus-4-1", "opencode/claude-opus-4-1", "requesty/anthropic/claude-opus-4-1", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-1" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "azure", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "neon", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token_batches": 0.0000375 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.1", "Claude Opus 4.1", "Claude Opus 4.1 (latest)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4-1", "modelKey": "anthropic/claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Anthropic: Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-opus-4-1", "modelKey": "claude-opus-4-1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-opus-4-1", "modelKey": "anthropic/claude-opus-4-1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-1", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-1-20250805", "provider": "anthropic", "model": "claude-opus-4-1-20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "helicone", "jiekou", "llmgateway", "merge-gateway", "nano-gpt" ], "aliases": [ "302ai/claude-opus-4-1-20250805", "abacus/claude-opus-4-1-20250805", "anthropic/claude-opus-4-1-20250805", "helicone/claude-opus-4-1-20250805", "jiekou/claude-opus-4-1-20250805", "llmgateway/claude-opus-4-1-20250805", "merge-gateway/anthropic/claude-opus-4-1-20250805", "nano-gpt/claude-opus-4-1-20250805" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 13.5, "output": 67.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-1-20250805", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.1 (20250805)", "Claude 4.1 Opus", "Claude Opus 4.1", "claude-opus-4-1-20250805" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "deprecationDate": "2026-08-05", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "claude-opus-4-1-20250805", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "Anthropic: Claude Opus 4.1 (20250805)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "claude-opus-4-1-20250805", "family": "claude-opus", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-opus-4-1-20250805", "modelKey": "anthropic/claude-opus-4-1-20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-20250805", "modelKey": "claude-opus-4-1-20250805", "displayName": "Claude 4.1 Opus", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-1-20250805", "mode": "chat", "metadata": { "deprecationDate": "2026-08-05" } } ] }, { "id": "anthropic/claude-opus-4-1-20250805-thinking", "provider": "anthropic", "model": "claude-opus-4-1-20250805-thinking", "displayName": "claude-opus-4-1-20250805-thinking", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/claude-opus-4-1-20250805-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-1-20250805-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "claude-opus-4-1-20250805-thinking" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-05-27", "lastUpdated": "2025-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-1-20250805-thinking", "modelKey": "claude-opus-4-1-20250805-thinking", "displayName": "claude-opus-4-1-20250805-thinking", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-05-27", "openWeights": false, "releaseDate": "2025-05-27" } } ] }, { "id": "anthropic/claude-opus-4-1-thinking", "provider": "anthropic", "model": "claude-opus-4-1-thinking", "displayName": "Claude 4.1 Opus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-1-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4.1 Opus Thinking" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-thinking", "modelKey": "claude-opus-4-1-thinking", "displayName": "Claude 4.1 Opus Thinking", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-1-thinking:1024", "provider": "anthropic", "model": "claude-opus-4-1-thinking:1024", "displayName": "Claude 4.1 Opus Thinking (1K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-1-thinking:1024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-thinking:1024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4.1 Opus Thinking (1K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-thinking:1024", "modelKey": "claude-opus-4-1-thinking:1024", "displayName": "Claude 4.1 Opus Thinking (1K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-1-thinking:32000", "provider": "anthropic", "model": "claude-opus-4-1-thinking:32000", "displayName": "Claude 4.1 Opus Thinking (32K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-1-thinking:32000" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-thinking:32000", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4.1 Opus Thinking (32K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-thinking:32000", "modelKey": "claude-opus-4-1-thinking:32000", "displayName": "Claude 4.1 Opus Thinking (32K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-1-thinking:32768", "provider": "anthropic", "model": "claude-opus-4-1-thinking:32768", "displayName": "Claude 4.1 Opus Thinking (32K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-1-thinking:32768" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-thinking:32768", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4.1 Opus Thinking (32K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-thinking:32768", "modelKey": "claude-opus-4-1-thinking:32768", "displayName": "Claude 4.1 Opus Thinking (32K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-1-thinking:8192", "provider": "anthropic", "model": "claude-opus-4-1-thinking:8192", "displayName": "Claude 4.1 Opus Thinking (8K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-1-thinking:8192" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-1-thinking:8192", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4.1 Opus Thinking (8K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-1-thinking:8192", "modelKey": "claude-opus-4-1-thinking:8192", "displayName": "Claude 4.1 Opus Thinking (8K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-1@20250805", "provider": "anthropic", "model": "claude-opus-4-1@20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4-1@20250805", "google-vertex/claude-opus-4-1@20250805", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-1@20250805" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4-1@20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4-1@20250805", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-1@20250805", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token_batches": 0.0000375 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.1" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4-1@20250805", "modelKey": "claude-opus-4-1@20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4-1@20250805", "modelKey": "claude-opus-4-1@20250805", "displayName": "Claude Opus 4.1", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-1@20250805", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-20250514", "provider": "anthropic", "model": "claude-opus-4-20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "jiekou", "llmgateway", "merge-gateway", "nano-gpt" ], "aliases": [ "302ai/claude-opus-4-20250514", "abacus/claude-opus-4-20250514", "anthropic/claude-opus-4-20250514", "jiekou/claude-opus-4-20250514", "llmgateway/claude-opus-4-20250514", "merge-gateway/anthropic/claude-opus-4-20250514", "nano-gpt/claude-opus-4-20250514" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 13.5, "output": 67.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus", "Claude Opus 4", "claude-opus-4-20250514" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "deprecationDate": "2026-05-14", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "claude-opus-4-20250514", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "lastUpdated": "2025-05-14", "openWeights": false, "releaseDate": "2025-05-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "claude-opus-4-20250514", "family": "claude-opus", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-opus-4-20250514", "modelKey": "anthropic/claude-opus-4-20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-20250514", "modelKey": "claude-opus-4-20250514", "displayName": "Claude 4 Opus", "metadata": { "lastUpdated": "2025-05-14", "openWeights": false, "releaseDate": "2025-05-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-20250514", "mode": "chat", "metadata": { "deprecationDate": "2026-05-14" } } ] }, { "id": "anthropic/claude-opus-4-5", "provider": "anthropic", "model": "claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "anthropic", "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "neon", "opencode", "perplexity-agent", "requesty", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-opus-4-5", "anthropic/claude-opus-4-5", "azure-cognitive-services/claude-opus-4-5", "azure/claude-opus-4-5", "azure_ai/claude-opus-4-5", "cloudflare-ai-gateway/anthropic/claude-opus-4-5", "neon/claude-opus-4-5", "opencode/claude-opus-4-5", "perplexity-agent/anthropic/claude-opus-4-5", "requesty/anthropic/claude-opus-4-5", "venice/claude-opus-4-5", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-5" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "azure", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "neon", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "cacheWrite": 7.5, "input": 6, "output": 30 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5", "Claude Opus 4.5 (latest)", "claude-opus-4-5" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-25", "lastUpdated": "2025-11-25", "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "claude-opus-4-5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4-5", "modelKey": "anthropic/claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-opus-4-5", "modelKey": "anthropic/claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-opus-4-5", "modelKey": "anthropic/claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-5", "modelKey": "claude-opus-4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2025-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-5", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-5-20251101", "provider": "anthropic", "model": "claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "jiekou", "llmgateway", "merge-gateway", "nano-gpt", "qihang-ai" ], "aliases": [ "302ai/claude-opus-4-5-20251101", "abacus/claude-opus-4-5-20251101", "anthropic/claude-opus-4-5-20251101", "jiekou/claude-opus-4-5-20251101", "llmgateway/claude-opus-4-5-20251101", "merge-gateway/anthropic/claude-opus-4-5-20251101", "nano-gpt/claude-opus-4-5-20251101", "qihang-ai/claude-opus-4-5-20251101" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.5, "output": 22.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.71, "output": 3.57 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-5-20251101", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude 4.5 Opus", "Claude Opus 4.5", "claude-opus-4-5-20251101" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-25", "lastUpdated": "2025-11-25", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "claude-opus-4-5-20251101", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "claude-opus-4-5-20251101", "family": "claude-opus", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-opus-4-5-20251101", "modelKey": "anthropic/claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "Claude 4.5 Opus", "metadata": { "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "claude-opus-4-5-20251101", "modelKey": "claude-opus-4-5-20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-5-20251101", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-5-20251101-thinking", "provider": "anthropic", "model": "claude-opus-4-5-20251101-thinking", "displayName": "claude-opus-4-5-20251101-thinking", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/claude-opus-4-5-20251101-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-5-20251101-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "claude-opus-4-5-20251101-thinking" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-11-25", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-5-20251101-thinking", "modelKey": "claude-opus-4-5-20251101-thinking", "displayName": "claude-opus-4-5-20251101-thinking", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } } ] }, { "id": "anthropic/claude-opus-4-5-20251101:thinking", "provider": "anthropic", "model": "claude-opus-4-5-20251101:thinking", "displayName": "Claude 4.5 Opus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-5-20251101:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-5-20251101:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.5 Opus Thinking" ], "releaseDate": "2025-11-01", "lastUpdated": "2025-11-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-5-20251101:thinking", "modelKey": "claude-opus-4-5-20251101:thinking", "displayName": "Claude 4.5 Opus Thinking", "metadata": { "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } } ] }, { "id": "anthropic/claude-opus-4-5@20251101", "provider": "anthropic", "model": "claude-opus-4-5@20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4-5@20251101", "google-vertex/claude-opus-4-5@20251101", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-5@20251101" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4-5@20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4-5@20251101", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-5@20251101", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-01", "lastUpdated": "2025-11-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4-5@20251101", "modelKey": "claude-opus-4-5@20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4-5@20251101", "modelKey": "claude-opus-4-5@20251101", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-5@20251101", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-6", "provider": "anthropic", "model": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "aihubmix", "anthropic", "anyapi", "auriko", "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "freemodel", "frogbot", "jiekou", "llmgateway", "merge-gateway", "nearai", "neon", "opencode", "perplexity-agent", "requesty", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-opus-4-6", "abacus/claude-opus-4-6", "aihubmix/claude-opus-4-6", "anthropic/claude-opus-4-6", "anyapi/anthropic/claude-opus-4-6", "auriko/claude-opus-4-6", "azure-cognitive-services/claude-opus-4-6", "azure/claude-opus-4-6", "azure_ai/claude-opus-4-6", "cloudflare-ai-gateway/anthropic/claude-opus-4-6", "freemodel/claude-opus-4-6", "frogbot/claude-opus-4-6", "jiekou/claude-opus-4-6", "llmgateway/claude-opus-4-6", "merge-gateway/anthropic/claude-opus-4-6", "nearai/anthropic/claude-opus-4-6", "neon/claude-opus-4-6", "opencode/claude-opus-4-6", "perplexity-agent/anthropic/claude-opus-4-6", "requesty/anthropic/claude-opus-4-6", "venice/claude-opus-4-6", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-6" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "adaptiveThinking": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "interleaved": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "aihubmix", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "auriko", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "azure", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "frogbot", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "nearai", "model": "anthropic/claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "neon", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "cacheWrite": 7.5, "input": 6, "output": 30 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6", "Claude Opus 4.6 (latest)", "claude-opus-4-6" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-06", "lastUpdated": "2026-03-13", "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "claude-opus-4-6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "claude-opus-4-6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02", "openWeights": false, "releaseDate": "2026-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-opus-4-6", "modelKey": "anthropic/claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-6", "modelKey": "claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-6", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1, "fast": 6 } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-6", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-6-20260205", "provider": "anthropic", "model": "claude-opus-4-6-20260205", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-opus-4-6-20260205" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-6-20260205", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-6-20260205", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1, "fast": 6 } } } ] }, { "id": "anthropic/claude-opus-4-6-fast", "provider": "anthropic", "model": "claude-opus-4-6-fast", "displayName": "Claude Opus 4.6 Fast", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/claude-opus-4-6-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-6-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3.6, "cacheWrite": 45, "input": 36, "output": 180 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6 Fast" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-04-08", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-6-fast", "modelKey": "claude-opus-4-6-fast", "displayName": "Claude Opus 4.6 Fast", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-08" } } ] }, { "id": "anthropic/claude-opus-4-6-think", "provider": "anthropic", "model": "claude-opus-4-6-think", "displayName": "Claude Opus 4.6 Thinking", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/claude-opus-4-6-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "claude-opus-4-6-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6 Thinking" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-opus-4-6-think", "modelKey": "claude-opus-4-6-think", "displayName": "Claude Opus 4.6 Thinking", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus-4-6-thinking", "provider": "anthropic", "model": "claude-opus-4-6-thinking", "displayName": "claude-opus-4-6-thinking", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/claude-opus-4-6-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-6-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "claude-opus-4-6-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-02-06", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-6-thinking", "modelKey": "claude-opus-4-6-thinking", "displayName": "claude-opus-4-6-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-06" } } ] }, { "id": "anthropic/claude-opus-4-6@default", "provider": "anthropic", "model": "claude-opus-4-6@default", "displayName": "Claude Opus 4.6", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4-6@default", "google-vertex/claude-opus-4-6@default", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-6@default" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4-6@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4-6@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-6@default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4-6@default", "modelKey": "claude-opus-4-6@default", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4-6@default", "modelKey": "claude-opus-4-6@default", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-6@default", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-7", "provider": "anthropic", "model": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "aihubmix", "anthropic", "anyapi", "auriko", "azure_ai", "cloudflare-ai-gateway", "freemodel", "frogbot", "llmgateway", "merge-gateway", "nearai", "neon", "opencode", "perplexity-agent", "snowflake-cortex", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-opus-4-7", "aihubmix/claude-opus-4-7", "anthropic/claude-opus-4-7", "anyapi/anthropic/claude-opus-4-7", "auriko/claude-opus-4-7", "azure_ai/claude-opus-4-7", "cloudflare-ai-gateway/anthropic/claude-opus-4-7", "freemodel/claude-opus-4-7", "frogbot/claude-opus-4-7", "llmgateway/claude-opus-4-7", "merge-gateway/anthropic/claude-opus-4-7", "nearai/anthropic/claude-opus-4-7", "neon/claude-opus-4-7", "opencode/claude-opus-4-7", "perplexity-agent/anthropic/claude-opus-4-7", "snowflake-cortex/claude-opus-4-7", "venice/claude-opus-4-7", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-7" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "adaptiveThinking": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true, "interleaved": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "aihubmix", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "auriko", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "frogbot", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "nearai", "model": "anthropic/claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "neon", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "cacheWrite": 7.5, "input": 6, "output": 30 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7", "claude-opus-4-7" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "claude-opus-4-7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "anthropic/claude-opus-4-7", "modelKey": "anthropic/claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4-7", "modelKey": "anthropic/claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-opus-4-7", "modelKey": "anthropic/claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "anthropic/claude-opus-4-7", "modelKey": "anthropic/claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-opus-4-7", "modelKey": "anthropic/claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "status": "beta", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-7", "modelKey": "claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-7", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1, "fast": 6 } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-7", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-7", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-7-20260416", "provider": "anthropic", "model": "claude-opus-4-7-20260416", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-opus-4-7-20260416" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-7-20260416", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-7-20260416", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1, "fast": 6 } } } ] }, { "id": "anthropic/claude-opus-4-7-fast", "provider": "anthropic", "model": "claude-opus-4-7-fast", "displayName": "Claude Opus 4.7 Fast", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/claude-opus-4-7-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-7-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3.6, "cacheWrite": 45, "input": 36, "output": 180 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 Fast" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-05-14", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-7-fast", "modelKey": "claude-opus-4-7-fast", "displayName": "Claude Opus 4.7 Fast", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-14" } } ] }, { "id": "anthropic/claude-opus-4-7-think", "provider": "anthropic", "model": "claude-opus-4-7-think", "displayName": "Claude Opus 4.7 Thinking", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/claude-opus-4-7-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "claude-opus-4-7-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7 Thinking" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-opus-4-7-think", "modelKey": "claude-opus-4-7-think", "displayName": "Claude Opus 4.7 Thinking", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "anthropic/claude-opus-4-7@default", "provider": "anthropic", "model": "claude-opus-4-7@default", "displayName": "Claude Opus 4.7", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4-7@default", "google-vertex/claude-opus-4-7@default", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-7@default" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4-7@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4-7@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-7@default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4-7@default", "modelKey": "claude-opus-4-7@default", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4-7@default", "modelKey": "claude-opus-4-7@default", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-7@default", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-8", "provider": "anthropic", "model": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anthropic", "azure_ai", "cloudflare-ai-gateway", "freemodel", "llmgateway", "opencode", "snowflake-cortex", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "anthropic/claude-opus-4-8", "azure_ai/claude-opus-4-8", "cloudflare-ai-gateway/anthropic/claude-opus-4-8", "freemodel/claude-opus-4-8", "llmgateway/claude-opus-4-8", "opencode/claude-opus-4-8", "snowflake-cortex/claude-opus-4-8", "venice/claude-opus-4-8", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-8" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "adaptiveThinking": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "cacheWrite": 7.5, "input": 6, "output": 30 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-opus-4-8", "modelKey": "anthropic/claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-8", "modelKey": "claude-opus-4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-opus-4-8", "mode": "chat", "metadata": { "providerSpecificEntry": { "us": 1.1, "fast": 2 } } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-opus-4-8", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-8", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-8-fast", "provider": "anthropic", "model": "claude-opus-4-8-fast", "displayName": "Claude Opus 4.8 Fast", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/claude-opus-4-8-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "claude-opus-4-8-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.2, "cacheWrite": 15, "input": 12, "output": 60 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 Fast" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-opus-4-8-fast", "modelKey": "claude-opus-4-8-fast", "displayName": "Claude Opus 4.8 Fast", "family": "claude-opus", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-28" } } ] }, { "id": "anthropic/claude-opus-4-8@default", "provider": "anthropic", "model": "claude-opus-4-8@default", "displayName": "Claude Opus 4.8", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4-8@default", "google-vertex/claude-opus-4-8@default", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-8@default" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "adaptiveThinking": true, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4-8@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4-8@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-8@default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4-8@default", "modelKey": "claude-opus-4-8@default", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4-8@default", "modelKey": "claude-opus-4-8@default", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4-8@default", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-4-thinking", "provider": "anthropic", "model": "claude-opus-4-thinking", "displayName": "Claude 4 Opus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus Thinking" ], "releaseDate": "2025-07-15", "lastUpdated": "2025-07-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-thinking", "modelKey": "claude-opus-4-thinking", "displayName": "Claude 4 Opus Thinking", "metadata": { "lastUpdated": "2025-07-15", "openWeights": false, "releaseDate": "2025-07-15" } } ] }, { "id": "anthropic/claude-opus-4-thinking:1024", "provider": "anthropic", "model": "claude-opus-4-thinking:1024", "displayName": "Claude 4 Opus Thinking (1K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-thinking:1024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-thinking:1024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus Thinking (1K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-thinking:1024", "modelKey": "claude-opus-4-thinking:1024", "displayName": "Claude 4 Opus Thinking (1K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-thinking:32000", "provider": "anthropic", "model": "claude-opus-4-thinking:32000", "displayName": "Claude 4 Opus Thinking (32K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-thinking:32000" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-thinking:32000", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus Thinking (32K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-thinking:32000", "modelKey": "claude-opus-4-thinking:32000", "displayName": "Claude 4 Opus Thinking (32K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-thinking:32768", "provider": "anthropic", "model": "claude-opus-4-thinking:32768", "displayName": "Claude 4 Opus Thinking (32K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-thinking:32768" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-thinking:32768", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus Thinking (32K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-thinking:32768", "modelKey": "claude-opus-4-thinking:32768", "displayName": "Claude 4 Opus Thinking (32K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4-thinking:8192", "provider": "anthropic", "model": "claude-opus-4-thinking:8192", "displayName": "Claude 4 Opus Thinking (8K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-opus-4-thinking:8192" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-opus-4-thinking:8192", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 75.004 } } ] }, "metadata": { "displayNames": [ "Claude 4 Opus Thinking (8K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-opus-4-thinking:8192", "modelKey": "claude-opus-4-thinking:8192", "displayName": "Claude 4 Opus Thinking (8K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-opus-4.1", "provider": "anthropic", "model": "claude-opus-4.1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fastrouter", "kilo", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "fastrouter/anthropic/claude-opus-4.1", "kilo/anthropic/claude-opus-4.1", "openrouter/anthropic/claude-opus-4.1", "orcarouter/anthropic/claude-opus-4.1", "poe/anthropic/claude-opus-4.1", "vercel/anthropic/claude-opus-4.1", "vercel_ai_gateway/anthropic/claude-opus-4.1", "zenmux/anthropic/claude-opus-4.1" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.3, "cacheWrite": 16, "input": 13, "output": 64 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "perImage": { "input": 0.0048 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.1", "Claude Opus 4.1", "Claude Opus 4.1 (latest)", "Claude-Opus-4.1" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Anthropic: Claude Opus 4.1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 31999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude-Opus-4.1", "family": "claude-opus", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4.1", "modelKey": "anthropic/claude-opus-4.1", "displayName": "Claude Opus 4.1", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.1", "displayName": "Anthropic: Claude Opus 4.1", "metadata": { "canonicalSlug": "anthropic/claude-4.1-opus-20250805", "createdAt": "2025-08-05T16:33:11.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 32000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus-4.5", "provider": "anthropic", "model": "claude-opus-4.5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github-copilot", "github_copilot", "gmi", "kilo", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "github-copilot/claude-opus-4.5", "github_copilot/claude-opus-4.5", "gmi/anthropic/claude-opus-4.5", "kilo/anthropic/claude-opus-4.5", "openrouter/anthropic/claude-opus-4.5", "orcarouter/anthropic/claude-opus-4.5", "poe/anthropic/claude-opus-4.5", "vercel/anthropic/claude-opus-4.5", "vercel_ai_gateway/anthropic/claude-opus-4.5", "zenmux/anthropic/claude-opus-4.5" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 409600, "inputTokens": 409600, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-copilot", "model": "claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.43, "cacheWrite": 5.3, "input": 4.3, "output": 21 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-opus-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/anthropic/claude-opus-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.5", "Claude Opus 4.5", "Claude Opus 4.5 (latest)", "Claude-Opus-4.5" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "verbosity" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-opus-4.5", "modelKey": "claude-opus-4.5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Anthropic: Claude Opus 4.5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Claude-Opus-4.5", "family": "claude-opus", "metadata": { "lastUpdated": "2025-11-21", "openWeights": false, "releaseDate": "2025-11-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2024-11-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4.5", "modelKey": "anthropic/claude-opus-4.5", "displayName": "Claude Opus 4.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-opus-4.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/anthropic/claude-opus-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.5", "displayName": "Anthropic: Claude Opus 4.5", "metadata": { "canonicalSlug": "anthropic/claude-4.5-opus-20251124", "createdAt": "2025-11-24T18:56:20.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 200000, "max_completion_tokens": 64000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-opus-4.6", "provider": "anthropic", "model": "claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github-copilot", "gmicloud", "kilo", "nano-gpt", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "github-copilot/claude-opus-4.6", "gmicloud/anthropic/claude-opus-4.6", "kilo/anthropic/claude-opus-4.6", "kilo/stealth/claude-opus-4.6", "nano-gpt/anthropic/claude-opus-4.6", "openrouter/anthropic/claude-opus-4.6", "orcarouter/anthropic/claude-opus-4.6", "poe/anthropic/claude-opus-4.6", "vercel/anthropic/claude-opus-4.6", "vercel_ai_gateway/anthropic/claude-opus-4.6", "zenmux/anthropic/claude-opus-4.6" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": true, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-copilot", "model": "claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "gmicloud", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "kilo", "model": "stealth/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "cacheWrite": 5, "input": 4, "output": 20 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.43, "cacheWrite": 5.3, "input": 4.3, "output": 21 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.6", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.6", "Claude 4.6 Opus", "Claude Opus 4.6", "Claude-Opus-4.6", "Stealth: Claude Opus 4.6 (20% off)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-opus-4.6", "modelKey": "claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Anthropic: Claude Opus 4.6", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "stealth/claude-opus-4.6", "modelKey": "stealth/claude-opus-4.6", "displayName": "Stealth: Claude Opus 4.6 (20% off)", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude 4.6 Opus", "family": "claude-opus", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude-Opus-4.6", "metadata": { "lastUpdated": "2026-02-04", "openWeights": false, "releaseDate": "2026-02-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4.6", "modelKey": "anthropic/claude-opus-4.6", "displayName": "Claude Opus 4.6", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-06", "openWeights": false, "releaseDate": "2026-02-06", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-opus-4.6", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.6", "displayName": "Anthropic: Claude Opus 4.6", "metadata": { "canonicalSlug": "anthropic/claude-4.6-opus-20260205", "createdAt": "2026-02-04T15:30:50.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" }, "reasoning": { "mandatory": false, "supports_max_tokens": true }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus-4.6-fast", "provider": "anthropic", "model": "claude-opus-4.6-fast", "displayName": "Anthropic: Claude Opus 4.6 (Fast)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github_copilot", "kilo", "openrouter" ], "aliases": [ "github_copilot/claude-opus-4.6-fast", "kilo/anthropic/claude-opus-4.6-fast", "openrouter/anthropic/claude-opus-4.6-fast" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 128000, "maxTokens": 16000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.6-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.6-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-opus-4.6-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.6-fast", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.6 (Fast)", "Claude Opus 4.6 (Fast)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-04-07", "lastUpdated": "2026-04-11", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p", "verbosity" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.6-fast", "modelKey": "anthropic/claude-opus-4.6-fast", "displayName": "Anthropic: Claude Opus 4.6 (Fast)", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.6-fast", "modelKey": "anthropic/claude-opus-4.6-fast", "displayName": "Claude Opus 4.6 (Fast)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-04-07", "openWeights": false, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-opus-4.6-fast", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.6-fast", "displayName": "Anthropic: Claude Opus 4.6 (Fast)", "metadata": { "canonicalSlug": "anthropic/claude-4.6-opus-fast-20260407", "createdAt": "2026-04-07T20:07:52.000Z", "expirationDate": "2026-06-29", "links": { "details": "/api/v1/models/anthropic/claude-4.6-opus-fast-20260407/endpoints" }, "reasoning": { "mandatory": false, "supports_max_tokens": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-opus-4.6:thinking", "provider": "anthropic", "model": "claude-opus-4.6:thinking", "displayName": "Claude 4.6 Opus Thinking", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.6:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.6:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.6 Opus Thinking" ], "families": [ "claude-opus" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.6:thinking", "modelKey": "anthropic/claude-opus-4.6:thinking", "displayName": "Claude 4.6 Opus Thinking", "family": "claude-opus", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus-4.6:thinking:low", "provider": "anthropic", "model": "claude-opus-4.6:thinking:low", "displayName": "Claude 4.6 Opus Thinking Low", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.6:thinking:low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.6:thinking:low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.6 Opus Thinking Low" ], "families": [ "claude-opus" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.6:thinking:low", "modelKey": "anthropic/claude-opus-4.6:thinking:low", "displayName": "Claude 4.6 Opus Thinking Low", "family": "claude-opus", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus-4.6:thinking:max", "provider": "anthropic", "model": "claude-opus-4.6:thinking:max", "displayName": "Claude 4.6 Opus Thinking Max", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.6:thinking:max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.6:thinking:max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.6 Opus Thinking Max" ], "families": [ "claude-opus" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.6:thinking:max", "modelKey": "anthropic/claude-opus-4.6:thinking:max", "displayName": "Claude 4.6 Opus Thinking Max", "family": "claude-opus", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus-4.6:thinking:medium", "provider": "anthropic", "model": "claude-opus-4.6:thinking:medium", "displayName": "Claude 4.6 Opus Thinking Medium", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.6:thinking:medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.6:thinking:medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.6 Opus Thinking Medium" ], "families": [ "claude-opus" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.6:thinking:medium", "modelKey": "anthropic/claude-opus-4.6:thinking:medium", "displayName": "Claude 4.6 Opus Thinking Medium", "family": "claude-opus", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus-4.7", "provider": "anthropic", "model": "claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github-copilot", "gmicloud", "kilo", "nano-gpt", "openrouter", "orcarouter", "poe", "vercel", "zenmux" ], "aliases": [ "github-copilot/claude-opus-4.7", "gmicloud/anthropic/claude-opus-4.7", "kilo/anthropic/claude-opus-4.7", "kilo/stealth/claude-opus-4.7", "nano-gpt/anthropic/claude-opus-4.7", "openrouter/anthropic/claude-opus-4.7", "orcarouter/anthropic/claude-opus-4.7", "poe/anthropic/claude-opus-4.7", "vercel/anthropic/claude-opus-4.7", "zenmux/anthropic/claude-opus-4.7" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 1048576, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true, "parallelFunctionCalling": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-copilot", "model": "claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "gmicloud", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.45, "input": 4.5, "output": 22.5 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "kilo", "model": "stealth/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "cacheWrite": 5, "input": 4, "output": 20 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4998, "input": 4.998, "output": 25.007 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 1, "cache_write": 12.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.43, "cacheWrite": 5.4, "input": 4.3, "output": 21 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.7", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.7", "Claude 4.7 Opus", "Claude Opus 4.7", "Claude-Opus-4.7", "Stealth: Claude Opus 4.7 (20% off)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-opus-4.7", "modelKey": "claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Anthropic: Claude Opus 4.7", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "stealth/claude-opus-4.7", "modelKey": "stealth/claude-opus-4.7", "displayName": "Stealth: Claude Opus 4.7 (20% off)", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude 4.7 Opus", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude-Opus-4.7", "metadata": { "lastUpdated": "2026-04-15", "openWeights": false, "releaseDate": "2026-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4.7", "modelKey": "anthropic/claude-opus-4.7", "displayName": "Claude Opus 4.7", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-opus-4.7", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.7", "displayName": "Anthropic: Claude Opus 4.7", "metadata": { "canonicalSlug": "anthropic/claude-4.7-opus-20260416", "createdAt": "2026-04-16T14:51:40.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus-4.7-fast", "provider": "anthropic", "model": "claude-opus-4.7-fast", "displayName": "Anthropic: Claude Opus 4.7 (Fast)", "family": "claude-opus", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/anthropic/claude-opus-4.7-fast", "openrouter/anthropic/claude-opus-4.7-fast" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-opus-4.7-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.7-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.7-fast", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "cacheWrite": 37.5, "input": 30, "output": 150 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.7 (Fast)", "Claude Opus 4.7 (Fast)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-16", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-opus-4.7-fast", "modelKey": "anthropic/claude-opus-4.7-fast", "displayName": "Anthropic: Claude Opus 4.7 (Fast)", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-05-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.7-fast", "modelKey": "anthropic/claude-opus-4.7-fast", "displayName": "Claude Opus 4.7 (Fast)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.7-fast", "displayName": "Anthropic: Claude Opus 4.7 (Fast)", "metadata": { "canonicalSlug": "anthropic/claude-4.7-opus-fast-20260512", "createdAt": "2026-05-12T19:10:11.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-opus-4.7:thinking", "provider": "anthropic", "model": "claude-opus-4.7:thinking", "displayName": "Claude 4.7 Opus Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.7:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.7:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4998, "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude 4.7 Opus Thinking" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.7:thinking", "modelKey": "anthropic/claude-opus-4.7:thinking", "displayName": "Claude 4.7 Opus Thinking", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "anthropic/claude-opus-4.8", "provider": "anthropic", "model": "claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "sources": [ "models.dev", "openrouter" ], "providers": [ "fastrouter", "github-copilot", "nano-gpt", "openrouter", "poe", "vercel", "zenmux" ], "aliases": [ "fastrouter/anthropic/claude-opus-4.8", "github-copilot/claude-opus-4.8", "nano-gpt/anthropic/claude-opus-4.8", "openrouter/anthropic/claude-opus-4.8", "poe/anthropic/claude-opus-4.8", "vercel/anthropic/claude-opus-4.8", "zenmux/anthropic/claude-opus-4.8" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 1048576, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "github-copilot", "model": "claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4998, "input": 4.998, "output": 25.007 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.2929, "output": 21.4646 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.8", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.8", "Claude Opus 4.8", "Claude-Opus-4.8" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-opus-4.8", "modelKey": "claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude Opus 4.8", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude-Opus-4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-opus-4.8", "modelKey": "anthropic/claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.8", "displayName": "Anthropic: Claude Opus 4.8", "metadata": { "canonicalSlug": "anthropic/claude-4.8-opus-20260528", "createdAt": "2026-05-27T18:04:51.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus-4.8-fast", "provider": "anthropic", "model": "claude-opus-4.8-fast", "displayName": "Claude Opus 4.8 (Fast)", "family": "claude-opus", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/anthropic/claude-opus-4.8-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-opus-4.8-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-opus-4.8-fast", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus 4.8 (Fast)", "Claude Opus 4.8 (Fast)" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-27", "lastUpdated": "2026-05-27", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-opus-4.8-fast", "modelKey": "anthropic/claude-opus-4.8-fast", "displayName": "Claude Opus 4.8 (Fast)", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-05-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-opus-4.8-fast", "displayName": "Anthropic: Claude Opus 4.8 (Fast)", "metadata": { "canonicalSlug": "anthropic/claude-4.8-opus-fast-20260528", "createdAt": "2026-05-27T20:28:23.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.8-opus-fast-20260528/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-opus-4.8:thinking", "provider": "anthropic", "model": "claude-opus-4.8:thinking", "displayName": "Claude Opus 4.8 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-opus-4.8:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-4.8:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4998, "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8 Thinking" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-4.8:thinking", "modelKey": "anthropic/claude-opus-4.8:thinking", "displayName": "Claude Opus 4.8 Thinking", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } } ] }, { "id": "anthropic/claude-opus-4@20250514", "provider": "anthropic", "model": "claude-opus-4@20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-opus-4@20250514", "google-vertex/claude-opus-4@20250514", "vertex_ai-anthropic_models/vertex_ai/claude-opus-4@20250514" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-opus-4@20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-opus-4@20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4@20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00003 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-opus-4@20250514", "modelKey": "claude-opus-4@20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-opus-4@20250514", "modelKey": "claude-opus-4@20250514", "displayName": "Claude Opus 4", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-opus-4@20250514", "mode": "chat" } ] }, { "id": "anthropic/claude-opus-41", "provider": "anthropic", "model": "claude-opus-41", "mode": "chat", "sources": [ "litellm" ], "providers": [ "github_copilot" ], "aliases": [ "github_copilot/claude-opus-41" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 80000, "inputTokens": 80000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-opus-41", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-opus-41", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "anthropic/claude-opus-latest", "provider": "anthropic", "model": "claude-opus-latest", "displayName": "Anthropic: Claude Opus Latest", "family": "claude-opus", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/~anthropic/claude-opus-latest", "nano-gpt/anthropic/claude-opus-latest", "openrouter/~anthropic/claude-opus-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~anthropic/claude-opus-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-opus-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4998, "input": 4.998, "output": 25.007 } }, { "source": "models.dev", "provider": "openrouter", "model": "~anthropic/claude-opus-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "openrouter", "provider": "openrouter", "model": "~anthropic/claude-opus-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Opus Latest", "Claude Opus Latest" ], "families": [ "claude-opus" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~anthropic/claude-opus-latest", "modelKey": "~anthropic/claude-opus-latest", "displayName": "Anthropic: Claude Opus Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-opus-latest", "modelKey": "anthropic/claude-opus-latest", "displayName": "Claude Opus Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~anthropic/claude-opus-latest", "modelKey": "~anthropic/claude-opus-latest", "displayName": "Claude Opus Latest", "family": "claude-opus", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~anthropic/claude-opus-latest", "displayName": "Anthropic: Claude Opus Latest", "metadata": { "canonicalSlug": "~anthropic/claude-opus-latest", "createdAt": "2026-04-21T18:16:01.000Z", "links": { "details": "/api/v1/models/~anthropic/claude-opus-latest/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity" ], "tokenizer": "Router", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-opus4-5", "provider": "anthropic", "model": "claude-opus4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-opus4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-opus4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5.98, "output": 29.89 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-opus4-5", "modelKey": "claude-opus4-5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } } ] }, { "id": "anthropic/claude-opus4-6", "provider": "anthropic", "model": "claude-opus4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-opus4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-opus4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5.98, "output": 29.89 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-opus4-6", "modelKey": "claude-opus4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "anthropic/claude-opus4-7", "provider": "anthropic", "model": "claude-opus4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-opus4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-opus4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.56, "cacheWrite": 6.99, "input": 5.6, "output": 27.99 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-opus4-7", "modelKey": "claude-opus4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "anthropic/claude-opus4-8", "provider": "anthropic", "model": "claude-opus4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/claude-opus4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "claude-opus4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.563, "cacheWrite": 7.049, "input": 5.64, "output": 28.198 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-opus4-8", "modelKey": "claude-opus4-8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } } ] }, { "id": "anthropic/claude-sonnet-3.5", "provider": "anthropic", "model": "claude-sonnet-3.5", "displayName": "Claude-Sonnet-3.5", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/anthropic/claude-sonnet-3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 189096, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-3.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } } ] }, "metadata": { "displayNames": [ "Claude-Sonnet-3.5" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "releaseDate": "2024-06-05", "lastUpdated": "2024-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-3.5", "modelKey": "anthropic/claude-sonnet-3.5", "displayName": "Claude-Sonnet-3.5", "family": "claude-sonnet", "status": "deprecated", "metadata": { "lastUpdated": "2024-06-05", "openWeights": false, "releaseDate": "2024-06-05" } } ] }, { "id": "anthropic/claude-sonnet-3.5-june", "provider": "anthropic", "model": "claude-sonnet-3.5-june", "displayName": "Claude-Sonnet-3.5-June", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/anthropic/claude-sonnet-3.5-june" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 189096, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-3.5-june", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } } ] }, "metadata": { "displayNames": [ "Claude-Sonnet-3.5-June" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "releaseDate": "2024-11-18", "lastUpdated": "2024-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-3.5-june", "modelKey": "anthropic/claude-sonnet-3.5-june", "displayName": "Claude-Sonnet-3.5-June", "family": "claude-sonnet", "status": "deprecated", "metadata": { "lastUpdated": "2024-11-18", "openWeights": false, "releaseDate": "2024-11-18" } } ] }, { "id": "anthropic/claude-sonnet-3.7", "provider": "anthropic", "model": "claude-sonnet-3.7", "displayName": "Claude-Sonnet-3.7", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/anthropic/claude-sonnet-3.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 196608, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-3.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } } ] }, "metadata": { "displayNames": [ "Claude-Sonnet-3.7" ], "families": [ "claude-sonnet" ], "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-3.7", "modelKey": "anthropic/claude-sonnet-3.7", "displayName": "Claude-Sonnet-3.7", "family": "claude-sonnet", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } } ] }, { "id": "anthropic/claude-sonnet-4", "provider": "anthropic", "model": "claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "cortecs", "fastrouter", "github-copilot", "github_copilot", "gmi", "helicone", "kilo", "neon", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "vercel_ai_gateway", "vertex_ai-anthropic_models", "zenmux" ], "aliases": [ "cloudflare-ai-gateway/anthropic/claude-sonnet-4", "cortecs/claude-sonnet-4", "fastrouter/anthropic/claude-sonnet-4", "github-copilot/claude-sonnet-4", "github_copilot/claude-sonnet-4", "gmi/anthropic/claude-sonnet-4", "helicone/claude-sonnet-4", "kilo/anthropic/claude-sonnet-4", "neon/claude-sonnet-4", "opencode/claude-sonnet-4", "openrouter/anthropic/claude-sonnet-4", "orcarouter/anthropic/claude-sonnet-4", "poe/anthropic/claude-sonnet-4", "requesty/anthropic/claude-sonnet-4", "vercel/anthropic/claude-sonnet-4", "vercel_ai_gateway/anthropic/claude-sonnet-4", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4", "zenmux/anthropic/claude-sonnet-4" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "cortecs", "model": "claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.307, "output": 16.536 } }, { "source": "models.dev", "provider": "fastrouter", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "github-copilot", "model": "claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.30000000000000004, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "neon", "model": "claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/anthropic/claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "perImage": { "input": 0.0048 }, "extra": { "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-sonnet-4", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Sonnet 4", "Claude Sonnet 4", "Claude Sonnet 4 (latest)", "Claude Sonnet 4.5", "Claude-Sonnet-4" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "claude-sonnet-4", "modelKey": "claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-sonnet-4", "modelKey": "claude-sonnet-4", "displayName": "Claude Sonnet 4 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-sonnet-4", "modelKey": "claude-sonnet-4", "displayName": "Anthropic: Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-14", "openWeights": false, "releaseDate": "2025-05-14", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Anthropic: Claude Sonnet 4", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-sonnet-4", "modelKey": "claude-sonnet-4", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-sonnet-4", "modelKey": "claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude-Sonnet-4", "family": "claude-sonnet", "metadata": { "lastUpdated": "2025-05-21", "openWeights": false, "releaseDate": "2025-05-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-sonnet-4", "modelKey": "anthropic/claude-sonnet-4", "displayName": "Claude Sonnet 4", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-sonnet-4", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/anthropic/claude-sonnet-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-sonnet-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-sonnet-4", "displayName": "Anthropic: Claude Sonnet 4", "metadata": { "canonicalSlug": "anthropic/claude-4-sonnet-20250522", "createdAt": "2025-05-22T16:12:51.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 64000, "is_moderated": false } } } ] }, { "id": "anthropic/claude-sonnet-4-0", "provider": "anthropic", "model": "claude-sonnet-4-0", "displayName": "Claude Sonnet 4 (latest)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "anthropic" ], "aliases": [ "anthropic/claude-sonnet-4-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "anthropic", "model": "claude-sonnet-4-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4 (latest)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-sonnet-4-0", "modelKey": "claude-sonnet-4-0", "displayName": "Claude Sonnet 4 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } } ] }, { "id": "anthropic/claude-sonnet-4-20250514", "provider": "anthropic", "model": "claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "jiekou", "llmgateway", "merge-gateway", "nano-gpt" ], "aliases": [ "302ai/claude-sonnet-4-20250514", "abacus/claude-sonnet-4-20250514", "anthropic/claude-sonnet-4-20250514", "jiekou/claude-sonnet-4-20250514", "llmgateway/claude-sonnet-4-20250514", "merge-gateway/anthropic/claude-sonnet-4-20250514", "nano-gpt/claude-sonnet-4-20250514" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.7, "output": 13.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-sonnet-4-20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet", "Claude Sonnet 4", "claude-sonnet-4-20250514" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "deprecationDate": "2026-05-14", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "claude-sonnet-4-20250514", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "lastUpdated": "2025-05-14", "openWeights": false, "releaseDate": "2025-05-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "claude-sonnet-4-20250514", "family": "claude-sonnet", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-sonnet-4-20250514", "modelKey": "anthropic/claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-20250514", "modelKey": "claude-sonnet-4-20250514", "displayName": "Claude 4 Sonnet", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-sonnet-4-20250514", "mode": "chat", "metadata": { "deprecationDate": "2026-05-14" } } ] }, { "id": "anthropic/claude-sonnet-4-5", "provider": "anthropic", "model": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "anthropic", "anyapi", "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "llmgateway", "nearai", "neon", "opencode", "perplexity-agent", "requesty", "snowflake", "snowflake-cortex", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-sonnet-4-5", "anthropic/claude-sonnet-4-5", "anyapi/anthropic/claude-sonnet-4-5", "azure-cognitive-services/claude-sonnet-4-5", "azure/claude-sonnet-4-5", "azure_ai/claude-sonnet-4-5", "cloudflare-ai-gateway/anthropic/claude-sonnet-4-5", "llmgateway/claude-sonnet-4-5", "nearai/anthropic/claude-sonnet-4-5", "neon/claude-sonnet-4-5", "opencode/claude-sonnet-4-5", "perplexity-agent/anthropic/claude-sonnet-4-5", "requesty/anthropic/claude-sonnet-4-5", "snowflake-cortex/claude-sonnet-4-5", "snowflake/claude-sonnet-4-5", "venice/claude-sonnet-4-5", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-5" ], "mergedProviderModelRecords": 17, "limits": { "contextTokens": 1000000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "structuredOutput": true, "interleaved": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "azure", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nearai", "model": "anthropic/claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15.5 } }, { "source": "models.dev", "provider": "neon", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "venice", "model": "claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.375, "cacheWrite": 4.69, "input": 3.75, "output": 18.75 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.0000075 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5", "Claude Sonnet 4.5 (latest)", "claude-sonnet-4-5" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "claude-sonnet-4-5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "anthropic/claude-sonnet-4-5", "modelKey": "anthropic/claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-sonnet-4-5", "modelKey": "anthropic/claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "anthropic/claude-sonnet-4-5", "modelKey": "anthropic/claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-sonnet-4-5", "modelKey": "anthropic/claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-sonnet-4-5", "modelKey": "anthropic/claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-sonnet-4-5", "modelKey": "claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2025-01-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-sonnet-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-sonnet-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-sonnet-4-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-5", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-5-20250929", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "anthropic", "helicone", "jiekou", "llmgateway", "merge-gateway", "nano-gpt", "qihang-ai" ], "aliases": [ "302ai/claude-sonnet-4-5-20250929", "abacus/claude-sonnet-4-5-20250929", "anthropic/claude-sonnet-4-5-20250929", "helicone/claude-sonnet-4-5-20250929", "jiekou/claude-sonnet-4-5-20250929", "llmgateway/claude-sonnet-4-5-20250929", "merge-gateway/anthropic/claude-sonnet-4-5-20250929", "nano-gpt/claude-sonnet-4-5-20250929", "qihang-ai/claude-sonnet-4-5-20250929" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "helicone", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.30000000000000004, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "jiekou", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.7, "output": 13.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.43, "output": 2.14 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Sonnet 4.5 (20250929)", "Claude Sonnet 4.5", "claude-sonnet-4-5-20250929" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "claude-sonnet-4-5-20250929", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Anthropic: Claude Sonnet 4.5 (20250929)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "claude-sonnet-4-5-20250929", "family": "claude-sonnet", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-sonnet-4-5-20250929", "modelKey": "anthropic/claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "claude-sonnet-4-5-20250929", "modelKey": "claude-sonnet-4-5-20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-5-20250929-thinking", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929-thinking", "displayName": "claude-sonnet-4-5-20250929-thinking", "sources": [ "models.dev" ], "providers": [ "302ai", "nano-gpt" ], "aliases": [ "302ai/claude-sonnet-4-5-20250929-thinking", "nano-gpt/claude-sonnet-4-5-20250929-thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-5-20250929-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-5-20250929-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 Thinking", "claude-sonnet-4-5-20250929-thinking" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-5-20250929-thinking", "modelKey": "claude-sonnet-4-5-20250929-thinking", "displayName": "claude-sonnet-4-5-20250929-thinking", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-5-20250929-thinking", "modelKey": "claude-sonnet-4-5-20250929-thinking", "displayName": "Claude Sonnet 4.5 Thinking", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } } ] }, { "id": "anthropic/claude-sonnet-4-5-20250929-v1:0", "provider": "anthropic", "model": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-5@20250929", "provider": "anthropic", "model": "claude-sonnet-4-5@20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-sonnet-4-5@20250929", "google-vertex/claude-sonnet-4-5@20250929", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-5@20250929" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-sonnet-4-5@20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-sonnet-4-5@20250929", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-5@20250929", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.0000075 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-sonnet-4-5@20250929", "modelKey": "claude-sonnet-4-5@20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-sonnet-4-5@20250929", "modelKey": "claude-sonnet-4-5@20250929", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-5@20250929", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-6", "provider": "anthropic", "model": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "aihubmix", "anthropic", "anyapi", "auriko", "azure", "azure_ai", "cloudflare-ai-gateway", "freemodel", "frogbot", "llmgateway", "merge-gateway", "nearai", "neon", "opencode", "perplexity-agent", "requesty", "snowflake", "snowflake-cortex", "venice", "vertex_ai-anthropic_models" ], "aliases": [ "302ai/claude-sonnet-4-6", "abacus/claude-sonnet-4-6", "aihubmix/claude-sonnet-4-6", "anthropic/claude-sonnet-4-6", "anyapi/anthropic/claude-sonnet-4-6", "auriko/claude-sonnet-4-6", "azure/claude-sonnet-4-6", "azure_ai/claude-sonnet-4-6", "cloudflare-ai-gateway/anthropic/claude-sonnet-4-6", "freemodel/claude-sonnet-4-6", "frogbot/claude-sonnet-4-6", "llmgateway/claude-sonnet-4-6", "merge-gateway/anthropic/claude-sonnet-4-6", "nearai/anthropic/claude-sonnet-4-6", "neon/claude-sonnet-4-6", "opencode/claude-sonnet-4-6", "perplexity-agent/anthropic/claude-sonnet-4-6", "requesty/anthropic/claude-sonnet-4-6", "snowflake-cortex/claude-sonnet-4-6", "snowflake/claude-sonnet-4-6", "venice/claude-sonnet-4-6", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-6" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "adaptiveThinking": true, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "interleaved": true, "structuredOutput": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "abacus", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "aihubmix", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "anthropic", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "auriko", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "azure", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "anthropic/claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "freemodel", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "frogbot", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "anthropic/claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nearai", "model": "anthropic/claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "neon", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "opencode", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "anthropic/claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "requesty", "model": "anthropic/claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "venice", "model": "claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 } }, { "source": "litellm", "provider": "anthropic", "model": "claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6", "claude-sonnet-4-6" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-18", "lastUpdated": "2026-03-13", "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "claude-sonnet-4-6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-18", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anthropic", "providerName": "Anthropic", "providerDoc": "https://docs.anthropic.com/en/docs/about-claude/models", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "anthropic/claude-sonnet-4-6", "modelKey": "anthropic/claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "claude-sonnet-4-6", "modelKey": "claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anthropic", "model": "claude-sonnet-4-6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/claude-sonnet-4-6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/claude-sonnet-4-6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-6-think", "provider": "anthropic", "model": "claude-sonnet-4-6-think", "displayName": "Claude Sonnet 4.6 Thinking", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "aihubmix" ], "aliases": [ "aihubmix/claude-sonnet-4-6-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "claude-sonnet-4-6-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 Thinking" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "claude-sonnet-4-6-think", "modelKey": "claude-sonnet-4-6-think", "displayName": "Claude Sonnet 4.6 Thinking", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "anthropic/claude-sonnet-4-6-thinking", "provider": "anthropic", "model": "claude-sonnet-4-6-thinking", "displayName": "claude-sonnet-4-6-thinking", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/claude-sonnet-4-6-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "claude-sonnet-4-6-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "claude-sonnet-4-6-thinking" ], "knowledgeCutoff": "2025-08", "releaseDate": "2026-02-18", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "claude-sonnet-4-6-thinking", "modelKey": "claude-sonnet-4-6-thinking", "displayName": "claude-sonnet-4-6-thinking", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-18" } } ] }, { "id": "anthropic/claude-sonnet-4-6@default", "provider": "anthropic", "model": "claude-sonnet-4-6@default", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-sonnet-4-6@default", "google-vertex/claude-sonnet-4-6@default", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-6@default" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-sonnet-4-6@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-sonnet-4-6@default", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-6@default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-sonnet-4-6@default", "modelKey": "claude-sonnet-4-6@default", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-sonnet-4-6@default", "modelKey": "claude-sonnet-4-6@default", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4-6@default", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-4-thinking", "provider": "anthropic", "model": "claude-sonnet-4-thinking", "displayName": "Claude 4 Sonnet Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-sonnet-4-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet Thinking" ], "releaseDate": "2025-02-24", "lastUpdated": "2025-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-thinking", "modelKey": "claude-sonnet-4-thinking", "displayName": "Claude 4 Sonnet Thinking", "metadata": { "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24" } } ] }, { "id": "anthropic/claude-sonnet-4-thinking:1024", "provider": "anthropic", "model": "claude-sonnet-4-thinking:1024", "displayName": "Claude 4 Sonnet Thinking (1K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-sonnet-4-thinking:1024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-thinking:1024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet Thinking (1K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-thinking:1024", "modelKey": "claude-sonnet-4-thinking:1024", "displayName": "Claude 4 Sonnet Thinking (1K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-sonnet-4-thinking:32768", "provider": "anthropic", "model": "claude-sonnet-4-thinking:32768", "displayName": "Claude 4 Sonnet Thinking (32K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-sonnet-4-thinking:32768" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-thinking:32768", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet Thinking (32K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-thinking:32768", "modelKey": "claude-sonnet-4-thinking:32768", "displayName": "Claude 4 Sonnet Thinking (32K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-sonnet-4-thinking:64000", "provider": "anthropic", "model": "claude-sonnet-4-thinking:64000", "displayName": "Claude 4 Sonnet Thinking (64K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-sonnet-4-thinking:64000" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-thinking:64000", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet Thinking (64K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-thinking:64000", "modelKey": "claude-sonnet-4-thinking:64000", "displayName": "Claude 4 Sonnet Thinking (64K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-sonnet-4-thinking:8192", "provider": "anthropic", "model": "claude-sonnet-4-thinking:8192", "displayName": "Claude 4 Sonnet Thinking (8K)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claude-sonnet-4-thinking:8192" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claude-sonnet-4-thinking:8192", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "Claude 4 Sonnet Thinking (8K)" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claude-sonnet-4-thinking:8192", "modelKey": "claude-sonnet-4-thinking:8192", "displayName": "Claude 4 Sonnet Thinking (8K)", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "anthropic/claude-sonnet-4.5", "provider": "anthropic", "model": "claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "github-copilot", "github_copilot", "gmi", "kilo", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway", "zenmux" ], "aliases": [ "github-copilot/claude-sonnet-4.5", "github_copilot/claude-sonnet-4.5", "gmi/anthropic/claude-sonnet-4.5", "kilo/anthropic/claude-sonnet-4.5", "openrouter/anthropic/claude-sonnet-4.5", "orcarouter/anthropic/claude-sonnet-4.5", "poe/anthropic/claude-sonnet-4.5", "vercel/anthropic/claude-sonnet-4.5", "vercel_ai_gateway/anthropic/claude-sonnet-4.5", "zenmux/anthropic/claude-sonnet-4.5" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-copilot", "model": "claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/claude-sonnet-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/anthropic/claude-sonnet-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "perImage": { "input": 0.0048 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-sonnet-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Sonnet 4.5", "Claude Sonnet 4.5", "Claude Sonnet 4.5 (latest)", "Claude-Sonnet-4.5" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-sonnet-4.5", "modelKey": "claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Anthropic: Claude Sonnet 4.5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Claude-Sonnet-4.5", "family": "claude-sonnet", "metadata": { "lastUpdated": "2025-09-26", "openWeights": false, "releaseDate": "2025-09-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-sonnet-4.5", "modelKey": "anthropic/claude-sonnet-4.5", "displayName": "Claude Sonnet 4.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/claude-sonnet-4.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/anthropic/claude-sonnet-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/anthropic/claude-sonnet-4.5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.5", "displayName": "Anthropic: Claude Sonnet 4.5", "metadata": { "canonicalSlug": "anthropic/claude-4.5-sonnet-20250929", "createdAt": "2025-09-29T16:01:16.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 64000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-sonnet-4.6", "provider": "anthropic", "model": "claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fastrouter", "github-copilot", "gmicloud", "kilo", "nano-gpt", "openrouter", "orcarouter", "poe", "vercel", "zenmux" ], "aliases": [ "fastrouter/anthropic/claude-sonnet-4.6", "github-copilot/claude-sonnet-4.6", "gmicloud/anthropic/claude-sonnet-4.6", "kilo/anthropic/claude-sonnet-4.6", "kilo/stealth/claude-sonnet-4.6", "nano-gpt/anthropic/claude-sonnet-4.6", "openrouter/anthropic/claude-sonnet-4.6", "orcarouter/anthropic/claude-sonnet-4.6", "poe/anthropic/claude-sonnet-4.6", "vercel/anthropic/claude-sonnet-4.6", "zenmux/anthropic/claude-sonnet-4.6" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "maxReasoningEffort": true, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": true, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "github-copilot", "model": "claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "gmicloud", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "kilo", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "kilo", "model": "stealth/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "cacheWrite": 3, "input": 2.4, "output": 12 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.993999999999998 } }, { "source": "models.dev", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 3.2, "input": 2.6, "output": 13 } }, { "source": "models.dev", "provider": "vercel", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.6, "cache_write": 7.5, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "extra": { "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.6", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic: Claude Sonnet 4.6", "Claude Sonnet 4.6", "Claude-Sonnet-4.6", "Stealth: Claude Sonnet 4.6 (20% off)" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "claude-sonnet-4.6", "modelKey": "claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 63999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Anthropic: Claude Sonnet 4.6", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "stealth/claude-sonnet-4.6", "modelKey": "stealth/claude-sonnet-4.6", "displayName": "Stealth: Claude Sonnet 4.6 (20% off)", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude-Sonnet-4.6", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "anthropic/claude-sonnet-4.6", "modelKey": "anthropic/claude-sonnet-4.6", "displayName": "Claude Sonnet 4.6", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-18", "openWeights": false, "releaseDate": "2026-02-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/anthropic/claude-sonnet-4.6", "mode": "chat", "metadata": { "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthropic/claude-sonnet-4.6", "displayName": "Anthropic: Claude Sonnet 4.6", "metadata": { "canonicalSlug": "anthropic/claude-4.6-sonnet-20260217", "createdAt": "2026-02-17T15:43:10.000Z", "links": { "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "tokenizer": "Claude", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anthropic/claude-sonnet-4.6:thinking", "provider": "anthropic", "model": "claude-sonnet-4.6:thinking", "displayName": "Claude Sonnet 4.6 Thinking", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthropic/claude-sonnet-4.6:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-sonnet-4.6:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.993999999999998 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6 Thinking" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-sonnet-4.6:thinking", "modelKey": "anthropic/claude-sonnet-4.6:thinking", "displayName": "Claude Sonnet 4.6 Thinking", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "anthropic/claude-sonnet-4@20250514", "provider": "anthropic", "model": "claude-sonnet-4@20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "google-vertex-anthropic", "vertex_ai-anthropic_models" ], "aliases": [ "google-vertex-anthropic/claude-sonnet-4@20250514", "google-vertex/claude-sonnet-4@20250514", "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "assistantPrefill": true, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex-anthropic", "model": "claude-sonnet-4@20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "google-vertex", "model": "claude-sonnet-4@20250514", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4@20250514", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex-anthropic", "providerName": "Vertex (Anthropic)", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "model": "claude-sonnet-4@20250514", "modelKey": "claude-sonnet-4@20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "claude-sonnet-4@20250514", "modelKey": "claude-sonnet-4@20250514", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-anthropic_models", "model": "vertex_ai/claude-sonnet-4@20250514", "mode": "chat" } ] }, { "id": "anthropic/claude-sonnet-latest", "provider": "anthropic", "model": "claude-sonnet-latest", "displayName": "Anthropic: Claude Sonnet Latest", "family": "claude-sonnet", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/~anthropic/claude-sonnet-latest", "nano-gpt/anthropic/claude-sonnet-latest", "openrouter/~anthropic/claude-sonnet-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~anthropic/claude-sonnet-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "anthropic/claude-sonnet-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2992, "input": 2.992, "output": 14.994 } }, { "source": "models.dev", "provider": "openrouter", "model": "~anthropic/claude-sonnet-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "~anthropic/claude-sonnet-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "Anthropic Claude Sonnet Latest", "Anthropic: Claude Sonnet Latest", "Claude Sonnet Latest" ], "families": [ "claude-sonnet" ], "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~anthropic/claude-sonnet-latest", "modelKey": "~anthropic/claude-sonnet-latest", "displayName": "Anthropic: Claude Sonnet Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthropic/claude-sonnet-latest", "modelKey": "anthropic/claude-sonnet-latest", "displayName": "Claude Sonnet Latest", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~anthropic/claude-sonnet-latest", "modelKey": "~anthropic/claude-sonnet-latest", "displayName": "Anthropic Claude Sonnet Latest", "family": "claude-sonnet", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] }, { "type": "budget_tokens", "min": 1024, "max": 127999 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~anthropic/claude-sonnet-latest", "displayName": "Anthropic Claude Sonnet Latest", "metadata": { "canonicalSlug": "~anthropic/claude-sonnet-latest", "createdAt": "2026-04-27T19:32:48.000Z", "links": { "details": "/api/v1/models/~anthropic/claude-sonnet-latest/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p", "verbosity" ], "tokenizer": "Router", "topProvider": { "context_length": 1000000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "anyscale/zephyr-7b-beta", "provider": "anyscale", "model": "zephyr-7b-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/HuggingFaceH4/zephyr-7b-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/HuggingFaceH4/zephyr-7b-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/HuggingFaceH4/zephyr-7b-beta", "mode": "chat" } ] }, { "id": "apiserpent/deep-search", "provider": "apiserpent", "model": "deep-search", "mode": "search", "sources": [ "litellm" ], "providers": [ "apiserpent" ], "aliases": [ "apiserpent/deep_search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "apiserpent", "model": "apiserpent/deep_search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.0006 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "apiserpent", "model": "apiserpent/deep_search", "mode": "search", "metadata": { "metadata": { "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } } } ] }, { "id": "apiserpent/search", "provider": "apiserpent", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "apiserpent" ], "aliases": [ "apiserpent/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "apiserpent", "model": "apiserpent/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.0006 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "apiserpent", "model": "apiserpent/search", "mode": "search", "metadata": { "metadata": { "notes": "APISerpent quick search (/api/search/quick), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } } } ] }, { "id": "assemblyai/best", "provider": "assemblyai", "model": "best", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "assemblyai" ], "aliases": [ "assemblyai/best" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "assemblyai", "model": "assemblyai/best", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00003333 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "assemblyai", "model": "assemblyai/best", "mode": "audio_transcription" } ] }, { "id": "assemblyai/nano", "provider": "assemblyai", "model": "nano", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "assemblyai" ], "aliases": [ "assemblyai/nano" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "assemblyai", "model": "assemblyai/nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00010278 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "assemblyai", "model": "assemblyai/nano", "mode": "audio_transcription" } ] }, { "id": "atomic-chat/gemma-4-e4b-it-iq4-xs", "provider": "atomic-chat", "model": "gemma-4-e4b-it-iq4-xs", "displayName": "Gemma 4 E4B Instruct (IQ4_XS)", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "atomic-chat" ], "aliases": [ "atomic-chat/gemma-4-E4B-it-IQ4_XS" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "atomic-chat", "model": "gemma-4-E4B-it-IQ4_XS", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 4 E4B Instruct (IQ4_XS)" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "atomic-chat", "providerName": "Atomic Chat", "providerApi": "http://127.0.0.1:1337/v1", "providerDoc": "https://atomic.chat", "model": "gemma-4-E4B-it-IQ4_XS", "modelKey": "gemma-4-E4B-it-IQ4_XS", "displayName": "Gemma 4 E4B Instruct (IQ4_XS)", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } } ] }, { "id": "atomic-chat/gemma-4-e4b-it-mlx-4bit", "provider": "atomic-chat", "model": "gemma-4-e4b-it-mlx-4bit", "displayName": "Gemma 4 E4B Instruct (MLX 4-bit)", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "atomic-chat" ], "aliases": [ "atomic-chat/gemma-4-E4B-it-MLX-4bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "atomic-chat", "model": "gemma-4-E4B-it-MLX-4bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 4 E4B Instruct (MLX 4-bit)" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "atomic-chat", "providerName": "Atomic Chat", "providerApi": "http://127.0.0.1:1337/v1", "providerDoc": "https://atomic.chat", "model": "gemma-4-E4B-it-MLX-4bit", "modelKey": "gemma-4-E4B-it-MLX-4bit", "displayName": "Gemma 4 E4B Instruct (MLX 4-bit)", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } } ] }, { "id": "aws-polly/generative", "provider": "aws-polly", "model": "generative", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "aws_polly" ], "aliases": [ "aws_polly/generative" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aws_polly", "model": "aws_polly/generative", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aws_polly", "model": "aws_polly/generative", "mode": "audio_speech", "metadata": { "source": "https://aws.amazon.com/polly/pricing/", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "aws-polly/long-form", "provider": "aws-polly", "model": "long-form", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "aws_polly" ], "aliases": [ "aws_polly/long-form" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aws_polly", "model": "aws_polly/long-form", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.0001 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aws_polly", "model": "aws_polly/long-form", "mode": "audio_speech", "metadata": { "source": "https://aws.amazon.com/polly/pricing/", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "aws-polly/neural", "provider": "aws-polly", "model": "neural", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "aws_polly" ], "aliases": [ "aws_polly/neural" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aws_polly", "model": "aws_polly/neural", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000016 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aws_polly", "model": "aws_polly/neural", "mode": "audio_speech", "metadata": { "source": "https://aws.amazon.com/polly/pricing/", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "aws-polly/standard", "provider": "aws-polly", "model": "standard", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "aws_polly" ], "aliases": [ "aws_polly/standard" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aws_polly", "model": "aws_polly/standard", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000004 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aws_polly", "model": "aws_polly/standard", "mode": "audio_speech", "metadata": { "source": "https://aws.amazon.com/polly/pricing/", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "azure-ai/cohere-embed-v3-english", "provider": "azure-ai", "model": "cohere-embed-v3-english", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Cohere-embed-v3-english" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Cohere-embed-v3-english", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Cohere-embed-v3-english", "mode": "embedding", "metadata": { "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" } } ] }, { "id": "azure-ai/cohere-embed-v3-multilingual", "provider": "azure-ai", "model": "cohere-embed-v3-multilingual", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Cohere-embed-v3-multilingual" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Cohere-embed-v3-multilingual", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Cohere-embed-v3-multilingual", "mode": "embedding", "metadata": { "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" } } ] }, { "id": "azure-ai/cohere-rerank-v3-english", "provider": "azure-ai", "model": "cohere-rerank-v3-english", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/cohere-rerank-v3-english" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3-english", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3-english", "mode": "rerank" } ] }, { "id": "azure-ai/cohere-rerank-v3-multilingual", "provider": "azure-ai", "model": "cohere-rerank-v3-multilingual", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/cohere-rerank-v3-multilingual" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3-multilingual", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3-multilingual", "mode": "rerank" } ] }, { "id": "azure-ai/cohere-rerank-v3.5", "provider": "azure-ai", "model": "cohere-rerank-v3.5", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/cohere-rerank-v3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v3.5", "mode": "rerank" } ] }, { "id": "azure-ai/cohere-rerank-v4.0-fast", "provider": "azure-ai", "model": "cohere-rerank-v4.0-fast", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/cohere-rerank-v4.0-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxQueryTokens": 4096, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v4.0-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v4.0-fast", "mode": "rerank", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" } } ] }, { "id": "azure-ai/cohere-rerank-v4.0-pro", "provider": "azure-ai", "model": "cohere-rerank-v4.0-pro", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/cohere-rerank-v4.0-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxQueryTokens": 4096, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v4.0-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.0025 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/cohere-rerank-v4.0-pro", "mode": "rerank", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" } } ] }, { "id": "azure-ai/embed-v-4-0", "provider": "azure-ai", "model": "embed-v-4-0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/embed-v-4-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/embed-v-4-0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "supportedEndpoints": [ "/v1/embeddings" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/embed-v-4-0", "mode": "embedding", "metadata": { "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supportedEndpoints": [ "/v1/embeddings" ] } } ] }, { "id": "azure-ai/flux-1.1-pro", "provider": "azure-ai", "model": "flux-1.1-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/FLUX-1.1-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/FLUX-1.1-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/FLUX-1.1-pro", "mode": "image_generation", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "azure-ai/flux.1-kontext-pro", "provider": "azure-ai", "model": "flux.1-kontext-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/FLUX.1-Kontext-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/FLUX.1-Kontext-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/FLUX.1-Kontext-pro", "mode": "image_generation", "metadata": { "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "azure-ai/flux.2-pro", "provider": "azure-ai", "model": "flux.2-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/flux.2-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/flux.2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/flux.2-pro", "mode": "image_generation", "metadata": { "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "azure-ai/jais-30b-chat", "provider": "azure-ai", "model": "jais-30b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/jais-30b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/jais-30b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3200, "output": 9710 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/jais-30b-chat", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" } } ] }, { "id": "azure-ai/jamba-instruct", "provider": "azure-ai", "model": "jamba-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/jamba-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 70000, "inputTokens": 70000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/jamba-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/jamba-instruct", "mode": "chat" } ] }, { "id": "azure-ai/mai-ds-r1", "provider": "azure-ai", "model": "mai-ds-r1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/MAI-DS-R1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/MAI-DS-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/MAI-DS-R1", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" } } ] }, { "id": "azure-ai/model-router", "provider": "azure-ai", "model": "model-router", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/model_router" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/model_router", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/model_router", "mode": "chat", "metadata": { "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/" } } ] }, { "id": "azure-ai/phi-3-medium-128k-instruct", "provider": "azure-ai", "model": "phi-3-medium-128k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-medium-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-medium-128k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-medium-128k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3-medium-4k-instruct", "provider": "azure-ai", "model": "phi-3-medium-4k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-medium-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-medium-4k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-medium-4k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3-mini-128k-instruct", "provider": "azure-ai", "model": "phi-3-mini-128k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-mini-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-mini-128k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-mini-128k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3-mini-4k-instruct", "provider": "azure-ai", "model": "phi-3-mini-4k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-mini-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-mini-4k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-mini-4k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3-small-128k-instruct", "provider": "azure-ai", "model": "phi-3-small-128k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-small-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-small-128k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-small-128k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3-small-8k-instruct", "provider": "azure-ai", "model": "phi-3-small-8k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3-small-8k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3-small-8k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3-small-8k-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3.5-mini-instruct", "provider": "azure-ai", "model": "phi-3.5-mini-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3.5-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-mini-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-mini-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3.5-moe-instruct", "provider": "azure-ai", "model": "phi-3.5-moe-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3.5-MoE-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-MoE-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.16, "output": 0.64 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-MoE-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-3.5-vision-instruct", "provider": "azure-ai", "model": "phi-3.5-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-3.5-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-3.5-vision-instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" } } ] }, { "id": "azure-ai/phi-4", "provider": "azure-ai", "model": "phi-4", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-4", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495" } } ] }, { "id": "azure-ai/phi-4-mini-instruct", "provider": "azure-ai", "model": "phi-4-mini-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-4-mini-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-4-mini-instruct", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" } } ] }, { "id": "azure-ai/phi-4-mini-reasoning", "provider": "azure-ai", "model": "phi-4-mini-reasoning", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-4-mini-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-4-mini-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.32 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-4-mini-reasoning", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" } } ] }, { "id": "azure-ai/phi-4-multimodal-instruct", "provider": "azure-ai", "model": "phi-4-multimodal-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-4-multimodal-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-4-multimodal-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "inputAudio": 4, "output": 0.32 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-4-multimodal-instruct", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" } } ] }, { "id": "azure-ai/phi-4-reasoning", "provider": "azure-ai", "model": "phi-4-reasoning", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/Phi-4-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Phi-4-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Phi-4-reasoning", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" } } ] }, { "id": "azure-ai/prebuilt-document", "provider": "azure-ai", "model": "prebuilt-document", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/doc-intelligence/prebuilt-document" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-document", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.01 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-document", "mode": "ocr", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "azure-ai/prebuilt-layout", "provider": "azure-ai", "model": "prebuilt-layout", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/doc-intelligence/prebuilt-layout" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-layout", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.01 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-layout", "mode": "ocr", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "azure-ai/prebuilt-read", "provider": "azure-ai", "model": "prebuilt-read", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/doc-intelligence/prebuilt-read" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-read", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.0015 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/doc-intelligence/prebuilt-read", "mode": "ocr", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "azure-cognitive-services/cohere-command-a", "provider": "azure-cognitive-services", "model": "cohere-command-a", "displayName": "Command A", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-command-a" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command A" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-a", "modelKey": "cohere-command-a", "displayName": "Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } } ] }, { "id": "azure-cognitive-services/cohere-command-r-08-2024", "provider": "azure-cognitive-services", "model": "cohere-command-r-08-2024", "displayName": "Command R", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-command-r-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Command R" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-r-08-2024", "modelKey": "cohere-command-r-08-2024", "displayName": "Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } } ] }, { "id": "azure-cognitive-services/cohere-command-r-plus-08-2024", "provider": "azure-cognitive-services", "model": "cohere-command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-command-r-plus-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command R+" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-r-plus-08-2024", "modelKey": "cohere-command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } } ] }, { "id": "azure-cognitive-services/cohere-embed-v-4-0", "provider": "azure-cognitive-services", "model": "cohere-embed-v-4-0", "displayName": "Embed v4", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-embed-v-4-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-embed-v-4-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v4" ], "families": [ "cohere-embed" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v-4-0", "modelKey": "cohere-embed-v-4-0", "displayName": "Embed v4", "family": "cohere-embed", "metadata": { "lastUpdated": "2025-04-15", "openWeights": true, "releaseDate": "2025-04-15" } } ] }, { "id": "azure-cognitive-services/cohere-embed-v3-english", "provider": "azure-cognitive-services", "model": "cohere-embed-v3-english", "displayName": "Embed v3 English", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-embed-v3-english" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-embed-v3-english", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v3 English" ], "families": [ "cohere-embed" ], "releaseDate": "2023-11-07", "lastUpdated": "2023-11-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v3-english", "modelKey": "cohere-embed-v3-english", "displayName": "Embed v3 English", "family": "cohere-embed", "metadata": { "lastUpdated": "2023-11-07", "openWeights": true, "releaseDate": "2023-11-07" } } ] }, { "id": "azure-cognitive-services/cohere-embed-v3-multilingual", "provider": "azure-cognitive-services", "model": "cohere-embed-v3-multilingual", "displayName": "Embed v3 Multilingual", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/cohere-embed-v3-multilingual" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "cohere-embed-v3-multilingual", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v3 Multilingual" ], "families": [ "cohere-embed" ], "releaseDate": "2023-11-07", "lastUpdated": "2023-11-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v3-multilingual", "modelKey": "cohere-embed-v3-multilingual", "displayName": "Embed v3 Multilingual", "family": "cohere-embed", "metadata": { "lastUpdated": "2023-11-07", "openWeights": true, "releaseDate": "2023-11-07" } } ] }, { "id": "azure-cognitive-services/model-router", "provider": "azure-cognitive-services", "model": "model-router", "displayName": "Model Router", "family": "model-router", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/model-router" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "model-router", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0 } } ] }, "metadata": { "displayNames": [ "Model Router" ], "families": [ "model-router" ], "releaseDate": "2025-05-19", "lastUpdated": "2025-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "model-router", "modelKey": "model-router", "displayName": "Model Router", "family": "model-router", "metadata": { "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-05-19" } } ] }, { "id": "azure-cognitive-services/o1", "provider": "azure-cognitive-services", "model": "o1", "displayName": "o1", "family": "o", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "o1" ], "families": [ "o" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o1", "modelKey": "o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "azure-cognitive-services/o3", "provider": "azure-cognitive-services", "model": "o3", "displayName": "o3", "family": "o", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "o3" ], "families": [ "o" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o3", "modelKey": "o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "azure-cognitive-services/phi-3-medium-128k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-medium-128k-instruct", "displayName": "Phi-3-medium-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-medium-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-medium-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-medium-128k-instruct", "modelKey": "phi-3-medium-128k-instruct", "displayName": "Phi-3-medium-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3-medium-4k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-medium-4k-instruct", "displayName": "Phi-3-medium-instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-medium-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-medium-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium-instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-medium-4k-instruct", "modelKey": "phi-3-medium-4k-instruct", "displayName": "Phi-3-medium-instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3-mini-128k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-mini-128k-instruct", "displayName": "Phi-3-mini-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-mini-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-mini-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-mini-128k-instruct", "modelKey": "phi-3-mini-128k-instruct", "displayName": "Phi-3-mini-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3-mini-4k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-mini-4k-instruct", "displayName": "Phi-3-mini-instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-mini-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-mini-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini-instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-mini-4k-instruct", "modelKey": "phi-3-mini-4k-instruct", "displayName": "Phi-3-mini-instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3-small-128k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-small-128k-instruct", "displayName": "Phi-3-small-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-small-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-small-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Phi-3-small-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-small-128k-instruct", "modelKey": "phi-3-small-128k-instruct", "displayName": "Phi-3-small-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3-small-8k-instruct", "provider": "azure-cognitive-services", "model": "phi-3-small-8k-instruct", "displayName": "Phi-3-small-instruct (8k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3-small-8k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3-small-8k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Phi-3-small-instruct (8k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-small-8k-instruct", "modelKey": "phi-3-small-8k-instruct", "displayName": "Phi-3-small-instruct (8k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure-cognitive-services/phi-3.5-mini-instruct", "provider": "azure-cognitive-services", "model": "phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3.5-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3.5-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-mini-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3.5-mini-instruct", "modelKey": "phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "azure-cognitive-services/phi-3.5-moe-instruct", "provider": "azure-cognitive-services", "model": "phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-3.5-moe-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-3.5-moe-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.64 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-MoE-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3.5-moe-instruct", "modelKey": "phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "azure-cognitive-services/phi-4", "provider": "azure-cognitive-services", "model": "phi-4", "displayName": "Phi-4", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4", "modelKey": "phi-4", "displayName": "Phi-4", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure-cognitive-services/phi-4-mini", "provider": "azure-cognitive-services", "model": "phi-4-mini", "displayName": "Phi-4-mini", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-mini", "modelKey": "phi-4-mini", "displayName": "Phi-4-mini", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure-cognitive-services/phi-4-mini-reasoning", "provider": "azure-cognitive-services", "model": "phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4-mini-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4-mini-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini-reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-mini-reasoning", "modelKey": "phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure-cognitive-services/phi-4-multimodal", "provider": "azure-cognitive-services", "model": "phi-4-multimodal", "displayName": "Phi-4-multimodal", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4-multimodal" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4-multimodal", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "inputAudio": 4, "output": 0.32 } } ] }, "metadata": { "displayNames": [ "Phi-4-multimodal" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-multimodal", "modelKey": "phi-4-multimodal", "displayName": "Phi-4-multimodal", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure-cognitive-services/phi-4-reasoning", "provider": "azure-cognitive-services", "model": "phi-4-reasoning", "displayName": "Phi-4-reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4-reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-reasoning", "modelKey": "phi-4-reasoning", "displayName": "Phi-4-reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure-cognitive-services/phi-4-reasoning-plus", "provider": "azure-cognitive-services", "model": "phi-4-reasoning-plus", "displayName": "Phi-4-reasoning-plus", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/phi-4-reasoning-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "phi-4-reasoning-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4-reasoning-plus" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-reasoning-plus", "modelKey": "phi-4-reasoning-plus", "displayName": "Phi-4-reasoning-plus", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/ada", "provider": "azure", "model": "ada", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/ada" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/ada", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/ada", "mode": "embedding" } ] }, { "id": "azure/azure-stt", "provider": "azure", "model": "azure-stt", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/speech/azure-stt" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/speech/azure-stt", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0002777778 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/speech/azure-stt", "mode": "audio_transcription", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "azure/azure-tts", "provider": "azure", "model": "azure-tts", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/speech/azure-tts" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/speech/azure-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000015 } } ] }, "metadata": { "modes": [ "audio_speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/speech/azure-tts", "mode": "audio_speech", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/calculator/" } } ] }, { "id": "azure/azure-tts-hd", "provider": "azure", "model": "azure-tts-hd", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/speech/azure-tts-hd" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/speech/azure-tts-hd", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } } ] }, "metadata": { "modes": [ "audio_speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/speech/azure-tts-hd", "mode": "audio_speech", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/calculator/" } } ] }, { "id": "azure/cohere-command-a", "provider": "azure", "model": "cohere-command-a", "displayName": "Command A", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-command-a" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command A" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-a", "modelKey": "cohere-command-a", "displayName": "Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } } ] }, { "id": "azure/cohere-command-r-08-2024", "provider": "azure", "model": "cohere-command-r-08-2024", "displayName": "Command R", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-command-r-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Command R" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-r-08-2024", "modelKey": "cohere-command-r-08-2024", "displayName": "Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } } ] }, { "id": "azure/cohere-command-r-plus-08-2024", "provider": "azure", "model": "cohere-command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-command-r-plus-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command R+" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-command-r-plus-08-2024", "modelKey": "cohere-command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } } ] }, { "id": "azure/cohere-embed-v-4-0", "provider": "azure", "model": "cohere-embed-v-4-0", "displayName": "Embed v4", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-embed-v-4-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-embed-v-4-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v4" ], "families": [ "cohere-embed" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v-4-0", "modelKey": "cohere-embed-v-4-0", "displayName": "Embed v4", "family": "cohere-embed", "metadata": { "lastUpdated": "2025-04-15", "openWeights": true, "releaseDate": "2025-04-15" } } ] }, { "id": "azure/cohere-embed-v3-english", "provider": "azure", "model": "cohere-embed-v3-english", "displayName": "Embed v3 English", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-embed-v3-english" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-embed-v3-english", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v3 English" ], "families": [ "cohere-embed" ], "releaseDate": "2023-11-07", "lastUpdated": "2023-11-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v3-english", "modelKey": "cohere-embed-v3-english", "displayName": "Embed v3 English", "family": "cohere-embed", "metadata": { "lastUpdated": "2023-11-07", "openWeights": true, "releaseDate": "2023-11-07" } } ] }, { "id": "azure/cohere-embed-v3-multilingual", "provider": "azure", "model": "cohere-embed-v3-multilingual", "displayName": "Embed v3 Multilingual", "family": "cohere-embed", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/cohere-embed-v3-multilingual" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "cohere-embed-v3-multilingual", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v3 Multilingual" ], "families": [ "cohere-embed" ], "releaseDate": "2023-11-07", "lastUpdated": "2023-11-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "cohere-embed-v3-multilingual", "modelKey": "cohere-embed-v3-multilingual", "displayName": "Embed v3 Multilingual", "family": "cohere-embed", "metadata": { "lastUpdated": "2023-11-07", "openWeights": true, "releaseDate": "2023-11-07" } } ] }, { "id": "azure/computer-use-preview", "provider": "azure", "model": "computer-use-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/computer-use-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/computer-use-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 12 } }, { "source": "litellm", "provider": "azure", "model": "computer-use-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 12 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/computer-use-preview", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "computer-use-preview", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "azure/container", "provider": "azure", "model": "container", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/container" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/container", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perSession": { "codeInterpreter": 0.03 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/container", "mode": "chat" } ] }, { "id": "azure/model-router", "provider": "azure", "model": "model-router", "displayName": "Model Router", "family": "model-router", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/model-router" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "model-router", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0 } } ] }, "metadata": { "displayNames": [ "Model Router" ], "families": [ "model-router" ], "releaseDate": "2025-05-19", "lastUpdated": "2025-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "model-router", "modelKey": "model-router", "displayName": "Model Router", "family": "model-router", "metadata": { "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-05-19" } } ] }, { "id": "azure/o1", "provider": "azure", "model": "o1", "displayName": "o1", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "o1" ], "families": [ "o" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o1", "modelKey": "o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1", "mode": "chat" } ] }, { "id": "azure/o3", "provider": "azure", "model": "o3", "displayName": "o3", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "o3" ], "families": [ "o" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o3", "modelKey": "o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "azure/phi-3-medium-128k-instruct", "provider": "azure", "model": "phi-3-medium-128k-instruct", "displayName": "Phi-3-medium-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-medium-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-medium-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-medium-128k-instruct", "modelKey": "phi-3-medium-128k-instruct", "displayName": "Phi-3-medium-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3-medium-4k-instruct", "provider": "azure", "model": "phi-3-medium-4k-instruct", "displayName": "Phi-3-medium-instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-medium-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-medium-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium-instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-medium-4k-instruct", "modelKey": "phi-3-medium-4k-instruct", "displayName": "Phi-3-medium-instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3-mini-128k-instruct", "provider": "azure", "model": "phi-3-mini-128k-instruct", "displayName": "Phi-3-mini-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-mini-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-mini-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-mini-128k-instruct", "modelKey": "phi-3-mini-128k-instruct", "displayName": "Phi-3-mini-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3-mini-4k-instruct", "provider": "azure", "model": "phi-3-mini-4k-instruct", "displayName": "Phi-3-mini-instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-mini-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-mini-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini-instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-mini-4k-instruct", "modelKey": "phi-3-mini-4k-instruct", "displayName": "Phi-3-mini-instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3-small-128k-instruct", "provider": "azure", "model": "phi-3-small-128k-instruct", "displayName": "Phi-3-small-instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-small-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-small-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Phi-3-small-instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-small-128k-instruct", "modelKey": "phi-3-small-128k-instruct", "displayName": "Phi-3-small-instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3-small-8k-instruct", "provider": "azure", "model": "phi-3-small-8k-instruct", "displayName": "Phi-3-small-instruct (8k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3-small-8k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3-small-8k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Phi-3-small-instruct (8k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3-small-8k-instruct", "modelKey": "phi-3-small-8k-instruct", "displayName": "Phi-3-small-instruct (8k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "azure/phi-3.5-mini-instruct", "provider": "azure", "model": "phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3.5-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3.5-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.52 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-mini-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3.5-mini-instruct", "modelKey": "phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "azure/phi-3.5-moe-instruct", "provider": "azure", "model": "phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-3.5-moe-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-3.5-moe-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.64 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-MoE-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-3.5-moe-instruct", "modelKey": "phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "azure/phi-4", "provider": "azure", "model": "phi-4", "displayName": "Phi-4", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4", "modelKey": "phi-4", "displayName": "Phi-4", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/phi-4-mini", "provider": "azure", "model": "phi-4-mini", "displayName": "Phi-4-mini", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-mini", "modelKey": "phi-4-mini", "displayName": "Phi-4-mini", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/phi-4-mini-reasoning", "provider": "azure", "model": "phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4-mini-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4-mini-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini-reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-mini-reasoning", "modelKey": "phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/phi-4-multimodal", "provider": "azure", "model": "phi-4-multimodal", "displayName": "Phi-4-multimodal", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4-multimodal" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4-multimodal", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "inputAudio": 4, "output": 0.32 } } ] }, "metadata": { "displayNames": [ "Phi-4-multimodal" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-multimodal", "modelKey": "phi-4-multimodal", "displayName": "Phi-4-multimodal", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/phi-4-reasoning", "provider": "azure", "model": "phi-4-reasoning", "displayName": "Phi-4-reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4-reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-reasoning", "modelKey": "phi-4-reasoning", "displayName": "Phi-4-reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/phi-4-reasoning-plus", "provider": "azure", "model": "phi-4-reasoning-plus", "displayName": "Phi-4-reasoning-plus", "family": "phi", "sources": [ "models.dev" ], "providers": [ "azure" ], "aliases": [ "azure/phi-4-reasoning-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "phi-4-reasoning-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Phi-4-reasoning-plus" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "phi-4-reasoning-plus", "modelKey": "phi-4-reasoning-plus", "displayName": "Phi-4-reasoning-plus", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "azure/sora-2", "provider": "azure", "model": "sora-2", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/sora-2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/sora-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.1 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/sora-2", "mode": "video_generation", "metadata": { "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" } } ] }, { "id": "azure/sora-2-pro", "provider": "azure", "model": "sora-2-pro", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/sora-2-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/sora-2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.3 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/sora-2-pro", "mode": "video_generation", "metadata": { "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" } } ] }, { "id": "azure/sora-2-pro-high-res", "provider": "azure", "model": "sora-2-pro-high-res", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/sora-2-pro-high-res" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/sora-2-pro-high-res", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.5 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/sora-2-pro-high-res", "mode": "video_generation", "metadata": { "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" } } ] }, { "id": "bailing/ling-1t", "provider": "bailing", "model": "ling-1t", "displayName": "Ling-1T", "family": "ling", "sources": [ "models.dev" ], "providers": [ "bailing" ], "aliases": [ "bailing/Ling-1T" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "bailing", "model": "Ling-1T", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.29 } } ] }, "metadata": { "displayNames": [ "Ling-1T" ], "families": [ "ling" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-10", "lastUpdated": "2025-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "bailing", "providerName": "Bailing", "providerApi": "https://api.tbox.cn/api/llm/v1/chat/completions", "providerDoc": "https://alipaytbox.yuque.com/sxs0ba/ling/intro", "model": "Ling-1T", "modelKey": "Ling-1T", "displayName": "Ling-1T", "family": "ling", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-10", "openWeights": true, "releaseDate": "2025-10" } } ] }, { "id": "bailing/ring-1t", "provider": "bailing", "model": "ring-1t", "displayName": "Ring-1T", "family": "ring", "sources": [ "models.dev" ], "providers": [ "bailing" ], "aliases": [ "bailing/Ring-1T" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "bailing", "model": "Ring-1T", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.29 } } ] }, "metadata": { "displayNames": [ "Ring-1T" ], "families": [ "ring" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-10", "lastUpdated": "2025-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "bailing", "providerName": "Bailing", "providerApi": "https://api.tbox.cn/api/llm/v1/chat/completions", "providerDoc": "https://alipaytbox.yuque.com/sxs0ba/ling/intro", "model": "Ring-1T", "modelKey": "Ring-1T", "displayName": "Ring-1T", "family": "ring", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-10", "openWeights": true, "releaseDate": "2025-10" } } ] }, { "id": "baseten/nemotron-120b-a12b", "provider": "baseten", "model": "nemotron-120b-a12b", "displayName": "Nemotron Super", "family": "nemotron", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "baseten" ], "aliases": [ "baseten/nvidia/Nemotron-120B-A12B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "outputTokens": 202800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "baseten", "model": "nvidia/Nemotron-120B-A12B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 0.75 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/nvidia/Nemotron-120B-A12B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Nemotron Super" ], "families": [ "nemotron" ], "modes": [ "chat" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "nvidia/Nemotron-120B-A12B", "modelKey": "nvidia/Nemotron-120B-A12B", "displayName": "Nemotron Super", "family": "nemotron", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/nvidia/Nemotron-120B-A12B", "mode": "chat" } ] }, { "id": "baseten/nvidia-nemotron-3-ultra-550b-a55b", "provider": "baseten", "model": "nvidia-nemotron-3-ultra-550b-a55b", "displayName": "Nemotron Ultra", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "baseten" ], "aliases": [ "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "outputTokens": 202800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "baseten", "model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "Nemotron Ultra" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "modelKey": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "displayName": "Nemotron Ultra", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "bedrock-converse/amazon.nova-2-lite-v1:0", "provider": "bedrock-converse", "model": "amazon.nova-2-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "amazon.nova-2-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "amazon.nova-2-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/amazon.nova-2-pro-preview-20251202-v1:0", "provider": "bedrock-converse", "model": "amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/amazon.nova-2-pro-preview-20251202-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "amazon.nova-2-pro-preview-20251202-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.546875, "input": 2.1875, "inputAudio": 2.1875, "inputImage": 2.1875, "output": 17.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/amazon.nova-lite-v1:0", "provider": "bedrock-converse", "model": "amazon.nova-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/amazon.nova-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "amazon.nova-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "amazon.nova-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/amazon.nova-micro-v1:0", "provider": "bedrock-converse", "model": "amazon.nova-micro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/amazon.nova-micro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "amazon.nova-micro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.14 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "amazon.nova-micro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/amazon.nova-pro-v1:0", "provider": "bedrock-converse", "model": "amazon.nova-pro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 3.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "amazon.nova-pro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-3-7-sonnet-20250219-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-3-7-sonnet-20250219-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-fable-5", "provider": "bedrock-converse", "model": "anthropic.claude-fable-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-fable-5", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/anthropic.claude-haiku-4-5@20251001", "provider": "bedrock-converse", "model": "anthropic.claude-haiku-4-5@20251001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-haiku-4-5@20251001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-haiku-4-5@20251001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-haiku-4-5@20251001", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-1-20250805-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-1-20250805-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-20250514-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-5-20251101-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-6-v1", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-6-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-6-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-6-v1", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-opus-4-8", "provider": "bedrock-converse", "model": "anthropic.claude-opus-4-8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-opus-4-8", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-sonnet-4-20250514-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-sonnet-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.amazon.nova-2-lite-v1:0", "provider": "bedrock-converse", "model": "apac.amazon.nova-2-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.amazon.nova-2-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0825, "input": 0.33, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.amazon.nova-2-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.amazon.nova-2-pro-preview-20251202-v1:0", "provider": "bedrock-converse", "model": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.amazon.nova-2-pro-preview-20251202-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.546875, "input": 2.1875, "inputAudio": 2.1875, "inputImage": 2.1875, "output": 17.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.amazon.nova-lite-v1:0", "provider": "bedrock-converse", "model": "apac.amazon.nova-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.amazon.nova-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.amazon.nova-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.063, "output": 0.252 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.amazon.nova-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.amazon.nova-micro-v1:0", "provider": "bedrock-converse", "model": "apac.amazon.nova-micro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.amazon.nova-micro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.amazon.nova-micro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.037, "output": 0.148 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.amazon.nova-micro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.amazon.nova-pro-v1:0", "provider": "bedrock-converse", "model": "apac.amazon.nova-pro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.84, "output": 3.36 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.amazon.nova-pro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/apac.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 1.375, "input": 1.1, "output": 5.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/apac.anthropic.claude-sonnet-4-20250514-v1:0", "provider": "bedrock-converse", "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/apac.anthropic.claude-sonnet-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 1.375, "input": 1.1, "output": 5.5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-opus-4-6-v1", "provider": "bedrock-converse", "model": "au.anthropic.claude-opus-4-6-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-6-v1", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "au.anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-opus-4-8", "provider": "bedrock-converse", "model": "au.anthropic.claude-opus-4-8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-opus-4-8", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/au.anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "au.anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/au.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "au.anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "au.anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/deepseek.v3-v1:0", "provider": "bedrock-converse", "model": "deepseek.v3-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/deepseek.v3-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 81920, "outputTokens": 81920, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "deepseek.v3-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.58, "output": 1.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "deepseek.v3-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/deepseek.v3.2", "provider": "bedrock-converse", "model": "deepseek.v3.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/deepseek.v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 1.85 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "deepseek.v3.2", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/eu.amazon.nova-2-lite-v1:0", "provider": "bedrock-converse", "model": "eu.amazon.nova-2-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.amazon.nova-2-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0825, "input": 0.33, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.amazon.nova-2-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.amazon.nova-2-pro-preview-20251202-v1:0", "provider": "bedrock-converse", "model": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.amazon.nova-2-pro-preview-20251202-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.546875, "input": 2.1875, "inputAudio": 2.1875, "inputImage": 2.1875, "output": 17.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.amazon.nova-lite-v1:0", "provider": "bedrock-converse", "model": "eu.amazon.nova-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.amazon.nova-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.amazon.nova-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.078, "output": 0.312 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.amazon.nova-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.amazon.nova-micro-v1:0", "provider": "bedrock-converse", "model": "eu.amazon.nova-micro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.amazon.nova-micro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.amazon.nova-micro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.046, "output": 0.184 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.amazon.nova-micro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.amazon.nova-pro-v1:0", "provider": "bedrock-converse", "model": "eu.amazon.nova-pro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.05, "output": 4.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.amazon.nova-pro-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/eu.anthropic.claude-fable-5", "provider": "bedrock-converse", "model": "eu.anthropic.claude-fable-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.1, "cacheWrite": 13.75, "input": 11, "output": 55 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-fable-5", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 1.375, "input": 1.1, "output": 5.5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000022 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "deprecationDate": "2026-10-15", "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-1-20250805-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-1-20250805-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-20250514-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-6-v1", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-6-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-6-v1", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-opus-4-8", "provider": "bedrock-converse", "model": "eu.anthropic.claude-opus-4-8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-opus-4-8", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-sonnet-4-20250514-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "eu.anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.deepseek.v3.2", "provider": "bedrock-converse", "model": "eu.deepseek.v3.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.deepseek.v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.74, "output": 2.22 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.deepseek.v3.2", "mode": "chat" } ] }, { "id": "bedrock-converse/eu.mistral.pixtral-large-2502-v1:0", "provider": "bedrock-converse", "model": "eu.mistral.pixtral-large-2502-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/eu.mistral.pixtral-large-2502-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "eu.mistral.pixtral-large-2502-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "eu.mistral.pixtral-large-2502-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/global.amazon.nova-2-lite-v1:0", "provider": "bedrock-converse", "model": "global.amazon.nova-2-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.amazon.nova-2-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.amazon.nova-2-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-fable-5", "provider": "bedrock-converse", "model": "global.anthropic.claude-fable-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "cacheWrite": 12.5, "input": 10, "output": 50 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-fable-5", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/global.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "bedrock-converse", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-opus-4-6-v1", "provider": "bedrock-converse", "model": "global.anthropic.claude-opus-4-6-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-6-v1", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "global.anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-opus-4-8", "provider": "bedrock-converse", "model": "global.anthropic.claude-opus-4-8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.00001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-opus-4-8", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-sonnet-4-20250514-v1:0", "provider": "bedrock-converse", "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-sonnet-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/global.anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "global.anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/global.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000006 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "global.anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/google.gemma-3-12b-it", "provider": "bedrock-converse", "model": "google.gemma-3-12b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/google.gemma-3-12b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "google.gemma-3-12b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.29 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "google.gemma-3-12b-it", "mode": "chat" } ] }, { "id": "bedrock-converse/google.gemma-3-27b-it", "provider": "bedrock-converse", "model": "google.gemma-3-27b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/google.gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "google.gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.23, "output": 0.38 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "google.gemma-3-27b-it", "mode": "chat" } ] }, { "id": "bedrock-converse/google.gemma-3-4b-it", "provider": "bedrock-converse", "model": "google.gemma-3-4b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/google.gemma-3-4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "google.gemma-3-4b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.08 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "google.gemma-3-4b-it", "mode": "chat" } ] }, { "id": "bedrock-converse/jp.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/jp.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 1.375, "input": 1.1, "output": 5.5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/jp.anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "jp.anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/jp.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "minimalReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "jp.anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "jp.anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/jp.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/jp.anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "jp.anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/jp.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "jp.anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "jp.anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/meta.llama3-3-70b-instruct-v1:0", "provider": "bedrock-converse", "model": "meta.llama3-3-70b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/meta.llama3-3-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "meta.llama3-3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "meta.llama3-3-70b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/meta.llama4-maverick-17b-instruct-v1:0", "provider": "bedrock-converse", "model": "meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/meta.llama4-maverick-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "meta.llama4-maverick-17b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.24, "output": 0.97 }, "extra": { "input_cost_per_token_batches": 1.2e-7, "output_cost_per_token_batches": 4.85e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/meta.llama4-scout-17b-instruct-v1:0", "provider": "bedrock-converse", "model": "meta.llama4-scout-17b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/meta.llama4-scout-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "meta.llama4-scout-17b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.17, "output": 0.66 }, "extra": { "input_cost_per_token_batches": 8.5e-8, "output_cost_per_token_batches": 3.3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "meta.llama4-scout-17b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/moonshot.kimi-k2-thinking", "provider": "bedrock-converse", "model": "moonshot.kimi-k2-thinking", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/moonshot.kimi-k2-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "moonshot.kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "moonshot.kimi-k2-thinking", "mode": "chat" } ] }, { "id": "bedrock-converse/moonshotai.kimi-k2.5", "provider": "bedrock-converse", "model": "moonshotai.kimi-k2.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/moonshotai.kimi-k2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "moonshotai.kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "moonshotai.kimi-k2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/nvidia.nemotron-nano-12b-v2", "provider": "bedrock-converse", "model": "nvidia.nemotron-nano-12b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/nvidia.nemotron-nano-12b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-12b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-12b-v2", "mode": "chat" } ] }, { "id": "bedrock-converse/nvidia.nemotron-nano-3-30b", "provider": "bedrock-converse", "model": "nvidia.nemotron-nano-3-30b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/nvidia.nemotron-nano-3-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-3-30b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-3-30b", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/nvidia.nemotron-nano-9b-v2", "provider": "bedrock-converse", "model": "nvidia.nemotron-nano-9b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/nvidia.nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-9b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.23 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "nvidia.nemotron-nano-9b-v2", "mode": "chat" } ] }, { "id": "bedrock-converse/nvidia.nemotron-super-3-120b", "provider": "bedrock-converse", "model": "nvidia.nemotron-super-3-120b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/nvidia.nemotron-super-3-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "nvidia.nemotron-super-3-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.65 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "nvidia.nemotron-super-3-120b", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/openai.gpt-oss-120b-1:0", "provider": "bedrock-converse", "model": "openai.gpt-oss-120b-1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/openai.gpt-oss-120b-1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "openai.gpt-oss-120b-1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "openai.gpt-oss-120b-1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/openai.gpt-oss-20b-1:0", "provider": "bedrock-converse", "model": "openai.gpt-oss-20b-1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/openai.gpt-oss-20b-1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "openai.gpt-oss-20b-1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "openai.gpt-oss-20b-1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/openai.gpt-oss-safeguard-120b", "provider": "bedrock-converse", "model": "openai.gpt-oss-safeguard-120b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/openai.gpt-oss-safeguard-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "openai.gpt-oss-safeguard-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "openai.gpt-oss-safeguard-120b", "mode": "chat" } ] }, { "id": "bedrock-converse/openai.gpt-oss-safeguard-20b", "provider": "bedrock-converse", "model": "openai.gpt-oss-safeguard-20b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/openai.gpt-oss-safeguard-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "openai.gpt-oss-safeguard-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "openai.gpt-oss-safeguard-20b", "mode": "chat" } ] }, { "id": "bedrock-converse/us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.36, "cacheWrite": 4.5, "input": 3.6, "output": 18 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000072, "input_cost_per_token_above_200k_tokens": 0.0000072, "output_cost_per_token_above_200k_tokens": 0.000027, "cache_creation_input_token_cost_above_200k_tokens": 0.000009, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000144, "cache_read_input_token_cost_above_200k_tokens": 7.2e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-2-lite-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-2-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-2-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-2-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0825, "input": 0.33, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-2-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-2-pro-preview-20251202-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-2-pro-preview-20251202-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-2-pro-preview-20251202-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.546875, "input": 2.1875, "inputAudio": 2.1875, "inputImage": 2.1875, "output": 17.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-lite-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-lite-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-lite-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-lite-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-lite-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-micro-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-micro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-micro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-micro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.14 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-micro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-premier-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-premier-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-premier-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-premier-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 12.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-premier-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.amazon.nova-pro-v1:0", "provider": "bedrock-converse", "model": "us.amazon.nova-pro-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.amazon.nova-pro-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.amazon.nova-pro-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 3.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.amazon.nova-pro-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-3-7-sonnet-20250219-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-3-7-sonnet-20250219-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-fable-5", "provider": "bedrock-converse", "model": "us.anthropic.claude-fable-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-fable-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.1, "cacheWrite": 13.75, "input": 11, "output": 55 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-fable-5", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-haiku-4-5-20251001-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-haiku-4-5-20251001-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 1.375, "input": 1.1, "output": 5.5 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" } } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-1-20250805-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-1-20250805-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-20250514-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-5-20251101-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-5-20251101-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-6-v1", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-6-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-6-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-6-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-6-v1", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-7", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-7", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-opus-4-8", "provider": "bedrock-converse", "model": "us.anthropic.claude-opus-4-8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "adaptiveThinking": true, "assistantPrefill": false, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "samplingParams": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 6.875, "input": 5.5, "output": 27.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.000011 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-opus-4-8", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-sonnet-4-20250514-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-sonnet-4-20250514-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-sonnet-4-5-20250929-v1:0", "provider": "bedrock-converse", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-sonnet-4-5-20250929-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.anthropic.claude-sonnet-4-6", "provider": "bedrock-converse", "model": "us.anthropic.claude-sonnet-4-6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.anthropic.claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "maxReasoningEffort": true, "moderation": false, "nativeStructuredOutput": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "cacheWrite": 4.125, "input": 3.3, "output": 16.5 }, "searchContextPerQuery": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0.0000066 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.anthropic.claude-sonnet-4-6", "mode": "chat" } ] }, { "id": "bedrock-converse/us.deepseek.r1-v1:0", "provider": "bedrock-converse", "model": "us.deepseek.r1-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.deepseek.r1-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.deepseek.r1-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.deepseek.r1-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.deepseek.v3.2", "provider": "bedrock-converse", "model": "us.deepseek.v3.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.deepseek.v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.deepseek.v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 1.85 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.deepseek.v3.2", "mode": "chat" } ] }, { "id": "bedrock-converse/us.meta.llama3-3-70b-instruct-v1:0", "provider": "bedrock-converse", "model": "us.meta.llama3-3-70b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.meta.llama3-3-70b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.meta.llama3-3-70b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.meta.llama3-3-70b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.meta.llama4-maverick-17b-instruct-v1:0", "provider": "bedrock-converse", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.meta.llama4-maverick-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.24, "output": 0.97 }, "extra": { "input_cost_per_token_batches": 1.2e-7, "output_cost_per_token_batches": 4.85e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.meta.llama4-scout-17b-instruct-v1:0", "provider": "bedrock-converse", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.meta.llama4-scout-17b-instruct-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.17, "output": 0.66 }, "extra": { "input_cost_per_token_batches": 8.5e-8, "output_cost_per_token_batches": 3.3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.meta.llama4-scout-17b-instruct-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.mistral.pixtral-large-2502-v1:0", "provider": "bedrock-converse", "model": "us.mistral.pixtral-large-2502-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.mistral.pixtral-large-2502-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.mistral.pixtral-large-2502-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.mistral.pixtral-large-2502-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.writer.palmyra-x4-v1:0", "provider": "bedrock-converse", "model": "us.writer.palmyra-x4-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.writer.palmyra-x4-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.writer.palmyra-x4-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.writer.palmyra-x4-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/us.writer.palmyra-x5-v1:0", "provider": "bedrock-converse", "model": "us.writer.palmyra-x5-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/us.writer.palmyra-x5-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "us.writer.palmyra-x5-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "us.writer.palmyra-x5-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/writer.palmyra-x4-v1:0", "provider": "bedrock-converse", "model": "writer.palmyra-x4-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/writer.palmyra-x4-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "writer.palmyra-x4-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "writer.palmyra-x4-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/writer.palmyra-x5-v1:0", "provider": "bedrock-converse", "model": "writer.palmyra-x5-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/writer.palmyra-x5-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "writer.palmyra-x5-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "writer.palmyra-x5-v1:0", "mode": "chat" } ] }, { "id": "bedrock-converse/zai.glm-4.7", "provider": "bedrock-converse", "model": "zai.glm-4.7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/zai.glm-4.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "zai.glm-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "zai.glm-4.7", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/zai.glm-4.7-flash", "provider": "bedrock-converse", "model": "zai.glm-4.7-flash", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/zai.glm-4.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "zai.glm-4.7-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "zai.glm-4.7-flash", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-converse/zai.glm-5", "provider": "bedrock-converse", "model": "zai.glm-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_converse" ], "aliases": [ "bedrock_converse/zai.glm-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_converse", "model": "zai.glm-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "zai.glm-5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "bedrock-mantle/openai.gpt-5.4", "provider": "bedrock-mantle", "model": "openai.gpt-5.4", "mode": "responses", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-5.4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-5.4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 2.75, "output": 16.5 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-5.4", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "bedrock-mantle/openai.gpt-5.5", "provider": "bedrock-mantle", "model": "openai.gpt-5.5", "mode": "responses", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-5.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-5.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 5.5, "output": 33 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-5.5", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "bedrock-mantle/openai.gpt-oss-120b", "provider": "bedrock-mantle", "model": "openai.gpt-oss-120b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-oss-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-120b", "mode": "chat" } ] }, { "id": "bedrock-mantle/openai.gpt-oss-20b", "provider": "bedrock-mantle", "model": "openai.gpt-oss-20b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-oss-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-20b", "mode": "chat" } ] }, { "id": "bedrock-mantle/openai.gpt-oss-safeguard-120b", "provider": "bedrock-mantle", "model": "openai.gpt-oss-safeguard-120b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-oss-safeguard-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-safeguard-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-safeguard-120b", "mode": "chat" } ] }, { "id": "bedrock-mantle/openai.gpt-oss-safeguard-20b", "provider": "bedrock-mantle", "model": "openai.gpt-oss-safeguard-20b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock_mantle" ], "aliases": [ "bedrock_mantle/openai.gpt-oss-safeguard-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-safeguard-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_mantle", "model": "bedrock_mantle/openai.gpt-oss-safeguard-20b", "mode": "chat" } ] }, { "id": "black-forest-labs/flux-dev", "provider": "black-forest-labs", "model": "flux-dev", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-dev" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-dev", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.025 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-dev", "mode": "image_generation", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "black-forest-labs/flux-kontext-max", "provider": "black-forest-labs", "model": "flux-kontext-max", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-kontext-max" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-kontext-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-kontext-max", "mode": "image_edit", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ] } } ] }, { "id": "black-forest-labs/flux-kontext-pro", "provider": "black-forest-labs", "model": "flux-kontext-pro", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-kontext-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-kontext-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-kontext-pro", "mode": "image_edit", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ] } } ] }, { "id": "black-forest-labs/flux-pro", "provider": "black-forest-labs", "model": "flux-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.05 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro", "mode": "image_generation", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "black-forest-labs/flux-pro-1.0-expand", "provider": "black-forest-labs", "model": "flux-pro-1.0-expand", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-pro-1.0-expand" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.0-expand", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.05 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.0-expand", "mode": "image_edit", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "black-forest-labs/flux-pro-1.0-fill", "provider": "black-forest-labs", "model": "flux-pro-1.0-fill", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-pro-1.0-fill" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.0-fill", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.05 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.0-fill", "mode": "image_edit", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "black-forest-labs/flux-pro-1.1", "provider": "black-forest-labs", "model": "flux-pro-1.1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-pro-1.1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.1", "mode": "image_generation", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "black-forest-labs/flux-pro-1.1-ultra", "provider": "black-forest-labs", "model": "flux-pro-1.1-ultra", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "black_forest_labs" ], "aliases": [ "black_forest_labs/flux-pro-1.1-ultra" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.1-ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "black_forest_labs", "model": "black_forest_labs/flux-pro-1.1-ultra", "mode": "image_generation", "metadata": { "source": "https://bfl.ai/pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "cerebras/llama3.1-70b", "provider": "cerebras", "model": "llama3.1-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cerebras" ], "aliases": [ "cerebras/llama3.1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cerebras", "model": "cerebras/llama3.1-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/llama3.1-70b", "mode": "chat" } ] }, { "id": "cerebras/llama3.1-8b", "provider": "cerebras", "model": "llama3.1-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cerebras" ], "aliases": [ "cerebras/llama3.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cerebras", "model": "cerebras/llama3.1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/llama3.1-8b", "mode": "chat" } ] }, { "id": "cerebras/zai-glm-4.6", "provider": "cerebras", "model": "zai-glm-4.6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cerebras" ], "aliases": [ "cerebras/zai-glm-4.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cerebras", "model": "cerebras/zai-glm-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.25, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-01-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/zai-glm-4.6", "mode": "chat", "metadata": { "deprecationDate": "2026-01-20", "source": "https://www.cerebras.ai/pricing" } } ] }, { "id": "cerebras/zai-glm-4.7", "provider": "cerebras", "model": "zai-glm-4.7", "displayName": "Z.AI GLM-4.7", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cerebras" ], "aliases": [ "cerebras/zai-glm-4.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cerebras", "model": "zai-glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 2.25, "output": 2.75 } }, { "source": "litellm", "provider": "cerebras", "model": "cerebras/zai-glm-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.25, "output": 2.75 } } ] }, "metadata": { "displayNames": [ "Z.AI GLM-4.7" ], "modes": [ "chat" ], "statuses": [ "beta" ], "releaseDate": "2026-01-07", "lastUpdated": "2026-06-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cerebras", "providerName": "Cerebras", "providerDoc": "https://inference-docs.cerebras.ai/models/overview", "model": "zai-glm-4.7", "modelKey": "zai-glm-4.7", "displayName": "Z.AI GLM-4.7", "status": "beta", "metadata": { "lastUpdated": "2026-06-10", "openWeights": true, "releaseDate": "2026-01-07", "reasoningOptions": [ { "type": "effort", "values": [ "none" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/zai-glm-4.7", "mode": "chat", "metadata": { "source": "https://www.cerebras.ai/pricing" } } ] }, { "id": "chutes/deephermes-3-mistral-24b-preview", "provider": "chutes", "model": "deephermes-3-mistral-24b-preview", "displayName": "DeepHermes 3 Mistral 24B Preview", "family": "nousresearch", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/NousResearch/DeepHermes-3-Mistral-24B-Preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01225, "input": 0.0245, "output": 0.0978 } } ] }, "metadata": { "displayNames": [ "DeepHermes 3 Mistral 24B Preview" ], "families": [ "nousresearch" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "modelKey": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "displayName": "DeepHermes 3 Mistral 24B Preview", "family": "nousresearch", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "chutes/dots.ocr", "provider": "chutes", "model": "dots.ocr", "displayName": "dots.ocr", "family": "rednote", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/rednote-hilab/dots.ocr" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "rednote-hilab/dots.ocr", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.01, "output": 0.0109 } } ] }, "metadata": { "displayNames": [ "dots.ocr" ], "families": [ "rednote" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "rednote-hilab/dots.ocr", "modelKey": "rednote-hilab/dots.ocr", "displayName": "dots.ocr", "family": "rednote", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "chutes/gemma-3-12b-it", "provider": "chutes", "model": "gemma-3-12b-it", "displayName": "gemma 3 12b it", "family": "unsloth", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/unsloth/gemma-3-12b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.03, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "gemma 3 12b it" ], "families": [ "unsloth" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/gemma-3-12b-it", "modelKey": "unsloth/gemma-3-12b-it", "displayName": "gemma 3 12b it", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "chutes/gemma-3-27b-it", "provider": "chutes", "model": "gemma-3-27b-it", "displayName": "gemma 3 27b it", "family": "unsloth", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/unsloth/gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0136, "input": 0.0272, "output": 0.1087 } } ] }, "metadata": { "displayNames": [ "gemma 3 27b it" ], "families": [ "unsloth" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/gemma-3-27b-it", "modelKey": "unsloth/gemma-3-27b-it", "displayName": "gemma 3 27b it", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "chutes/gemma-3-4b-it", "provider": "chutes", "model": "gemma-3-4b-it", "displayName": "gemma 3 4b it", "family": "unsloth", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/unsloth/gemma-3-4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 96000, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/gemma-3-4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.01, "output": 0.0272 } } ] }, "metadata": { "displayNames": [ "gemma 3 4b it" ], "families": [ "unsloth" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/gemma-3-4b-it", "modelKey": "unsloth/gemma-3-4b-it", "displayName": "gemma 3 4b it", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "chutes/hermes-4-14b", "provider": "chutes", "model": "hermes-4-14b", "displayName": "Hermes 4 14B", "family": "nousresearch", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/NousResearch/Hermes-4-14B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "NousResearch/Hermes-4-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0068, "input": 0.0136, "output": 0.0543 } } ] }, "metadata": { "displayNames": [ "Hermes 4 14B" ], "families": [ "nousresearch" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "NousResearch/Hermes-4-14B", "modelKey": "NousResearch/Hermes-4-14B", "displayName": "Hermes 4 14B", "family": "nousresearch", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "chutes/mimo-v2-flash-tee", "provider": "chutes", "model": "mimo-v2-flash-tee", "displayName": "MiMo V2 Flash TEE", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/XiaomiMiMo/MiMo-V2-Flash-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "XiaomiMiMo/MiMo-V2-Flash-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.045, "input": 0.09, "output": 0.29 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash TEE" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "XiaomiMiMo/MiMo-V2-Flash-TEE", "modelKey": "XiaomiMiMo/MiMo-V2-Flash-TEE", "displayName": "MiMo V2 Flash TEE", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16" } } ] }, { "id": "clarifai/mm-poly-8b", "provider": "clarifai", "model": "mm-poly-8b", "displayName": "MM Poly 8B", "family": "mm-poly", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/main/models/mm-poly-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "clarifai/main/models/mm-poly-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.658, "output": 1.11 } } ] }, "metadata": { "displayNames": [ "MM Poly 8B" ], "families": [ "mm-poly" ], "releaseDate": "2025-06", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "clarifai/main/models/mm-poly-8b", "modelKey": "clarifai/main/models/mm-poly-8b", "displayName": "MM Poly 8B", "family": "mm-poly", "metadata": { "lastUpdated": "2026-02-25", "openWeights": false, "releaseDate": "2025-06" } } ] }, { "id": "clarifai/trinity-mini", "provider": "clarifai", "model": "trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/arcee_ai/AFM/models/trinity-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "arcee_ai/AFM/models/trinity-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Trinity Mini" ], "families": [ "trinity-mini" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "arcee_ai/AFM/models/trinity-mini", "modelKey": "arcee_ai/AFM/models/trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-12" } } ] }, { "id": "claudinio/claudinio", "provider": "claudinio", "model": "claudinio", "displayName": "Claudinio", "sources": [ "models.dev" ], "providers": [ "claudinio" ], "aliases": [ "claudinio/claudinio" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "claudinio", "model": "claudinio", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "Claudinio" ], "knowledgeCutoff": "2026-05", "releaseDate": "2026-05-12", "lastUpdated": "2026-06-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "claudinio", "providerName": "Claudinio", "providerApi": "https://api.claudin.io/v1", "providerDoc": "https://claudin.io", "model": "claudinio", "modelKey": "claudinio", "displayName": "Claudinio", "metadata": { "knowledgeCutoff": "2026-05", "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-05-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "cloudferro-sherlock/bielik-11b-v2.6-instruct", "provider": "cloudferro-sherlock", "model": "bielik-11b-v2.6-instruct", "displayName": "Bielik 11B v2.6 Instruct", "sources": [ "models.dev" ], "providers": [ "cloudferro-sherlock" ], "aliases": [ "cloudferro-sherlock/speakleash/Bielik-11B-v2.6-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudferro-sherlock", "model": "speakleash/Bielik-11B-v2.6-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.67, "output": 0.67 } } ] }, "metadata": { "displayNames": [ "Bielik 11B v2.6 Instruct" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudferro-sherlock", "providerName": "CloudFerro Sherlock", "providerApi": "https://api-sherlock.cloudferro.com/openai/v1/", "providerDoc": "https://docs.sherlock.cloudferro.com/", "model": "speakleash/Bielik-11B-v2.6-Instruct", "modelKey": "speakleash/Bielik-11B-v2.6-Instruct", "displayName": "Bielik 11B v2.6 Instruct", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } } ] }, { "id": "cloudferro-sherlock/bielik-11b-v3.0-instruct", "provider": "cloudferro-sherlock", "model": "bielik-11b-v3.0-instruct", "displayName": "Bielik 11B v3.0 Instruct", "sources": [ "models.dev" ], "providers": [ "cloudferro-sherlock" ], "aliases": [ "cloudferro-sherlock/speakleash/Bielik-11B-v3.0-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudferro-sherlock", "model": "speakleash/Bielik-11B-v3.0-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.67, "output": 0.67 } } ] }, "metadata": { "displayNames": [ "Bielik 11B v3.0 Instruct" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudferro-sherlock", "providerName": "CloudFerro Sherlock", "providerApi": "https://api-sherlock.cloudferro.com/openai/v1/", "providerDoc": "https://docs.sherlock.cloudferro.com/", "model": "speakleash/Bielik-11B-v3.0-Instruct", "modelKey": "speakleash/Bielik-11B-v3.0-Instruct", "displayName": "Bielik 11B v3.0 Instruct", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } } ] }, { "id": "cloudflare-ai-gateway/aura-2-en", "provider": "cloudflare-ai-gateway", "model": "aura-2-en", "displayName": "Deepgram Aura 2 (EN)", "family": "aura", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-en" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/deepgram/aura-2-en", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Deepgram Aura 2 (EN)" ], "families": [ "aura" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/deepgram/aura-2-en", "modelKey": "workers-ai/@cf/deepgram/aura-2-en", "displayName": "Deepgram Aura 2 (EN)", "family": "aura", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } } ] }, { "id": "cloudflare-ai-gateway/aura-2-es", "provider": "cloudflare-ai-gateway", "model": "aura-2-es", "displayName": "Deepgram Aura 2 (ES)", "family": "aura", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-es" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/deepgram/aura-2-es", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Deepgram Aura 2 (ES)" ], "families": [ "aura" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/deepgram/aura-2-es", "modelKey": "workers-ai/@cf/deepgram/aura-2-es", "displayName": "Deepgram Aura 2 (ES)", "family": "aura", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } } ] }, { "id": "cloudflare-ai-gateway/bart-large-cnn", "provider": "cloudflare-ai-gateway", "model": "bart-large-cnn", "displayName": "BART Large CNN", "family": "bart", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/facebook/bart-large-cnn" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/facebook/bart-large-cnn", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "BART Large CNN" ], "families": [ "bart" ], "releaseDate": "2025-04-09", "lastUpdated": "2025-04-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/facebook/bart-large-cnn", "modelKey": "workers-ai/@cf/facebook/bart-large-cnn", "displayName": "BART Large CNN", "family": "bart", "metadata": { "lastUpdated": "2025-04-09", "openWeights": false, "releaseDate": "2025-04-09" } } ] }, { "id": "cloudflare-ai-gateway/bge-base-en-v1.5", "provider": "cloudflare-ai-gateway", "model": "bge-base-en-v1.5", "displayName": "BGE Base EN v1.5", "family": "bge", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-base-en-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/baai/bge-base-en-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.067, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Base EN v1.5" ], "families": [ "bge" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/baai/bge-base-en-v1.5", "modelKey": "workers-ai/@cf/baai/bge-base-en-v1.5", "displayName": "BGE Base EN v1.5", "family": "bge", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "cloudflare-ai-gateway/bge-large-en-v1.5", "provider": "cloudflare-ai-gateway", "model": "bge-large-en-v1.5", "displayName": "BGE Large EN v1.5", "family": "bge", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-large-en-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/baai/bge-large-en-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Large EN v1.5" ], "families": [ "bge" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/baai/bge-large-en-v1.5", "modelKey": "workers-ai/@cf/baai/bge-large-en-v1.5", "displayName": "BGE Large EN v1.5", "family": "bge", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "cloudflare-ai-gateway/bge-m3", "provider": "cloudflare-ai-gateway", "model": "bge-m3", "displayName": "BGE M3", "family": "bge", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/baai/bge-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.012, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE M3" ], "families": [ "bge" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/baai/bge-m3", "modelKey": "workers-ai/@cf/baai/bge-m3", "displayName": "BGE M3", "family": "bge", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "cloudflare-ai-gateway/bge-reranker-base", "provider": "cloudflare-ai-gateway", "model": "bge-reranker-base", "displayName": "BGE Reranker Base", "family": "bge", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-reranker-base" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/baai/bge-reranker-base", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0031, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Reranker Base" ], "families": [ "bge" ], "releaseDate": "2025-04-09", "lastUpdated": "2025-04-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/baai/bge-reranker-base", "modelKey": "workers-ai/@cf/baai/bge-reranker-base", "displayName": "BGE Reranker Base", "family": "bge", "metadata": { "lastUpdated": "2025-04-09", "openWeights": false, "releaseDate": "2025-04-09" } } ] }, { "id": "cloudflare-ai-gateway/bge-small-en-v1.5", "provider": "cloudflare-ai-gateway", "model": "bge-small-en-v1.5", "displayName": "BGE Small EN v1.5", "family": "bge", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-small-en-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/baai/bge-small-en-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Small EN v1.5" ], "families": [ "bge" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/baai/bge-small-en-v1.5", "modelKey": "workers-ai/@cf/baai/bge-small-en-v1.5", "displayName": "BGE Small EN v1.5", "family": "bge", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "cloudflare-ai-gateway/distilbert-sst-2-int8", "provider": "cloudflare-ai-gateway", "model": "distilbert-sst-2-int8", "displayName": "DistilBERT SST-2 INT8", "family": "distilbert", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/huggingface/distilbert-sst-2-int8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/huggingface/distilbert-sst-2-int8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.026, "output": 0 } } ] }, "metadata": { "displayNames": [ "DistilBERT SST-2 INT8" ], "families": [ "distilbert" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/huggingface/distilbert-sst-2-int8", "modelKey": "workers-ai/@cf/huggingface/distilbert-sst-2-int8", "displayName": "DistilBERT SST-2 INT8", "family": "distilbert", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "cloudflare-ai-gateway/gemma-sea-lion-v4-27b-it", "provider": "cloudflare-ai-gateway", "model": "gemma-sea-lion-v4-27b-it", "displayName": "Gemma SEA-LION v4 27B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.56 } } ] }, "metadata": { "displayNames": [ "Gemma SEA-LION v4 27B IT" ], "families": [ "gemma" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", "modelKey": "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", "displayName": "Gemma SEA-LION v4 27B IT", "family": "gemma", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "cloudflare-ai-gateway/granite-4.0-h-micro", "provider": "cloudflare-ai-gateway", "model": "granite-4.0-h-micro", "displayName": "IBM Granite 4.0 H Micro", "family": "granite", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/ibm-granite/granite-4.0-h-micro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.017, "output": 0.11 } } ] }, "metadata": { "displayNames": [ "IBM Granite 4.0 H Micro" ], "families": [ "granite" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/ibm-granite/granite-4.0-h-micro", "modelKey": "workers-ai/@cf/ibm-granite/granite-4.0-h-micro", "displayName": "IBM Granite 4.0 H Micro", "family": "granite", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } } ] }, { "id": "cloudflare-ai-gateway/indictrans2-en-indic-1b", "provider": "cloudflare-ai-gateway", "model": "indictrans2-en-indic-1b", "displayName": "IndicTrans2 EN-Indic 1B", "family": "indictrans", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.34, "output": 0.34 } } ] }, "metadata": { "displayNames": [ "IndicTrans2 EN-Indic 1B" ], "families": [ "indictrans" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", "modelKey": "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", "displayName": "IndicTrans2 EN-Indic 1B", "family": "indictrans", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "cloudflare-ai-gateway/melotts", "provider": "cloudflare-ai-gateway", "model": "melotts", "displayName": "MyShell MeloTTS", "family": "melotts", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/myshell-ai/melotts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/myshell-ai/melotts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MyShell MeloTTS" ], "families": [ "melotts" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/myshell-ai/melotts", "modelKey": "workers-ai/@cf/myshell-ai/melotts", "displayName": "MyShell MeloTTS", "family": "melotts", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } } ] }, { "id": "cloudflare-ai-gateway/nemotron-3-120b-a12b", "provider": "cloudflare-ai-gateway", "model": "nemotron-3-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/nvidia/nemotron-3-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b", "modelKey": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "cloudflare-ai-gateway/plamo-embedding-1b", "provider": "cloudflare-ai-gateway", "model": "plamo-embedding-1b", "displayName": "PLaMo Embedding 1B", "family": "plamo", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/pfnet/plamo-embedding-1b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/pfnet/plamo-embedding-1b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.019, "output": 0 } } ] }, "metadata": { "displayNames": [ "PLaMo Embedding 1B" ], "families": [ "plamo" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/pfnet/plamo-embedding-1b", "modelKey": "workers-ai/@cf/pfnet/plamo-embedding-1b", "displayName": "PLaMo Embedding 1B", "family": "plamo", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "cloudflare-ai-gateway/smart-turn-v2", "provider": "cloudflare-ai-gateway", "model": "smart-turn-v2", "displayName": "Pipecat Smart Turn v2", "family": "smart-turn", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/pipecat-ai/smart-turn-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/pipecat-ai/smart-turn-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Pipecat Smart Turn v2" ], "families": [ "smart-turn" ], "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/pipecat-ai/smart-turn-v2", "modelKey": "workers-ai/@cf/pipecat-ai/smart-turn-v2", "displayName": "Pipecat Smart Turn v2", "family": "smart-turn", "metadata": { "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } } ] }, { "id": "cloudflare-workers-ai/gemma-sea-lion-v4-27b-it", "provider": "cloudflare-workers-ai", "model": "gemma-sea-lion-v4-27b-it", "displayName": "Gemma Sea Lion V4 27B It", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "cloudflare-workers-ai" ], "aliases": [ "cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/aisingapore/gemma-sea-lion-v4-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.351, "output": 0.555 } } ] }, "metadata": { "displayNames": [ "Gemma Sea Lion V4 27B It" ], "families": [ "gemma" ], "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/aisingapore/gemma-sea-lion-v4-27b-it", "modelKey": "@cf/aisingapore/gemma-sea-lion-v4-27b-it", "displayName": "Gemma Sea Lion V4 27B It", "family": "gemma", "metadata": { "lastUpdated": "2025-09-23", "openWeights": true, "releaseDate": "2025-09-23" } } ] }, { "id": "cloudflare-workers-ai/granite-4.0-h-micro", "provider": "cloudflare-workers-ai", "model": "granite-4.0-h-micro", "displayName": "Granite 4.0 H Micro", "family": "granite", "sources": [ "models.dev" ], "providers": [ "cloudflare-workers-ai" ], "aliases": [ "cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/ibm-granite/granite-4.0-h-micro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.017, "output": 0.112 } } ] }, "metadata": { "displayNames": [ "Granite 4.0 H Micro" ], "families": [ "granite" ], "releaseDate": "2025-10-07", "lastUpdated": "2025-10-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/ibm-granite/granite-4.0-h-micro", "modelKey": "@cf/ibm-granite/granite-4.0-h-micro", "displayName": "Granite 4.0 H Micro", "family": "granite", "metadata": { "lastUpdated": "2025-10-07", "openWeights": true, "releaseDate": "2025-10-07" } } ] }, { "id": "cloudflare-workers-ai/nemotron-3-120b-a12b", "provider": "cloudflare-workers-ai", "model": "nemotron-3-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "cloudflare-workers-ai" ], "aliases": [ "cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "interleaved": true, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/nvidia/nemotron-3-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/nvidia/nemotron-3-120b-a12b", "modelKey": "@cf/nvidia/nemotron-3-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "cohere/c4ai-aya-expanse-32b", "provider": "cohere", "model": "c4ai-aya-expanse-32b", "displayName": "Aya Expanse 32B", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/c4ai-aya-expanse-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Aya Expanse 32B" ], "releaseDate": "2024-10-24", "lastUpdated": "2024-10-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "c4ai-aya-expanse-32b", "modelKey": "c4ai-aya-expanse-32b", "displayName": "Aya Expanse 32B", "metadata": { "lastUpdated": "2024-10-24", "openWeights": true, "releaseDate": "2024-10-24" } } ] }, { "id": "cohere/c4ai-aya-expanse-8b", "provider": "cohere", "model": "c4ai-aya-expanse-8b", "displayName": "Aya Expanse 8B", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/c4ai-aya-expanse-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Aya Expanse 8B" ], "releaseDate": "2024-10-24", "lastUpdated": "2024-10-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "c4ai-aya-expanse-8b", "modelKey": "c4ai-aya-expanse-8b", "displayName": "Aya Expanse 8B", "metadata": { "lastUpdated": "2024-10-24", "openWeights": true, "releaseDate": "2024-10-24" } } ] }, { "id": "cohere/c4ai-aya-vision-32b", "provider": "cohere", "model": "c4ai-aya-vision-32b", "displayName": "Aya Vision 32B", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/c4ai-aya-vision-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Aya Vision 32B" ], "releaseDate": "2025-03-04", "lastUpdated": "2025-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "c4ai-aya-vision-32b", "modelKey": "c4ai-aya-vision-32b", "displayName": "Aya Vision 32B", "metadata": { "lastUpdated": "2025-05-14", "openWeights": true, "releaseDate": "2025-03-04" } } ] }, { "id": "cohere/c4ai-aya-vision-8b", "provider": "cohere", "model": "c4ai-aya-vision-8b", "displayName": "Aya Vision 8B", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/c4ai-aya-vision-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Aya Vision 8B" ], "releaseDate": "2025-03-04", "lastUpdated": "2025-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "c4ai-aya-vision-8b", "modelKey": "c4ai-aya-vision-8b", "displayName": "Aya Vision 8B", "metadata": { "lastUpdated": "2025-05-14", "openWeights": true, "releaseDate": "2025-03-04" } } ] }, { "id": "cohere/cohere-command-a", "provider": "cohere", "model": "cohere-command-a", "displayName": "Cohere Command A", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/cohere/cohere-command-a" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "cohere/cohere-command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere Command A" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-11-01", "lastUpdated": "2024-11-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "cohere/cohere-command-a", "modelKey": "cohere/cohere-command-a", "displayName": "Cohere Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } } ] }, { "id": "cohere/cohere-command-r", "provider": "cohere", "model": "cohere-command-r", "displayName": "Cohere Command R", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/cohere/cohere-command-r" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "cohere/cohere-command-r", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere Command R" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-03-11", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "cohere/cohere-command-r", "modelKey": "cohere/cohere-command-r", "displayName": "Cohere Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-03-11" } } ] }, { "id": "cohere/cohere-command-r-08-2024", "provider": "cohere", "model": "cohere-command-r-08-2024", "displayName": "Cohere Command R 08-2024", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/cohere/cohere-command-r-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "cohere/cohere-command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere Command R 08-2024" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-08-01", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "cohere/cohere-command-r-08-2024", "modelKey": "cohere/cohere-command-r-08-2024", "displayName": "Cohere Command R 08-2024", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "cohere/cohere-command-r-plus", "provider": "cohere", "model": "cohere-command-r-plus", "displayName": "Cohere Command R+", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/cohere/cohere-command-r-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "cohere/cohere-command-r-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere Command R+" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-04-04", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "cohere/cohere-command-r-plus", "modelKey": "cohere/cohere-command-r-plus", "displayName": "Cohere Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-04-04" } } ] }, { "id": "cohere/cohere-command-r-plus-08-2024", "provider": "cohere", "model": "cohere-command-r-plus-08-2024", "displayName": "Cohere Command R+ 08-2024", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/cohere/cohere-command-r-plus-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "cohere/cohere-command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere Command R+ 08-2024" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-08-01", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "cohere/cohere-command-r-plus-08-2024", "modelKey": "cohere/cohere-command-r-plus-08-2024", "displayName": "Cohere Command R+ 08-2024", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "cohere/command", "provider": "cohere", "model": "command", "mode": "completion", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/command" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "command", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "command", "mode": "completion" } ] }, { "id": "cohere/command-a", "provider": "cohere", "model": "command-a", "displayName": "Cohere: Command A", "family": "command-a", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter", "vercel", "vercel_ai_gateway" ], "aliases": [ "kilo/cohere/command-a", "openrouter/cohere/command-a", "vercel/cohere/command-a", "vercel_ai_gateway/cohere/command-a" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "cohere/command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "cohere/command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "cohere/command-a", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-a", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "cohere/command-a", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Cohere: Command A", "Command A" ], "families": [ "command", "command-a" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "cohere/command-a", "modelKey": "cohere/command-a", "displayName": "Cohere: Command A", "metadata": { "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cohere/command-a", "modelKey": "cohere/command-a", "displayName": "Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "cohere/command-a", "modelKey": "cohere/command-a", "displayName": "Command A", "family": "command", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-03-13", "openWeights": false, "releaseDate": "2025-03-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-a", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cohere/command-a", "displayName": "Cohere: Command A", "metadata": { "canonicalSlug": "cohere/command-a-03-2025", "createdAt": "2025-03-13T19:32:22.000Z", "huggingFaceId": "CohereForAI/c4ai-command-a-03-2025", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/cohere/command-a-03-2025/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 8192, "is_moderated": true } } } ] }, { "id": "cohere/command-a-03-2025", "provider": "cohere", "model": "command-a-03-2025", "displayName": "Command A", "family": "command-a", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cohere", "cohere_chat", "merge-gateway" ], "aliases": [ "cohere/command-a-03-2025", "cohere_chat/command-a-03-2025", "merge-gateway/cohere/command-a-03-2025" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-a-03-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "cohere/command-a-03-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-a-03-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command A" ], "families": [ "command-a" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-03-13", "lastUpdated": "2025-03-13", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-a-03-2025", "modelKey": "command-a-03-2025", "displayName": "Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "cohere/command-a-03-2025", "modelKey": "cohere/command-a-03-2025", "displayName": "Command A", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-a-03-2025", "mode": "chat" } ] }, { "id": "cohere/command-a-plus-05-2026", "provider": "cohere", "model": "command-a-plus-05-2026", "displayName": "Command A Plus", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "cohere", "nano-gpt" ], "aliases": [ "cohere/command-a-plus-05-2026", "nano-gpt/command-a-plus-05-2026" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-a-plus-05-2026", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "command-a-plus-05-2026", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Cohere Command A+ (05/2026)", "Command A Plus" ], "families": [ "command-a" ], "knowledgeCutoff": "2025-04-01", "releaseDate": "2026-05-20", "lastUpdated": "2026-06-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-a-plus-05-2026", "modelKey": "command-a-plus-05-2026", "displayName": "Command A Plus", "family": "command-a", "metadata": { "knowledgeCutoff": "2025-04-01", "lastUpdated": "2026-06-09", "openWeights": true, "releaseDate": "2026-05-20", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "command-a-plus-05-2026", "modelKey": "command-a-plus-05-2026", "displayName": "Cohere Command A+ (05/2026)", "metadata": { "lastUpdated": "2026-05-22", "openWeights": false, "releaseDate": "2026-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "cohere/command-a-reasoning-08-2025", "provider": "cohere", "model": "command-a-reasoning-08-2025", "displayName": "Command A Reasoning", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "cohere", "nano-gpt" ], "aliases": [ "cohere/command-a-reasoning-08-2025", "nano-gpt/command-a-reasoning-08-2025" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-a-reasoning-08-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "command-a-reasoning-08-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Cohere Command A (08/2025)", "Command A Reasoning" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-08-21", "lastUpdated": "2025-08-21", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-a-reasoning-08-2025", "modelKey": "command-a-reasoning-08-2025", "displayName": "Command A Reasoning", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 1 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "command-a-reasoning-08-2025", "modelKey": "command-a-reasoning-08-2025", "displayName": "Cohere Command A (08/2025)", "metadata": { "lastUpdated": "2025-08-22", "openWeights": false, "releaseDate": "2025-08-22" } } ] }, { "id": "cohere/command-a-translate-08-2025", "provider": "cohere", "model": "command-a-translate-08-2025", "displayName": "Command A Translate", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/command-a-translate-08-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-a-translate-08-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command A Translate" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-08-28", "lastUpdated": "2025-08-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-a-translate-08-2025", "modelKey": "command-a-translate-08-2025", "displayName": "Command A Translate", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28" } } ] }, { "id": "cohere/command-a-vision-07-2025", "provider": "cohere", "model": "command-a-vision-07-2025", "displayName": "Command A Vision", "family": "command-a", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/command-a-vision-07-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-a-vision-07-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Command A Vision" ], "families": [ "command-a" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-07-31", "lastUpdated": "2025-07-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-a-vision-07-2025", "modelKey": "command-a-vision-07-2025", "displayName": "Command A Vision", "family": "command-a", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-07-31", "openWeights": true, "releaseDate": "2025-07-31" } } ] }, { "id": "cohere/command-light", "provider": "cohere", "model": "command-light", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cohere_chat" ], "aliases": [ "cohere_chat/command-light" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere_chat", "model": "command-light", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-light", "mode": "chat" } ] }, { "id": "cohere/command-nightly", "provider": "cohere", "model": "command-nightly", "mode": "completion", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/command-nightly" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "command-nightly", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "command-nightly", "mode": "completion" } ] }, { "id": "cohere/command-r", "provider": "cohere", "model": "command-r", "displayName": "Cohere: Command R", "family": "command-r", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cohere_chat", "nano-gpt", "vercel_ai_gateway" ], "aliases": [ "cohere_chat/command-r", "nano-gpt/cohere/command-r", "vercel_ai_gateway/cohere/command-r" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "cohere/command-r", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.476, "output": 1.428 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-r", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-r", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Cohere: Command R" ], "families": [ "command-r" ], "modes": [ "chat" ], "releaseDate": "2024-03-11", "lastUpdated": "2024-03-11", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "cohere/command-r", "modelKey": "cohere/command-r", "displayName": "Cohere: Command R", "family": "command-r", "metadata": { "lastUpdated": "2024-03-11", "openWeights": false, "releaseDate": "2024-03-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-r", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-r", "mode": "chat" } ] }, { "id": "cohere/command-r-08-2024", "provider": "cohere", "model": "command-r-08-2024", "displayName": "Command R", "family": "command-r", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cohere", "cohere_chat", "kilo", "merge-gateway", "openrouter" ], "aliases": [ "cohere/command-r-08-2024", "cohere_chat/command-r-08-2024", "kilo/cohere/command-r-08-2024", "merge-gateway/cohere/command-r-08-2024", "openrouter/cohere/command-r-08-2024" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "kilo", "model": "cohere/command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "cohere/command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "cohere/command-r-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-r-08-2024", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "cohere/command-r-08-2024", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Cohere: Command R (08-2024)", "Command R" ], "families": [ "command-r" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-r-08-2024", "modelKey": "command-r-08-2024", "displayName": "Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "cohere/command-r-08-2024", "modelKey": "cohere/command-r-08-2024", "displayName": "Cohere: Command R (08-2024)", "metadata": { "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "cohere/command-r-08-2024", "modelKey": "cohere/command-r-08-2024", "displayName": "Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cohere/command-r-08-2024", "modelKey": "cohere/command-r-08-2024", "displayName": "Command R", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-r-08-2024", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cohere/command-r-08-2024", "displayName": "Cohere: Command R (08-2024)", "metadata": { "canonicalSlug": "cohere/command-r-08-2024", "createdAt": "2024-08-30T00:00:00.000Z", "knowledgeCutoff": "2024-03-31", "links": { "details": "/api/v1/models/cohere/command-r-08-2024/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Cohere", "topProvider": { "context_length": 128000, "max_completion_tokens": 4000, "is_moderated": true } } } ] }, { "id": "cohere/command-r-plus", "provider": "cohere", "model": "command-r-plus", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "cohere_chat", "vercel_ai_gateway" ], "aliases": [ "azure/command-r-plus", "cohere_chat/command-r-plus", "vercel_ai_gateway/cohere/command-r-plus" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/command-r-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-r-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-r-plus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/command-r-plus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-r-plus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/command-r-plus", "mode": "chat" } ] }, { "id": "cohere/command-r-plus-08-2024", "provider": "cohere", "model": "command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "cohere", "cohere_chat", "kilo", "merge-gateway", "nano-gpt", "openrouter" ], "aliases": [ "anyapi/cohere/command-r-plus-08-2024", "cohere/command-r-plus-08-2024", "cohere_chat/command-r-plus-08-2024", "kilo/cohere/command-r-plus-08-2024", "merge-gateway/cohere/command-r-plus-08-2024", "nano-gpt/cohere/command-r-plus-08-2024", "openrouter/cohere/command-r-plus-08-2024" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "cohere/command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "cohere/command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "cohere/command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.856, "output": 14.246 } }, { "source": "models.dev", "provider": "openrouter", "model": "cohere/command-r-plus-08-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-r-plus-08-2024", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "cohere/command-r-plus-08-2024", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Cohere: Command R+", "Cohere: Command R+ (08-2024)", "Command R+" ], "families": [ "command-r" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-08-30", "lastUpdated": "2024-08-30", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "cohere/command-r-plus-08-2024", "modelKey": "cohere/command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-r-plus-08-2024", "modelKey": "command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "cohere/command-r-plus-08-2024", "modelKey": "cohere/command-r-plus-08-2024", "displayName": "Cohere: Command R+ (08-2024)", "metadata": { "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "cohere/command-r-plus-08-2024", "modelKey": "cohere/command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "cohere/command-r-plus-08-2024", "modelKey": "cohere/command-r-plus-08-2024", "displayName": "Cohere: Command R+", "family": "command-r", "metadata": { "lastUpdated": "2024-08-30", "openWeights": false, "releaseDate": "2024-08-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cohere/command-r-plus-08-2024", "modelKey": "cohere/command-r-plus-08-2024", "displayName": "Command R+", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "openWeights": true, "releaseDate": "2024-08-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-r-plus-08-2024", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cohere/command-r-plus-08-2024", "displayName": "Cohere: Command R+ (08-2024)", "metadata": { "canonicalSlug": "cohere/command-r-plus-08-2024", "createdAt": "2024-08-30T00:00:00.000Z", "knowledgeCutoff": "2024-03-31", "links": { "details": "/api/v1/models/cohere/command-r-plus-08-2024/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Cohere", "topProvider": { "context_length": 128000, "max_completion_tokens": 4000, "is_moderated": true } } } ] }, { "id": "cohere/command-r7b-12-2024", "provider": "cohere", "model": "command-r7b-12-2024", "displayName": "Command R7B", "family": "command-r", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cohere", "cohere_chat", "kilo", "merge-gateway", "openrouter" ], "aliases": [ "cohere/command-r7b-12-2024", "cohere_chat/command-r7b-12-2024", "kilo/cohere/command-r7b-12-2024", "merge-gateway/cohere/command-r7b-12-2024", "openrouter/cohere/command-r7b-12-2024" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-r7b-12-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0375, "output": 0.15 } }, { "source": "models.dev", "provider": "kilo", "model": "cohere/command-r7b-12-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0375, "output": 0.15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "cohere/command-r7b-12-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0375, "output": 0.15 } }, { "source": "models.dev", "provider": "openrouter", "model": "cohere/command-r7b-12-2024", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0375, "output": 0.15 } }, { "source": "litellm", "provider": "cohere_chat", "model": "command-r7b-12-2024", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.0375 } }, { "source": "openrouter", "provider": "openrouter", "model": "cohere/command-r7b-12-2024", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.0375, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Cohere: Command R7B (12-2024)", "Command R7B" ], "families": [ "command-r" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2024-12-02", "lastUpdated": "2024-12-02", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-r7b-12-2024", "modelKey": "command-r7b-12-2024", "displayName": "Command R7B", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-12-02", "openWeights": true, "releaseDate": "2024-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "cohere/command-r7b-12-2024", "modelKey": "cohere/command-r7b-12-2024", "displayName": "Cohere: Command R7B (12-2024)", "metadata": { "lastUpdated": "2024-12-02", "openWeights": true, "releaseDate": "2024-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "cohere/command-r7b-12-2024", "modelKey": "cohere/command-r7b-12-2024", "displayName": "Command R7B", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-12-02", "openWeights": true, "releaseDate": "2024-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cohere/command-r7b-12-2024", "modelKey": "cohere/command-r7b-12-2024", "displayName": "Command R7B", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-12-02", "openWeights": true, "releaseDate": "2024-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere_chat", "model": "command-r7b-12-2024", "mode": "chat", "metadata": { "source": "https://docs.cohere.com/v2/docs/command-r7b" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cohere/command-r7b-12-2024", "displayName": "Cohere: Command R7B (12-2024)", "metadata": { "canonicalSlug": "cohere/command-r7b-12-2024", "createdAt": "2024-12-14T06:35:52.000Z", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/cohere/command-r7b-12-2024/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Cohere", "topProvider": { "context_length": 128000, "max_completion_tokens": 4000, "is_moderated": true } } } ] }, { "id": "cohere/command-r7b-arabic-02-2025", "provider": "cohere", "model": "command-r7b-arabic-02-2025", "displayName": "Command R7B Arabic", "family": "command-r", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/command-r7b-arabic-02-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "command-r7b-arabic-02-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0375, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Command R7B Arabic" ], "families": [ "command-r" ], "knowledgeCutoff": "2024-06-01", "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "command-r7b-arabic-02-2025", "modelKey": "command-r7b-arabic-02-2025", "displayName": "Command R7B Arabic", "family": "command-r", "metadata": { "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-02-27", "openWeights": true, "releaseDate": "2025-02-27" } } ] }, { "id": "cohere/embed-english-light-v2.0", "provider": "cohere", "model": "embed-english-light-v2.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-english-light-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-english-light-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-english-light-v2.0", "mode": "embedding" } ] }, { "id": "cohere/embed-english-light-v3.0", "provider": "cohere", "model": "embed-english-light-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-english-light-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-english-light-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-english-light-v3.0", "mode": "embedding" } ] }, { "id": "cohere/embed-english-v2.0", "provider": "cohere", "model": "embed-english-v2.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-english-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-english-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-english-v2.0", "mode": "embedding" } ] }, { "id": "cohere/embed-english-v3.0", "provider": "cohere", "model": "embed-english-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-english-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-english-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "perImage": { "input": 0.0001 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-english-v3.0", "mode": "embedding", "metadata": { "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." } } } ] }, { "id": "cohere/embed-multilingual-light-v3.0", "provider": "cohere", "model": "embed-multilingual-light-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-multilingual-light-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-multilingual-light-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 100, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-multilingual-light-v3.0", "mode": "embedding" } ] }, { "id": "cohere/embed-multilingual-v2.0", "provider": "cohere", "model": "embed-multilingual-v2.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-multilingual-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 768, "inputTokens": 768, "maxTokens": 768, "outputTokens": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-multilingual-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-multilingual-v2.0", "mode": "embedding" } ] }, { "id": "cohere/embed-multilingual-v3.0", "provider": "cohere", "model": "embed-multilingual-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/embed-multilingual-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "embed-multilingual-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "embed-multilingual-v3.0", "mode": "embedding" } ] }, { "id": "cohere/embed-v4.0", "provider": "cohere", "model": "embed-v4.0", "displayName": "Embed v4.0", "family": "cohere-embed", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "cohere", "vercel", "vercel_ai_gateway" ], "aliases": [ "cohere/embed-v4.0", "vercel/cohere/embed-v4.0", "vercel_ai_gateway/cohere/embed-v4.0" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "cohere/embed-v4.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/embed-v4.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "displayNames": [ "Embed v4.0" ], "families": [ "cohere-embed" ], "modes": [ "chat", "embedding" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "cohere/embed-v4.0", "modelKey": "cohere/embed-v4.0", "displayName": "Embed v4.0", "family": "cohere-embed", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "cohere/embed-v4.0", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/cohere/embed-v4.0", "mode": "chat" } ] }, { "id": "cohere/north-mini-code-1-0", "provider": "cohere", "model": "north-mini-code-1-0", "displayName": "North Mini Code", "family": "north", "sources": [ "models.dev" ], "providers": [ "cohere" ], "aliases": [ "cohere/north-mini-code-1-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cohere", "model": "north-mini-code-1-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "North Mini Code" ], "families": [ "north" ], "knowledgeCutoff": "2025-09-23", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cohere", "providerName": "Cohere", "providerDoc": "https://docs.cohere.com/docs/models", "model": "north-mini-code-1-0", "modelKey": "north-mini-code-1-0", "displayName": "North Mini Code", "family": "north", "metadata": { "knowledgeCutoff": "2025-09-23", "lastUpdated": "2026-06-09", "openWeights": true, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } } ] }, { "id": "cohere/north-mini-code:free", "provider": "cohere", "model": "north-mini-code:free", "displayName": "North Mini Code (free)", "family": "north", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/cohere/north-mini-code:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "cohere/north-mini-code:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "cohere/north-mini-code:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cohere: North Mini Code (free)", "North Mini Code (free)" ], "families": [ "north" ], "releaseDate": "2026-06-17", "lastUpdated": "2026-06-17", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cohere/north-mini-code:free", "modelKey": "cohere/north-mini-code:free", "displayName": "North Mini Code (free)", "family": "north", "metadata": { "lastUpdated": "2026-06-17", "openWeights": true, "releaseDate": "2026-06-17" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cohere/north-mini-code:free", "displayName": "Cohere: North Mini Code (free)", "metadata": { "canonicalSlug": "cohere/north-mini-code-20260617", "createdAt": "2026-06-17T19:15:48.000Z", "huggingFaceId": "CohereLabs/North-Mini-Code-1.0", "links": { "details": "/api/v1/models/cohere/north-mini-code-20260617/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Cohere", "topProvider": { "context_length": 256000, "max_completion_tokens": 64000, "is_moderated": true } } } ] }, { "id": "cohere/rerank-english-v2.0", "provider": "cohere", "model": "rerank-english-v2.0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/rerank-english-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "rerank-english-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "rerank-english-v2.0", "mode": "rerank" } ] }, { "id": "cohere/rerank-english-v3.0", "provider": "cohere", "model": "rerank-english-v3.0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/rerank-english-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "rerank-english-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "rerank-english-v3.0", "mode": "rerank" } ] }, { "id": "cohere/rerank-multilingual-v2.0", "provider": "cohere", "model": "rerank-multilingual-v2.0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/rerank-multilingual-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "rerank-multilingual-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "rerank-multilingual-v2.0", "mode": "rerank" } ] }, { "id": "cohere/rerank-multilingual-v3.0", "provider": "cohere", "model": "rerank-multilingual-v3.0", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "cohere" ], "aliases": [ "cohere/rerank-multilingual-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "rerank-multilingual-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "rerank-multilingual-v3.0", "mode": "rerank" } ] }, { "id": "cohere/rerank-v3.5", "provider": "cohere", "model": "rerank-v3.5", "displayName": "Cohere Rerank 3.5", "family": "o", "mode": "rerank", "sources": [ "litellm", "models.dev" ], "providers": [ "cohere", "vercel" ], "aliases": [ "cohere/rerank-v3.5", "vercel/cohere/rerank-v3.5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxQueryTokens": 2048, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cohere", "model": "rerank-v3.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0.002 } } ] }, "metadata": { "displayNames": [ "Cohere Rerank 3.5" ], "families": [ "o" ], "modes": [ "rerank" ], "releaseDate": "2024-12-02", "lastUpdated": "2024-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "cohere/rerank-v3.5", "modelKey": "cohere/rerank-v3.5", "displayName": "Cohere Rerank 3.5", "family": "o", "metadata": { "lastUpdated": "2024-12-02", "openWeights": false, "releaseDate": "2024-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cohere", "model": "rerank-v3.5", "mode": "rerank" } ] }, { "id": "cohere/rerank-v4-fast", "provider": "cohere", "model": "rerank-v4-fast", "displayName": "Cohere Rerank 4 Fast", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/cohere/rerank-v4-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Cohere Rerank 4 Fast" ], "families": [ "o" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "cohere/rerank-v4-fast", "modelKey": "cohere/rerank-v4-fast", "displayName": "Cohere Rerank 4 Fast", "family": "o", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "cohere/rerank-v4-pro", "provider": "cohere", "model": "rerank-v4-pro", "displayName": "Cohere Rerank 4 Pro", "family": "o", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/cohere/rerank-v4-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Cohere Rerank 4 Pro" ], "families": [ "o" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "cohere/rerank-v4-pro", "modelKey": "cohere/rerank-v4-pro", "displayName": "Cohere Rerank 4 Pro", "family": "o", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "cortecs/hermes-4-70b", "provider": "cortecs", "model": "hermes-4-70b", "displayName": "Hermes 4 70B", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/hermes-4-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "hermes-4-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.116, "output": 0.358 } } ] }, "metadata": { "displayNames": [ "Hermes 4 70B" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-08-26", "lastUpdated": "2025-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "hermes-4-70b", "modelKey": "hermes-4-70b", "displayName": "Hermes 4 70B", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-08-26", "openWeights": true, "releaseDate": "2025-08-26" } } ] }, { "id": "cortecs/intellect-3", "provider": "cortecs", "model": "intellect-3", "displayName": "INTELLECT 3", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/intellect-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "intellect-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.219, "output": 1.202 } } ] }, "metadata": { "displayNames": [ "INTELLECT 3" ], "knowledgeCutoff": "2025-11", "releaseDate": "2025-11-26", "lastUpdated": "2025-11-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "intellect-3", "modelKey": "intellect-3", "displayName": "INTELLECT 3", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-26", "openWeights": true, "releaseDate": "2025-11-26" } } ] }, { "id": "cortecs/nemotron-3-super-120b-a12b", "provider": "cortecs", "model": "nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B A12B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.266, "output": 0.799 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super 120B A12B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2025-12", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "nemotron-3-super-120b-a12b", "modelKey": "nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B A12B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "crof/gemma-4-31b-it", "provider": "crof", "model": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/gemma-4-31b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B IT" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "gemma-4-31b-it", "modelKey": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "crof/greg-1-mini", "provider": "crof", "model": "greg-1-mini", "displayName": "Greg 1 Mini", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/greg-1-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 229376, "outputTokens": 229376, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "greg-1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.07, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Greg 1 Mini" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "greg-1-mini", "modelKey": "greg-1-mini", "displayName": "Greg 1 Mini", "metadata": { "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27" } } ] }, { "id": "crof/greg-2-super", "provider": "crof", "model": "greg-2-super", "displayName": "Greg 2 Super", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/greg-2-super" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 229376, "outputTokens": 229376, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "greg-2-super", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 1.5, "output": 5 } } ] }, "metadata": { "displayNames": [ "Greg 2 Super" ], "releaseDate": "2026-06-14", "lastUpdated": "2026-06-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "greg-2-super", "modelKey": "greg-2-super", "displayName": "Greg 2 Super", "metadata": { "lastUpdated": "2026-06-14", "openWeights": false, "releaseDate": "2026-06-14" } } ] }, { "id": "crof/greg-2-ultra", "provider": "crof", "model": "greg-2-ultra", "displayName": "Greg 2 Ultra", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/greg-2-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 229376, "outputTokens": 229376, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "greg-2-ultra", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 3, "output": 10 } } ] }, "metadata": { "displayNames": [ "Greg 2 Ultra" ], "releaseDate": "2026-06-14", "lastUpdated": "2026-06-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "greg-2-ultra", "modelKey": "greg-2-ultra", "displayName": "Greg 2 Ultra", "metadata": { "lastUpdated": "2026-06-14", "openWeights": false, "releaseDate": "2026-06-14" } } ] }, { "id": "crof/greg-rp", "provider": "crof", "model": "greg-rp", "displayName": "Greg (Roleplay)", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/greg-rp" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 229376, "outputTokens": 229376, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "greg-rp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Greg (Roleplay)" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "greg-rp", "modelKey": "greg-rp", "displayName": "Greg (Roleplay)", "metadata": { "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27" } } ] }, { "id": "crof/mimo-v2.5-pro", "provider": "crof", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003, "input": 0.4, "output": 0.8 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "databricks/databricks-bge-large-en", "provider": "databricks", "model": "databricks-bge-large-en", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-bge-large-en" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-bge-large-en", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.10003, "output": 0 }, "extra": { "input_dbu_cost_per_token": 0.000001429, "output_dbu_cost_per_token": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-bge-large-en", "mode": "embedding", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-3-7-sonnet", "provider": "databricks", "model": "databricks-claude-3-7-sonnet", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-3-7-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-3-7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.99999, "output": 15.00002 }, "extra": { "input_dbu_cost_per_token": 0.000042857, "output_dbu_cost_per_token": 0.000214286 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-3-7-sonnet", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-haiku-4-5", "provider": "databricks", "model": "databricks-claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-haiku-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.00002, "output": 5.00003 }, "extra": { "input_dbu_cost_per_token": 0.000014286, "output_dbu_cost_per_token": 0.000071429 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5 (latest)" ], "families": [ "claude-haiku" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-haiku-4-5", "modelKey": "databricks-claude-haiku-4-5", "displayName": "Claude Haiku 4.5 (latest)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-haiku-4-5", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-opus-4", "provider": "databricks", "model": "databricks-claude-opus-4", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-opus-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-opus-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15.00002, "output": 75.00003 }, "extra": { "input_dbu_cost_per_token": 0.000214286, "output_dbu_cost_per_token": 0.001071429 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-opus-4", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-opus-4-1", "provider": "databricks", "model": "databricks-claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-opus-4-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-opus-4-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-opus-4-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15.00002, "output": 75.00003 }, "extra": { "input_dbu_cost_per_token": 0.000214286, "output_dbu_cost_per_token": 0.001071429 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.1 (latest)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-opus-4-1", "modelKey": "databricks-claude-opus-4-1", "displayName": "Claude Opus 4.1 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-opus-4-1", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-opus-4-5", "provider": "databricks", "model": "databricks-claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-opus-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-opus-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.00003, "output": 25.00001 }, "extra": { "input_dbu_cost_per_token": 0.000071429, "output_dbu_cost_per_token": 0.000357143 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5 (latest)" ], "families": [ "claude-opus" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-opus-4-5", "modelKey": "databricks-claude-opus-4-5", "displayName": "Claude Opus 4.5 (latest)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-opus-4-5", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-opus-4-6", "provider": "databricks", "model": "databricks-claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-opus-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-opus-4-6", "modelKey": "databricks-claude-opus-4-6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "databricks/databricks-claude-opus-4-7", "provider": "databricks", "model": "databricks-claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-opus-4-7", "modelKey": "databricks-claude-opus-4-7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "databricks/databricks-claude-sonnet-4", "provider": "databricks", "model": "databricks-claude-sonnet-4", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-sonnet-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.99999, "output": 15.00002 }, "extra": { "input_dbu_cost_per_token": 0.000042857, "output_dbu_cost_per_token": 0.000214286 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-sonnet-4", "modelKey": "databricks-claude-sonnet-4", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-sonnet-4-1", "provider": "databricks", "model": "databricks-claude-sonnet-4-1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-sonnet-4-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.99999, "output": 15.00002 }, "extra": { "input_dbu_cost_per_token": 0.000042857, "output_dbu_cost_per_token": 0.000214286 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4-1", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-sonnet-4-5", "provider": "databricks", "model": "databricks-claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-sonnet-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.99999, "output": 15.00002 }, "extra": { "input_dbu_cost_per_token": 0.000042857, "output_dbu_cost_per_token": 0.000214286 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5 (latest)" ], "families": [ "claude-sonnet" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-sonnet-4-5", "modelKey": "databricks-claude-sonnet-4-5", "displayName": "Claude Sonnet 4.5 (latest)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-claude-sonnet-4-5", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-claude-sonnet-4-6", "provider": "databricks", "model": "databricks-claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-claude-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-claude-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-claude-sonnet-4-6", "modelKey": "databricks-claude-sonnet-4-6", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "databricks/databricks-gemini-2-5-flash", "provider": "databricks", "model": "databricks-gemini-2-5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-2-5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65535, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-2-5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gemini-2-5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.30002, "output": 2.49998 }, "extra": { "input_dbu_cost_per_token": 0.000004285999999999999, "output_dbu_cost_per_token": 0.000035714 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash" ], "families": [ "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-2-5-flash", "modelKey": "databricks-gemini-2-5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gemini-2-5-flash", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gemini-2-5-pro", "provider": "databricks", "model": "databricks-gemini-2-5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-2-5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-2-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gemini-2-5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.24999, "output": 9.99999 }, "extra": { "input_dbu_cost_per_token": 0.000017857, "output_dbu_cost_per_token": 0.000142857 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro" ], "families": [ "gemini-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-2-5-pro", "modelKey": "databricks-gemini-2-5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gemini-2-5-pro", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gemini-3-1-flash-lite", "provider": "databricks", "model": "databricks-gemini-3-1-flash-lite", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-3-1-flash-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-3-1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Lite Preview" ], "families": [ "gemini-flash-lite" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-3-1-flash-lite", "modelKey": "databricks-gemini-3-1-flash-lite", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } } ] }, { "id": "databricks/databricks-gemini-3-1-pro", "provider": "databricks", "model": "databricks-gemini-3-1-pro", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-3-1-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-3-1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro Preview Custom Tools" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "lastUpdated": "2026-02-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-3-1-pro", "modelKey": "databricks-gemini-3-1-pro", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } } ] }, { "id": "databricks/databricks-gemini-3-flash", "provider": "databricks", "model": "databricks-gemini-3-flash", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-3-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-3-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Flash Preview" ], "families": [ "gemini-flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-3-flash", "modelKey": "databricks-gemini-3-flash", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } } ] }, { "id": "databricks/databricks-gemini-3-pro", "provider": "databricks", "model": "databricks-gemini-3-pro", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemini-3-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gemini-3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Gemini 3 Pro Preview" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-11-18", "lastUpdated": "2025-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gemini-3-pro", "modelKey": "databricks-gemini-3-pro", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } } ] }, { "id": "databricks/databricks-gemma-3-12b", "provider": "databricks", "model": "databricks-gemma-3-12b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gemma-3-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gemma-3-12b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15001, "output": 0.50001 }, "extra": { "input_dbu_cost_per_token": 0.0000021429999999999996, "output_dbu_cost_per_token": 0.000007143 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gemma-3-12b", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-5", "provider": "databricks", "model": "databricks-gpt-5", "displayName": "GPT-5", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.24999, "output": 9.99999 }, "extra": { "input_dbu_cost_per_token": 0.000017857, "output_dbu_cost_per_token": 0.000142857 } } ] }, "metadata": { "displayNames": [ "GPT-5" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5", "modelKey": "databricks-gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-5", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-5-1", "provider": "databricks", "model": "databricks-gpt-5-1", "displayName": "GPT-5.1", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-5-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.24999, "output": 9.99999 }, "extra": { "input_dbu_cost_per_token": 0.000017857, "output_dbu_cost_per_token": 0.000142857 } } ] }, "metadata": { "displayNames": [ "GPT-5.1" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-1", "modelKey": "databricks-gpt-5-1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-5-1", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-5-2", "provider": "databricks", "model": "databricks-gpt-5-2", "displayName": "GPT-5.2", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.2" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-2", "modelKey": "databricks-gpt-5-2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "databricks/databricks-gpt-5-4", "provider": "databricks", "model": "databricks-gpt-5-4", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-4", "modelKey": "databricks-gpt-5-4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } } ] }, { "id": "databricks/databricks-gpt-5-4-mini", "provider": "databricks", "model": "databricks-gpt-5-4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-4-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 mini" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-4-mini", "modelKey": "databricks-gpt-5-4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "databricks/databricks-gpt-5-4-nano", "provider": "databricks", "model": "databricks-gpt-5-4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-4-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 nano" ], "families": [ "gpt-nano" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-4-nano", "modelKey": "databricks-gpt-5-4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "databricks/databricks-gpt-5-5", "provider": "databricks", "model": "databricks-gpt-5-5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-5", "modelKey": "databricks-gpt-5-5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "databricks/databricks-gpt-5-mini", "provider": "databricks", "model": "databricks-gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.24997, "output": 1.99997 }, "extra": { "input_dbu_cost_per_token": 0.000003571, "output_dbu_cost_per_token": 0.000028571 } } ] }, "metadata": { "displayNames": [ "GPT-5 Mini" ], "families": [ "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-mini", "modelKey": "databricks-gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-5-mini", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-5-nano", "provider": "databricks", "model": "databricks-gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-5-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04998, "output": 0.39998 }, "extra": { "input_dbu_cost_per_token": 7.14e-7, "output_dbu_cost_per_token": 0.000005714000000000001 } } ] }, "metadata": { "displayNames": [ "GPT-5 Nano" ], "families": [ "gpt-nano" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-5-nano", "modelKey": "databricks-gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-5-nano", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-oss-120b", "provider": "databricks", "model": "databricks-gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-oss-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.28 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15001, "output": 0.59997 }, "extra": { "input_dbu_cost_per_token": 0.0000021429999999999996, "output_dbu_cost_per_token": 0.000008571 } } ] }, "metadata": { "displayNames": [ "GPT OSS 120B" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-oss-120b", "modelKey": "databricks-gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-oss-120b", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-gpt-oss-20b", "provider": "databricks", "model": "databricks-gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gpt-oss-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "databricks", "model": "databricks-gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.30002 }, "extra": { "input_dbu_cost_per_token": 0.000001, "output_dbu_cost_per_token": 0.000004285999999999999 } } ] }, "metadata": { "displayNames": [ "GPT OSS 20B" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "databricks", "providerName": "Databricks", "providerApi": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "providerDoc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "model": "databricks-gpt-oss-20b", "modelKey": "databricks-gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gpt-oss-20b", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-gte-large-en", "provider": "databricks", "model": "databricks-gte-large-en", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-gte-large-en" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-gte-large-en", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12999, "output": 0 }, "extra": { "input_dbu_cost_per_token": 0.000001857, "output_dbu_cost_per_token": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-gte-large-en", "mode": "embedding", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-llama-2-70b-chat", "provider": "databricks", "model": "databricks-llama-2-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-llama-2-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-llama-2-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.50001, "output": 1.50003 }, "extra": { "input_dbu_cost_per_token": 0.000007143, "output_dbu_cost_per_token": 0.000021429 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-llama-2-70b-chat", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-llama-4-maverick", "provider": "databricks", "model": "databricks-llama-4-maverick", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-llama-4-maverick" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-llama-4-maverick", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.50001, "output": 1.50003 }, "extra": { "input_dbu_cost_per_token": 0.000007143, "output_dbu_cost_per_token": 0.000021429 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-llama-4-maverick", "mode": "chat", "metadata": { "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-meta-llama-3-1-405b-instruct", "provider": "databricks", "model": "databricks-meta-llama-3-1-405b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-meta-llama-3-1-405b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-1-405b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.00003, "output": 15.00002 }, "extra": { "input_dbu_cost_per_token": 0.000071429, "output_dbu_cost_per_token": 0.000214286 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-1-405b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-meta-llama-3-1-8b-instruct", "provider": "databricks", "model": "databricks-meta-llama-3-1-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-meta-llama-3-1-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15001, "output": 0.45003 }, "extra": { "input_dbu_cost_per_token": 0.0000021429999999999996, "output_dbu_cost_per_token": 0.000006429000000000001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-1-8b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-meta-llama-3-3-70b-instruct", "provider": "databricks", "model": "databricks-meta-llama-3-3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-meta-llama-3-3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.50001, "output": 1.50003 }, "extra": { "input_dbu_cost_per_token": 0.000007143, "output_dbu_cost_per_token": 0.000021429 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-3-70b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-meta-llama-3-70b-instruct", "provider": "databricks", "model": "databricks-meta-llama-3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-meta-llama-3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.00002, "output": 2.99999 }, "extra": { "input_dbu_cost_per_token": 0.000014286, "output_dbu_cost_per_token": 0.000042857 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-meta-llama-3-70b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-mixtral-8x7b-instruct", "provider": "databricks", "model": "databricks-mixtral-8x7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-mixtral-8x7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-mixtral-8x7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.50001, "output": 1.00002 }, "extra": { "input_dbu_cost_per_token": 0.000007143, "output_dbu_cost_per_token": 0.000014286 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-mixtral-8x7b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-mpt-30b-instruct", "provider": "databricks", "model": "databricks-mpt-30b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-mpt-30b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-mpt-30b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.00002, "output": 1.00002 }, "extra": { "input_dbu_cost_per_token": 0.000014286, "output_dbu_cost_per_token": 0.000014286 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-mpt-30b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "databricks/databricks-mpt-7b-instruct", "provider": "databricks", "model": "databricks-mpt-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "databricks" ], "aliases": [ "databricks/databricks-mpt-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "databricks", "model": "databricks/databricks-mpt-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.50001, "output": 0 }, "extra": { "input_dbu_cost_per_token": 0.000007143, "output_dbu_cost_per_token": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "databricks", "model": "databricks/databricks-mpt-7b-instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" } } ] }, { "id": "dataforseo/search", "provider": "dataforseo", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "dataforseo" ], "aliases": [ "dataforseo/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "dataforseo", "model": "dataforseo/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.003 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "dataforseo", "model": "dataforseo/search", "mode": "search" } ] }, { "id": "deepgram/base", "provider": "deepgram", "model": "base", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-conversationalai", "provider": "deepgram", "model": "base-conversationalai", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-conversationalai" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-conversationalai", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-conversationalai", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-finance", "provider": "deepgram", "model": "base-finance", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-finance" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-finance", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-finance", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-general", "provider": "deepgram", "model": "base-general", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-general" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-general", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-general", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-meeting", "provider": "deepgram", "model": "base-meeting", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-meeting" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-meeting", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-meeting", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-phonecall", "provider": "deepgram", "model": "base-phonecall", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-phonecall" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-phonecall", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-phonecall", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-video", "provider": "deepgram", "model": "base-video", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-video" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-video", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-video", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/base-voicemail", "provider": "deepgram", "model": "base-voicemail", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/base-voicemail" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/base-voicemail", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00020833 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/base-voicemail", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/enhanced", "provider": "deepgram", "model": "enhanced", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/enhanced" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/enhanced", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00024167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/enhanced", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/enhanced-finance", "provider": "deepgram", "model": "enhanced-finance", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/enhanced-finance" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/enhanced-finance", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00024167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/enhanced-finance", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/enhanced-general", "provider": "deepgram", "model": "enhanced-general", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/enhanced-general" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/enhanced-general", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00024167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/enhanced-general", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/enhanced-meeting", "provider": "deepgram", "model": "enhanced-meeting", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/enhanced-meeting" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/enhanced-meeting", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00024167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/enhanced-meeting", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/enhanced-phonecall", "provider": "deepgram", "model": "enhanced-phonecall", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/enhanced-phonecall" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/enhanced-phonecall", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00024167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/enhanced-phonecall", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/nova", "provider": "deepgram", "model": "nova", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/nova" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/nova", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00007167 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/nova", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepgram/whisper", "provider": "deepgram", "model": "whisper", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "deepinfra/hermes-3-llama-3.1-405b", "provider": "deepinfra", "model": "hermes-3-llama-3.1-405b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "mode": "chat" } ] }, { "id": "deepinfra/hermes-3-llama-3.1-70b", "provider": "deepinfra", "model": "hermes-3-llama-3.1-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "mode": "chat" } ] }, { "id": "deepinfra/l3-8b-lunaris-v1-turbo", "provider": "deepinfra", "model": "l3-8b-lunaris-v1-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.05 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo", "mode": "chat" } ] }, { "id": "deepinfra/l3.1-70b-euryale-v2.2", "provider": "deepinfra", "model": "l3.1-70b-euryale-v2.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2", "mode": "chat" } ] }, { "id": "deepinfra/l3.3-70b-euryale-v2.3", "provider": "deepinfra", "model": "l3.3-70b-euryale-v2.3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3", "mode": "chat" } ] }, { "id": "deepinfra/mimo-v2.5", "provider": "deepinfra", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/XiaomiMiMo/MiMo-V2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "deepinfra", "model": "XiaomiMiMo/MiMo-V2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 }, "tiered": { "contextOver200K": { "input": 0.8, "output": 4, "cache_read": 0.16 }, "tiers": [ { "input": 0.8, "output": 4, "cache_read": 0.16, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "XiaomiMiMo/MiMo-V2.5", "modelKey": "XiaomiMiMo/MiMo-V2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepinfra/mimo-v2.5-pro", "provider": "deepinfra", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "deepinfra", "model": "XiaomiMiMo/MiMo-V2.5-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "XiaomiMiMo/MiMo-V2.5-Pro", "modelKey": "XiaomiMiMo/MiMo-V2.5-Pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepinfra/mythomax-l2-13b", "provider": "deepinfra", "model": "mythomax-l2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/Gryphe/MythoMax-L2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/Gryphe/MythoMax-L2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.09 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/Gryphe/MythoMax-L2-13b", "mode": "chat" } ] }, { "id": "deepinfra/nvidia-nemotron-nano-9b-v2", "provider": "deepinfra", "model": "nvidia-nemotron-nano-9b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.16 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "mode": "chat" } ] }, { "id": "deepinfra/olmocr-7b-0725-fp8", "provider": "deepinfra", "model": "olmocr-7b-0725-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/allenai/olmOCR-7B-0725-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/allenai/olmOCR-7B-0725-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/allenai/olmOCR-7B-0725-FP8", "mode": "chat" } ] }, { "id": "deepinfra/phi-4", "provider": "deepinfra", "model": "phi-4", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/microsoft/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/microsoft/phi-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.14 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/microsoft/phi-4", "mode": "chat" } ] }, { "id": "deepinfra/wizardlm-2-8x22b", "provider": "deepinfra", "model": "wizardlm-2-8x22b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/microsoft/WizardLM-2-8x22B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/microsoft/WizardLM-2-8x22B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.48, "output": 0.48 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/microsoft/WizardLM-2-8x22B", "mode": "chat" } ] }, { "id": "deepseek/deepseek-3.2", "provider": "deepseek", "model": "deepseek-3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/deepseek-3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "deepseek-3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2" ], "families": [ "deepseek" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-02", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "deepseek-3.2", "modelKey": "deepseek-3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-12-02", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "deepseek/deepseek-4-flash", "provider": "deepseek", "model": "deepseek-4-flash", "displayName": "Deepseek V4 Flash", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/deepseek-4-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Deepseek V4 Flash" ], "families": [ "deepseek" ], "releaseDate": "2026-05-27", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "deepseek-4-flash", "modelKey": "deepseek-4-flash", "displayName": "Deepseek V4 Flash", "family": "deepseek", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-27" } } ] }, { "id": "deepseek/deepseek-chat", "provider": "deepseek", "model": "deepseek-chat", "displayName": "DeepSeek Chat", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "anyapi", "deepseek", "kilo", "nano-gpt", "openrouter", "orcarouter", "zenmux" ], "aliases": [ "302ai/deepseek-chat", "anyapi/deepseek/deepseek-chat", "deepseek/deepseek-chat", "kilo/deepseek/deepseek-chat", "nano-gpt/deepseek-chat", "openrouter/deepseek/deepseek-chat", "orcarouter/deepseek/deepseek-chat", "zenmux/deepseek/deepseek-chat" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1000000, "inputTokens": 131072, "maxTokens": 8192, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "assistantPrefill": true, "supports1MContext": true, "structuredOutput": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.43 } }, { "source": "models.dev", "provider": "deepseek", "model": "deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.32, "output": 0.89 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.7 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2002, "output": 0.8001 } }, { "source": "models.dev", "provider": "orcarouter", "model": "deepseek/deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "zenmux", "model": "deepseek/deepseek-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.28, "output": 0.42 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "input": 0.28, "output": 0.42 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "cacheWrite": 0, "input": 0.28, "output": 0.42 }, "extra": { "input_cost_per_token_cache_hit": 2.8e-8 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.28 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-chat", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2002, "output": 0.8001 } } ] }, "metadata": { "displayNames": [ "DeepSeek Chat", "DeepSeek V3/Deepseek Chat", "DeepSeek-V3.2 (Non-thinking Mode)", "DeepSeek: DeepSeek V3", "Deepseek-Chat" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-11-29", "lastUpdated": "2024-11-29", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "deepseek-chat", "modelKey": "deepseek-chat", "displayName": "Deepseek-Chat", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-11-29", "openWeights": false, "releaseDate": "2024-11-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "deepseek/deepseek-chat", "modelKey": "deepseek/deepseek-chat", "displayName": "DeepSeek Chat", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepseek", "providerName": "DeepSeek", "providerApi": "https://api.deepseek.com", "providerDoc": "https://api-docs.deepseek.com/quick_start/pricing", "model": "deepseek-chat", "modelKey": "deepseek-chat", "displayName": "DeepSeek Chat", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-chat", "modelKey": "deepseek/deepseek-chat", "displayName": "DeepSeek: DeepSeek V3", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-chat", "modelKey": "deepseek-chat", "displayName": "DeepSeek V3/Deepseek Chat", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-chat", "modelKey": "deepseek/deepseek-chat", "displayName": "DeepSeek Chat", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "deepseek/deepseek-chat", "modelKey": "deepseek/deepseek-chat", "displayName": "DeepSeek Chat", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "deepseek/deepseek-chat", "modelKey": "deepseek/deepseek-chat", "displayName": "DeepSeek-V3.2 (Non-thinking Mode)", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek-chat", "mode": "chat", "metadata": { "source": "https://api-docs.deepseek.com/quick_start/pricing", "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-chat", "mode": "chat", "metadata": { "source": "https://api-docs.deepseek.com/quick_start/pricing", "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-chat", "displayName": "DeepSeek: DeepSeek V3", "metadata": { "canonicalSlug": "deepseek/deepseek-chat-v3", "createdAt": "2024-12-26T19:28:40.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3", "knowledgeCutoff": "2024-07-31", "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 128000, "max_completion_tokens": 16000, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-chat-cheaper", "provider": "deepseek", "model": "deepseek-chat-cheaper", "displayName": "DeepSeek V3/Chat Cheaper", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek-chat-cheaper" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-chat-cheaper", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3/Chat Cheaper" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-chat-cheaper", "modelKey": "deepseek-chat-cheaper", "displayName": "DeepSeek V3/Chat Cheaper", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "deepseek/deepseek-chat-v3-0324", "provider": "deepseek", "model": "deepseek-chat-v3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/deepseek/deepseek-chat-v3-0324", "openrouter/deepseek/deepseek-chat-v3-0324" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 65536, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-chat-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.095, "input": 0.2, "output": 0.77 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.2, "output": 0.77 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat-v3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.28 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3-0324", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.135, "input": 0.2, "output": 0.77 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3 0324", "DeepSeek: DeepSeek V3 0324" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07-31", "releaseDate": "2025-03-24", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-chat-v3-0324", "modelKey": "deepseek/deepseek-chat-v3-0324", "displayName": "DeepSeek: DeepSeek V3 0324", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-chat-v3-0324", "modelKey": "deepseek/deepseek-chat-v3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat-v3-0324", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3-0324", "displayName": "DeepSeek: DeepSeek V3 0324", "metadata": { "canonicalSlug": "deepseek/deepseek-chat-v3-0324", "createdAt": "2025-03-24T13:59:15.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3-0324", "knowledgeCutoff": "2024-07-31", "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 163840, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-chat-v3.1", "provider": "deepseek", "model": "deepseek-chat-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/deepseek/deepseek-chat-v3.1", "openrouter/deepseek/deepseek-chat-v3.1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-chat-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.75 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 0.21, "output": 0.79 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat-v3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.8 }, "extra": { "input_cost_per_token_cache_hit": 2e-8 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "input": 0.21, "output": 0.79 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1", "DeepSeek: DeepSeek V3.1" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-21", "lastUpdated": "2025-08-21", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-chat-v3.1", "modelKey": "deepseek/deepseek-chat-v3.1", "displayName": "DeepSeek: DeepSeek V3.1", "metadata": { "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-chat-v3.1", "modelKey": "deepseek/deepseek-chat-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-chat-v3.1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-chat-v3.1", "displayName": "DeepSeek: DeepSeek V3.1", "metadata": { "canonicalSlug": "deepseek/deepseek-chat-v3.1", "createdAt": "2025-08-21T12:33:48.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3.1", "instructType": "deepseek-v3.1", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 163840, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-coder", "provider": "deepseek", "model": "deepseek-coder", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepseek" ], "aliases": [ "deepseek/deepseek-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-coder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.28 }, "extra": { "input_cost_per_token_cache_hit": 1.4e-8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-coder", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-1b-base", "provider": "deepseek", "model": "deepseek-coder-1b-base", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-33b-instruct", "provider": "deepseek", "model": "deepseek-coder-33b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-6.7b", "provider": "deepseek", "model": "deepseek-coder-6.7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/deepseek-coder-6.7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/deepseek-coder-6.7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.12 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/deepseek-coder-6.7b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-7b-base", "provider": "deepseek", "model": "deepseek-coder-7b-base", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-7b-base-v1p5", "provider": "deepseek", "model": "deepseek-coder-7b-base-v1p5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-7b-instruct-v1p5", "provider": "deepseek", "model": "deepseek-coder-7b-instruct-v1p5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-v2-base", "provider": "deepseek", "model": "deepseek-coder-v2-base", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/deepseek-coder-v2-base" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/deepseek-coder-v2-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/deepseek-coder-v2-base", "mode": "completion" } ] }, { "id": "deepseek/deepseek-coder-v2-instruct", "provider": "deepseek", "model": "deepseek-coder-v2-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "ollama" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "ollama/deepseek-coder-v2-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/deepseek-coder-v2-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/deepseek-coder-v2-instruct", "mode": "chat" } ] }, { "id": "deepseek/deepseek-coder-v2-lite-base", "provider": "deepseek", "model": "deepseek-coder-v2-lite-base", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "ollama" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base", "ollama/deepseek-coder-v2-lite-base" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "functionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/deepseek-coder-v2-lite-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat", "completion" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/deepseek-coder-v2-lite-base", "mode": "completion" } ] }, { "id": "deepseek/deepseek-coder-v2-lite-instruct", "provider": "deepseek", "model": "deepseek-coder-v2-lite-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "ollama" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct", "ollama/deepseek-coder-v2-lite-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "functionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/deepseek-coder-v2-lite-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/deepseek-coder-v2-lite-instruct", "mode": "chat" } ] }, { "id": "deepseek/deepseek-latest", "provider": "deepseek", "model": "deepseek-latest", "displayName": "DeepSeek Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek/deepseek-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "DeepSeek Latest" ], "releaseDate": "2026-05-03", "lastUpdated": "2026-05-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-latest", "modelKey": "deepseek/deepseek-latest", "displayName": "DeepSeek Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03" } } ] }, { "id": "deepseek/deepseek-llama3.3-70b", "provider": "deepseek", "model": "deepseek-llama3.3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/deepseek-llama3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/deepseek-llama3.3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/deepseek-llama3.3-70b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-math-v2", "provider": "deepseek", "model": "deepseek-math-v2", "displayName": "DeepSeek Math V2", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "qiniu-ai" ], "aliases": [ "nano-gpt/deepseek-math-v2", "qiniu-ai/deepseek/deepseek-math-v2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 160000, "inputTokens": 128000, "outputTokens": 160000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-math-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "DeepSeek Math V2", "Deepseek/Deepseek-Math-V2" ], "releaseDate": "2025-12-03", "lastUpdated": "2025-12-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-math-v2", "modelKey": "deepseek-math-v2", "displayName": "DeepSeek Math V2", "metadata": { "lastUpdated": "2025-12-03", "openWeights": false, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-math-v2", "modelKey": "deepseek/deepseek-math-v2", "displayName": "Deepseek/Deepseek-Math-V2", "metadata": { "lastUpdated": "2025-12-04", "openWeights": false, "releaseDate": "2025-12-04" } } ] }, { "id": "deepseek/deepseek-ocr", "provider": "deepseek", "model": "deepseek-ocr", "displayName": "DeepSeek OCR", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "clarifai", "novita", "novita-ai", "siliconflow-cn" ], "aliases": [ "clarifai/deepseek-ai/deepseek-ocr/models/DeepSeek-OCR", "novita-ai/deepseek/deepseek-ocr", "novita/deepseek/deepseek-ocr", "siliconflow-cn/deepseek-ai/DeepSeek-OCR" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.7 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-ocr", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.03 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-OCR", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-ocr", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "DeepSeek OCR", "DeepSeek-OCR", "deepseek-ai/DeepSeek-OCR" ], "families": [ "deepseek" ], "modes": [ "chat" ], "releaseDate": "2025-10-20", "lastUpdated": "2026-02-25", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR", "modelKey": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR", "displayName": "DeepSeek OCR", "family": "deepseek", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-10-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-ocr", "modelKey": "deepseek/deepseek-ocr", "displayName": "DeepSeek-OCR", "metadata": { "lastUpdated": "2025-10-24", "openWeights": true, "releaseDate": "2025-10-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-OCR", "modelKey": "deepseek-ai/DeepSeek-OCR", "displayName": "deepseek-ai/DeepSeek-OCR", "metadata": { "lastUpdated": "2025-10-20", "openWeights": true, "releaseDate": "2025-10-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-ocr", "mode": "chat" } ] }, { "id": "deepseek/deepseek-ocr-2", "provider": "deepseek", "model": "deepseek-ocr-2", "displayName": "deepseek/deepseek-ocr-2", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/deepseek/deepseek-ocr-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-ocr-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "deepseek/deepseek-ocr-2" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-ocr-2", "modelKey": "deepseek/deepseek-ocr-2", "displayName": "deepseek/deepseek-ocr-2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } } ] }, { "id": "deepseek/deepseek-ocr-maas", "provider": "deepseek", "model": "deepseek-ocr-maas", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "vertex_ai" ], "aliases": [ "vertex_ai/deepseek-ai/deepseek-ocr-maas" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/deepseek-ai/deepseek-ocr-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 }, "perPage": { "ocr": 0.0003 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedRegions": [ "us-central1" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/deepseek-ai/deepseek-ocr-maas", "mode": "ocr", "metadata": { "source": "https://cloud.google.com/vertex-ai/pricing", "supportedRegions": [ "us-central1" ] } } ] }, { "id": "deepseek/deepseek-prover-v2", "provider": "deepseek", "model": "deepseek-prover-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2", "mode": "chat" } ] }, { "id": "deepseek/deepseek-prover-v2-671b", "provider": "deepseek", "model": "deepseek-prover-v2-671b", "displayName": "DeepSeek Prover v2 671B", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "nano-gpt", "novita", "novita-ai" ], "aliases": [ "nano-gpt/deepseek/deepseek-prover-v2-671b", "novita-ai/deepseek/deepseek-prover-v2-671b", "novita/deepseek/deepseek-prover-v2-671b" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 160000, "inputTokens": 160000, "maxTokens": 160000, "outputTokens": 160000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "temperature": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-prover-v2-671b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-prover-v2-671b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.5 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-prover-v2-671b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "DeepSeek Prover v2 671B", "Deepseek Prover V2 671B" ], "families": [ "deepseek" ], "modes": [ "chat" ], "releaseDate": "2025-04-30", "lastUpdated": "2025-04-30", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-prover-v2-671b", "modelKey": "deepseek/deepseek-prover-v2-671b", "displayName": "DeepSeek Prover v2 671B", "family": "deepseek", "metadata": { "lastUpdated": "2025-04-30", "openWeights": false, "releaseDate": "2025-04-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-prover-v2-671b", "modelKey": "deepseek/deepseek-prover-v2-671b", "displayName": "Deepseek Prover V2 671B", "metadata": { "lastUpdated": "2025-04-30", "openWeights": true, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-prover-v2-671b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1", "provider": "deepseek", "model": "deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "alibaba-cn", "anyapi", "azure", "azure-cognitive-services", "azure_ai", "deepinfra", "deepseek", "drun", "fireworks_ai", "github-models", "hyperbolic", "iflowcn", "kilo", "nano-gpt", "nebius", "openrouter", "qiniu-ai", "replicate", "sambanova", "siliconflow", "siliconflow-cn", "snowflake", "snowflake-cortex", "synthetic", "together_ai", "togetherai", "vercel", "vercel_ai_gateway" ], "aliases": [ "abacus/deepseek-ai/DeepSeek-R1", "alibaba-cn/deepseek-r1", "anyapi/deepseek/deepseek-r1", "azure-cognitive-services/deepseek-r1", "azure/deepseek-r1", "azure_ai/deepseek-r1", "deepinfra/deepseek-ai/DeepSeek-R1", "deepseek/deepseek-r1", "drun/public/deepseek-r1", "fireworks_ai/accounts/fireworks/models/deepseek-r1", "github-models/deepseek/deepseek-r1", "hyperbolic/deepseek-ai/DeepSeek-R1", "iflowcn/deepseek-r1", "kilo/deepseek/deepseek-r1", "nano-gpt/deepseek-r1", "nebius/deepseek-ai/DeepSeek-R1", "openrouter/deepseek/deepseek-r1", "qiniu-ai/deepseek-r1", "replicate/deepseek-ai/deepseek-r1", "sambanova/DeepSeek-R1", "siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1", "siliconflow-cn/deepseek-ai/DeepSeek-R1", "siliconflow/deepseek-ai/DeepSeek-R1", "snowflake-cortex/deepseek-r1", "snowflake/deepseek-r1", "synthetic/hf:deepseek-ai/DeepSeek-R1", "together_ai/deepseek-ai/DeepSeek-R1", "togetherai/deepseek-ai/DeepSeek-R1", "vercel/deepseek/deepseek-r1", "vercel_ai_gateway/deepseek/deepseek-r1" ], "mergedProviderModelRecords": 30, "limits": { "contextTokens": 1000000, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true, "attachments": true, "openWeights": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 7 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 2.294 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "models.dev", "provider": "drun", "model": "public/deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "models.dev", "provider": "github-models", "model": "deepseek/deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "iflowcn", "model": "deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.7 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.5 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.18 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.18 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.18 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "togetherai", "model": "deepseek-ai/DeepSeek-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 7 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.4 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 }, "extra": { "input_cost_per_token_cache_hit": 1.4e-7 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 8 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 }, "extra": { "input_cost_per_token_cache_hit": 1.4e-7 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.75, "output": 10, "reasoningOutput": 10 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/DeepSeek-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 7 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-R1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 7 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-r1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-r1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1", "DeepSeek Reasoner", "DeepSeek-R1", "DeepSeek: R1", "Pro/deepseek-ai/DeepSeek-R1", "deepseek-ai/DeepSeek-R1" ], "families": [ "deepseek-thinking" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_completion_tokens", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 30 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "deepseek-ai/DeepSeek-R1", "modelKey": "deepseek-ai/DeepSeek-R1", "displayName": "DeepSeek R1", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek R1", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "deepseek/deepseek-r1", "modelKey": "deepseek/deepseek-r1", "displayName": "DeepSeek Reasoner", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "drun", "providerName": "D.Run (China)", "providerApi": "https://chat.d.run/v1", "providerDoc": "https://www.d.run", "model": "public/deepseek-r1", "modelKey": "public/deepseek-r1", "displayName": "DeepSeek R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "deepseek/deepseek-r1", "modelKey": "deepseek/deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-r1", "modelKey": "deepseek/deepseek-r1", "displayName": "DeepSeek: R1", "metadata": { "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek R1", "metadata": { "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-r1", "modelKey": "deepseek/deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek-R1", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1", "modelKey": "deepseek-ai/DeepSeek-R1", "displayName": "deepseek-ai/DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/deepseek-ai/DeepSeek-R1", "modelKey": "Pro/deepseek-ai/DeepSeek-R1", "displayName": "Pro/deepseek-ai/DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1", "modelKey": "deepseek-ai/DeepSeek-R1", "displayName": "deepseek-ai/DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "deepseek-r1", "modelKey": "deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-R1", "modelKey": "hf:deepseek-ai/DeepSeek-R1", "displayName": "DeepSeek R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "deepseek-ai/DeepSeek-R1", "modelKey": "deepseek-ai/DeepSeek-R1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-r1", "modelKey": "deepseek/deepseek-r1", "displayName": "DeepSeek-R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/deepseek-r1", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-r1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-R1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-r1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-r1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/DeepSeek-R1", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/deepseek-r1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-R1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-r1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-r1", "displayName": "DeepSeek: R1", "metadata": { "canonicalSlug": "deepseek/deepseek-r1", "createdAt": "2025-01-20T13:51:35.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-R1", "instructType": "deepseek-r1", "knowledgeCutoff": "2024-07-31", "links": { "details": "/api/v1/models/deepseek/deepseek-r1/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_completion_tokens", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 64000, "max_completion_tokens": 16000, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-r1-0528", "provider": "deepseek", "model": "deepseek-r1-0528", "displayName": "DeepSeek-R1-0528", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba-cn", "azure", "azure-cognitive-services", "cortecs", "crusoe", "deepinfra", "fireworks_ai", "github-models", "huggingface", "hyperbolic", "io-net", "jiekou", "kilo", "lambda_ai", "llmgateway", "meganova", "nano-gpt", "nebius", "novita", "novita-ai", "openrouter", "qiniu-ai", "submodel", "synthetic", "wandb" ], "aliases": [ "alibaba-cn/deepseek-r1-0528", "alibaba-cn/siliconflow/deepseek-r1-0528", "azure-cognitive-services/deepseek-r1-0528", "azure/deepseek-r1-0528", "cortecs/deepseek-r1-0528", "crusoe/deepseek-ai/DeepSeek-R1-0528", "deepinfra/deepseek-ai/DeepSeek-R1-0528", "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528", "github-models/deepseek/deepseek-r1-0528", "huggingface/deepseek-ai/DeepSeek-R1-0528", "hyperbolic/deepseek-ai/DeepSeek-R1-0528", "io-net/deepseek-ai/DeepSeek-R1-0528", "jiekou/deepseek/deepseek-r1-0528", "kilo/deepseek/deepseek-r1-0528", "lambda_ai/deepseek-r1-0528", "llmgateway/deepseek-r1-0528", "meganova/deepseek-ai/DeepSeek-R1-0528", "nano-gpt/deepseek-ai/DeepSeek-R1-0528", "nebius/deepseek-ai/DeepSeek-R1-0528", "novita-ai/deepseek/deepseek-r1-0528", "novita/deepseek/deepseek-r1-0528", "openrouter/deepseek/deepseek-r1-0528", "qiniu-ai/deepseek-r1-0528", "submodel/deepseek-ai/DeepSeek-R1-0528", "synthetic/hf:deepseek-ai/DeepSeek-R1-0528", "wandb/deepseek-ai/DeepSeek-R1-0528" ], "mergedProviderModelRecords": 26, "limits": { "contextTokens": 164000, "inputTokens": 164000, "maxTokens": 164000, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true, "assistantPrefill": true, "promptCaching": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 2.294 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "siliconflow/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.18 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.35, "output": 5.4 } }, { "source": "models.dev", "provider": "cortecs", "model": "deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.585, "output": 2.307 } }, { "source": "models.dev", "provider": "deepinfra", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.35, "input": 0.5, "output": 2.15 } }, { "source": "models.dev", "provider": "github-models", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "huggingface", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 5 } }, { "source": "models.dev", "provider": "io-net", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 4, "input": 2, "output": 8.75 } }, { "source": "models.dev", "provider": "jiekou", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.5 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.45, "output": 2.15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "meganova", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.7 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.35, "input": 0.7, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.35, "input": 0.5, "output": 2.15 } }, { "source": "models.dev", "provider": "submodel", "model": "deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.15 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 8 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 7 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 0.5, "output": 2.15 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 8 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } }, { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/deepseek-r1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.35, "input": 0.7, "output": 2.5 }, "extra": { "input_cost_per_token_cache_hit": 3.5e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-r1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 2.15 }, "extra": { "input_cost_per_token_cache_hit": 1.4e-7 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-R1-0528", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 135000, "output": 540000 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-r1-0528", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.35, "input": 0.5, "output": 2.15 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1", "DeepSeek R1 (0528)", "DeepSeek R1 0528", "DeepSeek-R1-0528", "DeepSeek: R1 0528", "R1 0528", "siliconflow/deepseek-r1-0528" ], "families": [ "deepseek", "deepseek-thinking" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-05-28", "lastUpdated": "2025-05-28", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 26 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-05-28", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "siliconflow/deepseek-r1-0528", "modelKey": "siliconflow/deepseek-r1-0528", "displayName": "siliconflow/deepseek-r1-0528", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek-R1-0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek-R1-0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "deepseek/deepseek-r1-0528", "modelKey": "deepseek/deepseek-r1-0528", "displayName": "DeepSeek-R1-0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek R1", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "deepseek/deepseek-r1-0528", "modelKey": "deepseek/deepseek-r1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-r1-0528", "modelKey": "deepseek/deepseek-r1-0528", "displayName": "DeepSeek: R1 0528", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek R1 (0528)", "family": "deepseek", "status": "beta", "metadata": { "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek", "metadata": { "lastUpdated": "2025-05-28", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-0528", "modelKey": "deepseek/deepseek-r1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-r1-0528", "modelKey": "deepseek/deepseek-r1-0528", "displayName": "R1 0528", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-28", "openWeights": true, "releaseDate": "2025-05-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek-r1-0528", "modelKey": "deepseek-r1-0528", "displayName": "DeepSeek-R1-0528", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "deepseek-ai/DeepSeek-R1-0528", "modelKey": "deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek R1 0528", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-08-23", "openWeights": false, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-R1-0528", "modelKey": "hf:deepseek-ai/DeepSeek-R1-0528", "displayName": "DeepSeek R1 (0528)", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/deepseek-ai/DeepSeek-R1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-R1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/deepseek-r1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1-0528", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-r1-0528", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-R1-0528", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-r1-0528", "displayName": "DeepSeek: R1 0528", "metadata": { "canonicalSlug": "deepseek/deepseek-r1-0528", "createdAt": "2025-05-28T17:59:30.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-R1-0528", "instructType": "deepseek-r1", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/deepseek/deepseek-r1-0528/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 163840, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-r1-0528-distill-qwen3-8b", "provider": "deepseek", "model": "deepseek-r1-0528-distill-qwen3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-0528-maas", "provider": "deepseek", "model": "deepseek-r1-0528-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-deepseek_models" ], "aliases": [ "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-r1-0528-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65336, "inputTokens": 65336, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-r1-0528-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "modes": [ "chat" ], "supportedRegions": [ "us-central1" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-r1-0528-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supportedRegions": [ "us-central1" ] } } ] }, { "id": "deepseek/deepseek-r1-0528-qwen3-8b", "provider": "deepseek", "model": "deepseek-r1-0528-qwen3-8b", "displayName": "DeepSeek R1 0528 Qwen3 8B", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai" ], "aliases": [ "novita-ai/deepseek/deepseek-r1-0528-qwen3-8b", "novita/deepseek/deepseek-r1-0528-qwen3-8b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-0528-qwen3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.09 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-0528-qwen3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.09 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 0528 Qwen3 8B" ], "modes": [ "chat" ], "releaseDate": "2025-05-29", "lastUpdated": "2025-05-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-0528-qwen3-8b", "modelKey": "deepseek/deepseek-r1-0528-qwen3-8b", "displayName": "DeepSeek R1 0528 Qwen3 8B", "metadata": { "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-05-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-0528-qwen3-8b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-0528-tee", "provider": "deepseek", "model": "deepseek-r1-0528-tee", "displayName": "DeepSeek R1 0528 TEE", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/deepseek-ai/DeepSeek-R1-0528-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "deepseek-ai/DeepSeek-R1-0528-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.225, "input": 0.45, "output": 2.15 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 0528 TEE" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "lastUpdated": "2025-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "deepseek-ai/DeepSeek-R1-0528-TEE", "modelKey": "deepseek-ai/DeepSeek-R1-0528-TEE", "displayName": "DeepSeek R1 0528 TEE", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } } ] }, { "id": "deepseek/deepseek-r1-0528-tput", "provider": "deepseek", "model": "deepseek-r1-0528-tput", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/deepseek-ai/DeepSeek-R1-0528-tput" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-R1-0528-tput", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-R1-0528-tput", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" } } ] }, { "id": "deepseek/deepseek-r1-0528-turbo", "provider": "deepseek", "model": "deepseek-r1-0528-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-671b", "provider": "deepseek", "model": "deepseek-r1-671b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/deepseek-r1-671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/deepseek-r1-671b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/deepseek-r1-671b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-7b-qwen", "provider": "deepseek", "model": "deepseek-r1-7b-qwen", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/deepseek-r1-7b-qwen" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/deepseek-r1-7b-qwen", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/deepseek-r1-7b-qwen", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-8b", "provider": "deepseek", "model": "deepseek-r1-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/deepseek-r1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/deepseek-r1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/deepseek-r1-8b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-basic", "provider": "deepseek", "model": "deepseek-r1-basic", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 20480, "outputTokens": 20480, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "deepseek/deepseek-r1-distill-llama-70b", "provider": "deepseek", "model": "deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba-cn", "chutes", "deepinfra", "digitalocean", "fastrouter", "fireworks_ai", "gradient_ai", "helicone", "kilo", "nebius", "novita", "novita-ai", "nscale", "openrouter", "ovhcloud", "sambanova", "vercel_ai_gateway" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-llama-70b", "chutes/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "digitalocean/deepseek-r1-distill-llama-70b", "fastrouter/deepseek-ai/deepseek-r1-distill-llama-70b", "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b", "gradient_ai/deepseek-r1-distill-llama-70b", "helicone/deepseek-r1-distill-llama-70b", "kilo/deepseek/deepseek-r1-distill-llama-70b", "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "novita-ai/deepseek/deepseek-r1-distill-llama-70b", "novita/deepseek/deepseek-r1-distill-llama-70b", "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "openrouter/deepseek/deepseek-r1-distill-llama-70b", "ovhcloud/DeepSeek-R1-Distill-Llama-70B", "sambanova/DeepSeek-R1-Distill-Llama-70B", "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b" ], "mergedProviderModelRecords": 17, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } }, { "source": "models.dev", "provider": "chutes", "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0136, "input": 0.0272, "output": 0.1087 } }, { "source": "models.dev", "provider": "digitalocean", "model": "deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.99, "output": 0.99 } }, { "source": "models.dev", "provider": "fastrouter", "model": "deepseek-ai/deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.14 } }, { "source": "models.dev", "provider": "helicone", "model": "deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.13 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.7, "output": 0.8 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/deepseek-r1-distill-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.99, "output": 0.99 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.75 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.375, "output": 0.375 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.67, "output": 0.67 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/DeepSeek-R1-Distill-Llama-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 1.4 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "output": 0.99 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-r1-distill-llama-70b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill LLama 70B", "DeepSeek R1 Distill Llama 70B", "DeepSeek: R1 Distill Llama 70B", "R1 Distill Llama 70B" ], "families": [ "deepseek-thinking" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-llama-70b", "modelKey": "deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "modelKey": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "deepseek-r1-distill-llama-70b", "modelKey": "deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-30", "openWeights": true, "releaseDate": "2025-01-30", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "deepseek-ai/deepseek-r1-distill-llama-70b", "modelKey": "deepseek-ai/deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-23", "openWeights": true, "releaseDate": "2025-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-r1-distill-llama-70b", "modelKey": "deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-r1-distill-llama-70b", "modelKey": "deepseek/deepseek-r1-distill-llama-70b", "displayName": "DeepSeek: R1 Distill Llama 70B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-distill-llama-70b", "modelKey": "deepseek/deepseek-r1-distill-llama-70b", "displayName": "DeepSeek R1 Distill LLama 70B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-27", "openWeights": true, "releaseDate": "2025-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-r1-distill-llama-70b", "modelKey": "deepseek/deepseek-r1-distill-llama-70b", "displayName": "R1 Distill Llama 70B", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07-31", "lastUpdated": "2025-01-23", "openWeights": true, "releaseDate": "2025-01-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/deepseek-r1-distill-llama-70b", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-llama-70b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-r1-distill-llama-70b", "displayName": "DeepSeek: R1 Distill Llama 70B", "metadata": { "canonicalSlug": "deepseek/deepseek-r1-distill-llama-70b", "createdAt": "2025-01-23T20:12:49.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "instructType": "deepseek-r1", "knowledgeCutoff": "2024-07-31", "links": { "details": "/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 8192, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-r1-distill-llama-70b-abliterated", "provider": "deepseek", "model": "deepseek-r1-distill-llama-70b-abliterated", "displayName": "DeepSeek R1 Llama 70B Abliterated", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Llama 70B Abliterated" ], "families": [ "deepseek" ], "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated", "modelKey": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated", "displayName": "DeepSeek R1 Llama 70B Abliterated", "family": "deepseek", "metadata": { "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } } ] }, { "id": "deepseek/deepseek-r1-distill-llama-8b", "provider": "deepseek", "model": "deepseek-r1-distill-llama-8b", "displayName": "DeepSeek R1 Distill Llama 8B", "family": "deepseek-thinking", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "fireworks_ai", "nscale" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-llama-8b", "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b", "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-llama-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0.025 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill Llama 8B" ], "families": [ "deepseek-thinking" ], "modes": [ "chat" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-llama-8b", "modelKey": "deepseek-r1-distill-llama-8b", "displayName": "DeepSeek R1 Distill Llama 8B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-1-5b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-1-5b", "displayName": "DeepSeek R1 Distill Qwen 1.5B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-qwen-1-5b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-qwen-1-5b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill Qwen 1.5B" ], "families": [ "qwen" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-qwen-1-5b", "modelKey": "deepseek-r1-distill-qwen-1-5b", "displayName": "DeepSeek R1 Distill Qwen 1.5B", "family": "qwen", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-1.5b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-1.5b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nscale" ], "aliases": [ "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.09 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-14b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-14b", "displayName": "DeepSeek R1 Distill Qwen 14B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "fireworks_ai", "novita", "novita-ai", "nscale", "siliconflow", "siliconflow-cn" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-qwen-14b", "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b", "novita-ai/deepseek/deepseek-r1-distill-qwen-14b", "novita/deepseek/deepseek-r1-distill-qwen-14b", "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "siliconflow-cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "siliconflow/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "responseSchema": true, "systemMessages": true, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-qwen-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.144, "output": 0.431 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-distill-qwen-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-qwen-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.07 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill Qwen 14B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B" ], "families": [ "deepseek-thinking", "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-qwen-14b", "modelKey": "deepseek-r1-distill-qwen-14b", "displayName": "DeepSeek R1 Distill Qwen 14B", "family": "qwen", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-distill-qwen-14b", "modelKey": "deepseek/deepseek-r1-distill-qwen-14b", "displayName": "DeepSeek R1 Distill Qwen 14B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "modelKey": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "displayName": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "modelKey": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "displayName": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-qwen-14b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-1p5b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-1p5b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b", "mode": "chat" } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-32b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-32b", "displayName": "DeepSeek R1 Distill Qwen 32B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "fireworks_ai", "kilo", "novita", "novita-ai", "nscale", "siliconflow", "siliconflow-cn" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-qwen-32b", "cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b", "kilo/deepseek/deepseek-r1-distill-qwen-32b", "novita-ai/deepseek/deepseek-r1-distill-qwen-32b", "novita/deepseek/deepseek-r1-distill-qwen-32b", "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "siliconflow-cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "siliconflow/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-qwen-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.861 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 4.88 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.497, "output": 4.881 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.29 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 0.27 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-qwen-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill Qwen 32B", "DeepSeek: R1 Distill Qwen 32B", "Deepseek R1 Distill Qwen 32B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "families": [ "deepseek-thinking", "qwen" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-qwen-32b", "modelKey": "deepseek-r1-distill-qwen-32b", "displayName": "DeepSeek R1 Distill Qwen 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "modelKey": "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "displayName": "DeepSeek R1 Distill Qwen 32B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "modelKey": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "displayName": "Deepseek R1 Distill Qwen 32B", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-r1-distill-qwen-32b", "modelKey": "deepseek/deepseek-r1-distill-qwen-32b", "displayName": "DeepSeek: R1 Distill Qwen 32B", "metadata": { "lastUpdated": "2025-11-25", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-distill-qwen-32b", "modelKey": "deepseek/deepseek-r1-distill-qwen-32b", "displayName": "DeepSeek R1 Distill Qwen 32B", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "modelKey": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "displayName": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "modelKey": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "displayName": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "family": "qwen", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-distill-qwen-32b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-32b-abliterated", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-32b-abliterated", "displayName": "DeepSeek R1 Qwen Abliterated", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Qwen Abliterated" ], "families": [ "qwen" ], "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated", "modelKey": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated", "displayName": "DeepSeek R1 Qwen Abliterated", "family": "qwen", "metadata": { "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } } ] }, { "id": "deepseek/deepseek-r1-distill-qwen-7b", "provider": "deepseek", "model": "deepseek-r1-distill-qwen-7b", "displayName": "DeepSeek R1 Distill Qwen 7B", "family": "qwen", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "fireworks_ai", "nscale" ], "aliases": [ "alibaba-cn/deepseek-r1-distill-qwen-7b", "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b", "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-r1-distill-qwen-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.144 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Distill Qwen 7B" ], "families": [ "qwen" ], "modes": [ "chat" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-r1-distill-qwen-7b", "modelKey": "deepseek-r1-distill-qwen-7b", "displayName": "DeepSeek R1 Distill Qwen 7B", "family": "qwen", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } } ] }, { "id": "deepseek/deepseek-r1-sambanova", "provider": "deepseek", "model": "deepseek-r1-sambanova", "displayName": "DeepSeek R1 Fast", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek-r1-sambanova" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-r1-sambanova", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 6.987 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 Fast" ], "releaseDate": "2025-02-20", "lastUpdated": "2025-02-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-r1-sambanova", "modelKey": "deepseek-r1-sambanova", "displayName": "DeepSeek R1 Fast", "metadata": { "lastUpdated": "2025-02-20", "openWeights": false, "releaseDate": "2025-02-20" } } ] }, { "id": "deepseek/deepseek-r1-turbo", "provider": "deepseek", "model": "deepseek-r1-turbo", "displayName": "DeepSeek R1 (Turbo)", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "deepinfra", "novita", "novita-ai" ], "aliases": [ "deepinfra/deepseek-ai/DeepSeek-R1-Turbo", "novita-ai/deepseek/deepseek-r1-turbo", "novita/deepseek/deepseek-r1-turbo" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 64000, "inputTokens": 64000, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-r1-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-r1-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "DeepSeek R1 (Turbo)" ], "modes": [ "chat" ], "releaseDate": "2025-03-05", "lastUpdated": "2025-03-05", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-r1-turbo", "modelKey": "deepseek/deepseek-r1-turbo", "displayName": "DeepSeek R1 (Turbo)", "metadata": { "lastUpdated": "2025-03-05", "openWeights": true, "releaseDate": "2025-03-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-R1-Turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-r1-turbo", "mode": "chat" } ] }, { "id": "deepseek/deepseek-reasoner", "provider": "deepseek", "model": "deepseek-reasoner", "displayName": "DeepSeek Reasoner", "family": "deepseek-thinking", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "deepseek", "helicone", "nano-gpt", "orcarouter" ], "aliases": [ "302ai/deepseek-reasoner", "deepseek/deepseek-reasoner", "helicone/deepseek-reasoner", "nano-gpt/deepseek-reasoner", "orcarouter/deepseek/deepseek-reasoner" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1000000, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": false, "transcription": false, "assistantPrefill": true, "supports1MContext": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "deepseek-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.43 } }, { "source": "models.dev", "provider": "deepseek", "model": "deepseek-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "helicone", "model": "deepseek-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.7 } }, { "source": "models.dev", "provider": "orcarouter", "model": "deepseek/deepseek-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.435, "output": 0.87 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek-reasoner", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "input": 0.28, "output": 0.42 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-reasoner", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "input": 0.28, "output": 0.42 }, "extra": { "input_cost_per_token_cache_hit": 2.8e-8 } } ] }, "metadata": { "displayNames": [ "DeepSeek Reasoner", "Deepseek-Reasoner" ], "families": [ "deepseek-thinking" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "deepseek-reasoner", "modelKey": "deepseek-reasoner", "displayName": "Deepseek-Reasoner", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepseek", "providerName": "DeepSeek", "providerApi": "https://api.deepseek.com", "providerDoc": "https://api-docs.deepseek.com/quick_start/pricing", "model": "deepseek-reasoner", "modelKey": "deepseek-reasoner", "displayName": "DeepSeek Reasoner", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-reasoner", "modelKey": "deepseek-reasoner", "displayName": "DeepSeek Reasoner", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-reasoner", "modelKey": "deepseek-reasoner", "displayName": "DeepSeek Reasoner", "metadata": { "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "deepseek/deepseek-reasoner", "modelKey": "deepseek/deepseek-reasoner", "displayName": "DeepSeek Reasoner", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-28", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek-reasoner", "mode": "chat", "metadata": { "source": "https://api-docs.deepseek.com/quick_start/pricing", "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-reasoner", "mode": "chat", "metadata": { "source": "https://api-docs.deepseek.com/quick_start/pricing", "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "deepseek/deepseek-reasoner-cheaper", "provider": "deepseek", "model": "deepseek-reasoner-cheaper", "displayName": "Deepseek R1 Cheaper", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek-reasoner-cheaper" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-reasoner-cheaper", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.7 } } ] }, "metadata": { "displayNames": [ "Deepseek R1 Cheaper" ], "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-reasoner-cheaper", "modelKey": "deepseek-reasoner-cheaper", "displayName": "Deepseek R1 Cheaper", "metadata": { "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } } ] }, { "id": "deepseek/deepseek-tng-r1t2-chimera", "provider": "deepseek", "model": "deepseek-tng-r1t2-chimera", "displayName": "DeepSeek TNG R1T2 Chimera", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/deepseek-tng-r1t2-chimera" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 130000, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "deepseek-tng-r1t2-chimera", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "DeepSeek TNG R1T2 Chimera" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-02", "lastUpdated": "2025-07-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-tng-r1t2-chimera", "modelKey": "deepseek-tng-r1t2-chimera", "displayName": "DeepSeek TNG R1T2 Chimera", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-02", "openWeights": false, "releaseDate": "2025-07-02" } } ] }, { "id": "deepseek/deepseek-tng-r1t2-chimera-tee", "provider": "deepseek", "model": "deepseek-tng-r1t2-chimera-tee", "displayName": "DeepSeek TNG R1T2 Chimera TEE", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/tngtech/DeepSeek-TNG-R1T2-Chimera-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "DeepSeek TNG R1T2 Chimera TEE" ], "families": [ "deepseek" ], "releaseDate": "2026-04-25", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE", "modelKey": "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE", "displayName": "DeepSeek TNG R1T2 Chimera TEE", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2026-04-25" } } ] }, { "id": "deepseek/deepseek-v2-lite-chat", "provider": "deepseek", "model": "deepseek-v2-lite-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v2p5", "provider": "deepseek", "model": "deepseek-v2p5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-v2p5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v2p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v2p5", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3", "provider": "deepseek", "model": "deepseek-v3", "displayName": "DeepSeek V3", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "azure_ai", "deepinfra", "deepseek", "digitalocean", "drun", "fireworks_ai", "helicone", "hyperbolic", "iflowcn", "nebius", "qiniu-ai", "replicate", "siliconflow", "siliconflow-cn", "synthetic", "together_ai", "togetherai", "vercel", "vercel_ai_gateway" ], "aliases": [ "alibaba-cn/deepseek-v3", "azure_ai/deepseek-v3", "deepinfra/deepseek-ai/DeepSeek-V3", "deepseek/deepseek-v3", "digitalocean/deepseek-v3", "drun/public/deepseek-v3", "fireworks_ai/accounts/fireworks/models/deepseek-v3", "helicone/deepseek-v3", "hyperbolic/deepseek-ai/DeepSeek-V3", "iflowcn/deepseek-v3", "nebius/deepseek-ai/DeepSeek-V3", "qiniu-ai/deepseek-v3", "replicate/deepseek-ai/deepseek-v3", "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3", "siliconflow-cn/deepseek-ai/DeepSeek-V3", "siliconflow/deepseek-ai/DeepSeek-V3", "synthetic/hf:deepseek-ai/DeepSeek-V3", "together_ai/deepseek-ai/DeepSeek-V3", "togetherai/deepseek-ai/DeepSeek-V3", "vercel/deepseek/deepseek-v3", "vercel_ai_gateway/deepseek/deepseek-v3" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 164000, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": true, "reasoning": true, "temperature": true, "toolCalling": true, "structuredOutput": true, "responseSchema": true, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 1.147 } }, { "source": "models.dev", "provider": "drun", "model": "public/deepseek-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } }, { "source": "models.dev", "provider": "helicone", "model": "deepseek-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "iflowcn", "model": "deepseek-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-V3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/deepseek-ai/DeepSeek-V3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-V3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-V3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 1.25 } }, { "source": "models.dev", "provider": "togetherai", "model": "deepseek-ai/DeepSeek-V3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 1.25 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1.12 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/deepseek-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.14, "output": 4.56 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.38, "output": 0.89 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.07, "cacheWrite": 0, "input": 0.27, "output": 1.1 }, "extra": { "input_cost_per_token_cache_hit": 7e-8 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-V3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-V3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.45, "output": 1.45 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-V3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 1.25 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3", "DeepSeek V3 0324", "DeepSeek-V3", "Pro/deepseek-ai/DeepSeek-V3", "deepseek-ai/DeepSeek-V3" ], "families": [ "deepseek" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-v3", "modelKey": "deepseek-v3", "displayName": "DeepSeek V3", "family": "deepseek", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "deepseek-v3", "modelKey": "deepseek-v3", "displayName": "DeepSeek V3", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "drun", "providerName": "D.Run (China)", "providerApi": "https://chat.d.run/v1", "providerDoc": "https://www.d.run", "model": "public/deepseek-v3", "modelKey": "public/deepseek-v3", "displayName": "DeepSeek V3", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-12-26", "openWeights": true, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-v3", "modelKey": "deepseek-v3", "displayName": "DeepSeek V3", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2024-12-26", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "deepseek-v3", "modelKey": "deepseek-v3", "displayName": "DeepSeek-V3", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-26", "openWeights": true, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek-v3", "modelKey": "deepseek-v3", "displayName": "DeepSeek-V3", "metadata": { "lastUpdated": "2025-08-13", "openWeights": false, "releaseDate": "2025-08-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3", "modelKey": "deepseek-ai/DeepSeek-V3", "displayName": "deepseek-ai/DeepSeek-V3", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/deepseek-ai/DeepSeek-V3", "modelKey": "Pro/deepseek-ai/DeepSeek-V3", "displayName": "Pro/deepseek-ai/DeepSeek-V3", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3", "modelKey": "deepseek-ai/DeepSeek-V3", "displayName": "deepseek-ai/DeepSeek-V3", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-V3", "modelKey": "hf:deepseek-ai/DeepSeek-V3", "displayName": "DeepSeek V3", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "deepseek-ai/DeepSeek-V3", "modelKey": "deepseek-ai/DeepSeek-V3", "displayName": "DeepSeek-V3", "family": "deepseek", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v3", "modelKey": "deepseek/deepseek-v3", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-12-26", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/deepseek-v3", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-v3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-V3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-V3", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-v3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-V3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/deepseek/deepseek-v3", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3-0324", "provider": "deepseek", "model": "deepseek-v3-0324", "displayName": "siliconflow/deepseek-v3-0324", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "alibaba-cn", "azure", "azure-cognitive-services", "azure_ai", "baseten", "cortecs", "crusoe", "deepinfra", "fireworks_ai", "github-models", "gmi", "hyperbolic", "jiekou", "lambda_ai", "meganova", "nano-gpt", "nebius", "novita", "novita-ai", "qiniu-ai", "sambanova", "submodel", "synthetic", "wandb" ], "aliases": [ "alibaba-cn/siliconflow/deepseek-v3-0324", "azure-cognitive-services/deepseek-v3-0324", "azure/deepseek-v3-0324", "azure_ai/deepseek-v3-0324", "baseten/deepseek-ai/DeepSeek-V3-0324", "cortecs/deepseek-v3-0324", "crusoe/deepseek-ai/DeepSeek-V3-0324", "deepinfra/deepseek-ai/DeepSeek-V3-0324", "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324", "github-models/deepseek/deepseek-v3-0324", "gmi/deepseek-ai/DeepSeek-V3-0324", "hyperbolic/deepseek-ai/DeepSeek-V3-0324", "jiekou/deepseek/deepseek-v3-0324", "lambda_ai/deepseek-v3-0324", "meganova/deepseek-ai/DeepSeek-V3-0324", "nano-gpt/deepseek-v3-0324", "nebius/deepseek-ai/DeepSeek-V3-0324", "novita-ai/deepseek/deepseek-v3-0324", "novita/deepseek/deepseek-v3-0324", "qiniu-ai/deepseek-v3-0324", "sambanova/DeepSeek-V3-0324", "submodel/deepseek-ai/DeepSeek-V3-0324", "synthetic/hf:deepseek-ai/DeepSeek-V3-0324", "wandb/deepseek-ai/DeepSeek-V3-0324" ], "mergedProviderModelRecords": 24, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "systemMessages": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "siliconflow/deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.14, "output": 4.56 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.14, "output": 4.56 } }, { "source": "models.dev", "provider": "cortecs", "model": "deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.551, "output": 1.654 } }, { "source": "models.dev", "provider": "github-models", "model": "deepseek/deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "jiekou", "model": "deepseek/deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.14 } }, { "source": "models.dev", "provider": "meganova", "model": "deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.88 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.7 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1.12 } }, { "source": "models.dev", "provider": "submodel", "model": "deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/deepseek-v3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.14, "output": 4.56 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.77, "output": 0.77 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 1.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.88 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.28, "output": 0.88 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/deepseek-v3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1.12 }, "extra": { "input_cost_per_token_cache_hit": 1.35e-7 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4.5 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-V3-0324", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 114000, "output": 275000 } } ] }, "metadata": { "displayNames": [ "DeepSeek Chat 0324", "DeepSeek V3 (0324)", "DeepSeek V3 0324", "DeepSeek-V3-0324", "siliconflow/deepseek-v3-0324" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-12-26", "lastUpdated": "2025-11-25", "providerModelRecordCount": 24 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "siliconflow/deepseek-v3-0324", "modelKey": "siliconflow/deepseek-v3-0324", "displayName": "siliconflow/deepseek-v3-0324", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3-0324", "modelKey": "deepseek-v3-0324", "displayName": "DeepSeek-V3-0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3-0324", "modelKey": "deepseek-v3-0324", "displayName": "DeepSeek-V3-0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "deepseek-v3-0324", "modelKey": "deepseek-v3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "deepseek/deepseek-v3-0324", "modelKey": "deepseek/deepseek-v3-0324", "displayName": "DeepSeek-V3-0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "deepseek/deepseek-v3-0324", "modelKey": "deepseek/deepseek-v3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "deepseek-ai/DeepSeek-V3-0324", "modelKey": "deepseek-ai/DeepSeek-V3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "lastUpdated": "2025-03-24", "openWeights": true, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-v3-0324", "modelKey": "deepseek-v3-0324", "displayName": "DeepSeek Chat 0324", "metadata": { "lastUpdated": "2025-03-24", "openWeights": false, "releaseDate": "2025-03-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3-0324", "modelKey": "deepseek/deepseek-v3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-25", "openWeights": true, "releaseDate": "2025-03-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek-v3-0324", "modelKey": "deepseek-v3-0324", "displayName": "DeepSeek-V3-0324", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "deepseek-ai/DeepSeek-V3-0324", "modelKey": "deepseek-ai/DeepSeek-V3-0324", "displayName": "DeepSeek V3 0324", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-23", "openWeights": false, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-V3-0324", "modelKey": "hf:deepseek-ai/DeepSeek-V3-0324", "displayName": "DeepSeek V3 (0324)", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/deepseek-v3-0324", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/deepseek-v3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/deepseek-ai/DeepSeek-V3-0324", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3-0324", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/DeepSeek-V3-0324", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-V3-0324", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3-0324-tee", "provider": "deepseek", "model": "deepseek-v3-0324-tee", "displayName": "DeepSeek V3 0324 TEE", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/deepseek-ai/DeepSeek-V3-0324-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "deepseek-ai/DeepSeek-V3-0324-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 0.25, "output": 1 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3 0324 TEE" ], "families": [ "deepseek" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "deepseek-ai/DeepSeek-V3-0324-TEE", "modelKey": "deepseek-ai/DeepSeek-V3-0324-TEE", "displayName": "DeepSeek V3 0324 TEE", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } } ] }, { "id": "deepseek/deepseek-v3-1", "provider": "deepseek", "model": "deepseek-v3-1", "displayName": "DeepSeek V3.1", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "alibaba-cn", "togetherai" ], "aliases": [ "alibaba-cn/deepseek-v3-1", "togetherai/deepseek-ai/DeepSeek-V3-1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-v3-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 1.721 } }, { "source": "models.dev", "provider": "togetherai", "model": "deepseek-ai/DeepSeek-V3-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.7 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1" ], "families": [ "deepseek" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-08", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-v3-1", "modelKey": "deepseek-v3-1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "deepseek-ai/DeepSeek-V3-1", "modelKey": "deepseek-ai/DeepSeek-V3-1", "displayName": "DeepSeek V3.1", "family": "deepseek", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepseek/deepseek-v3-2-251201", "provider": "deepseek", "model": "deepseek-v3-2-251201", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/deepseek-v3-2-251201" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 98304, "inputTokens": 98304, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "deepseek-v3-2-251201", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "deepseek-v3-2-251201", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3-2-exp", "provider": "deepseek", "model": "deepseek-v3-2-exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "alibaba-cn" ], "aliases": [ "alibaba-cn/deepseek-v3-2-exp" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-v3-2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.287, "output": 0.431 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Exp" ], "families": [ "deepseek" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-v3-2-exp", "modelKey": "deepseek-v3-2-exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "deepseek/deepseek-v3-turbo", "provider": "deepseek", "model": "deepseek-v3-turbo", "displayName": "DeepSeek V3 (Turbo)", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai" ], "aliases": [ "novita-ai/deepseek/deepseek-v3-turbo", "novita/deepseek/deepseek-v3-turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 64000, "inputTokens": 64000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.3 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.3 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3 (Turbo)" ], "modes": [ "chat" ], "releaseDate": "2025-03-05", "lastUpdated": "2025-03-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3-turbo", "modelKey": "deepseek/deepseek-v3-turbo", "displayName": "DeepSeek V3 (Turbo)", "metadata": { "lastUpdated": "2025-03-05", "openWeights": true, "releaseDate": "2025-03-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3-turbo", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3.1", "provider": "deepseek", "model": "deepseek-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "baseten", "deepinfra", "jiekou", "llmgateway", "meganova", "nano-gpt", "novita", "novita-ai", "qiniu-ai", "replicate", "sambanova", "siliconflow", "submodel", "synthetic", "together_ai", "vercel", "wandb" ], "aliases": [ "abacus/deepseek/deepseek-v3.1", "azure-cognitive-services/deepseek-v3.1", "azure/deepseek-v3.1", "baseten/deepseek-ai/DeepSeek-V3.1", "deepinfra/deepseek-ai/DeepSeek-V3.1", "jiekou/deepseek/deepseek-v3.1", "llmgateway/deepseek-v3.1", "meganova/deepseek-ai/DeepSeek-V3.1", "nano-gpt/TEE/deepseek-v3.1", "nano-gpt/deepseek-ai/DeepSeek-V3.1", "novita-ai/deepseek/deepseek-v3.1", "novita/deepseek/deepseek-v3.1", "qiniu-ai/deepseek-v3.1", "replicate/deepseek-ai/deepseek-v3.1", "sambanova/DeepSeek-V3.1", "siliconflow/deepseek-ai/DeepSeek-V3.1", "submodel/deepseek-ai/DeepSeek-V3.1", "synthetic/hf:deepseek-ai/DeepSeek-V3.1", "together_ai/deepseek-ai/DeepSeek-V3.1", "vercel/deepseek/deepseek-v3.1", "wandb/deepseek-ai/DeepSeek-V3.1" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 164000, "inputTokens": 164000, "maxTokens": 163840, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "structuredOutput": true, "functionCalling": true, "toolChoice": true, "parallelFunctionCalling": true, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "deepseek/deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 1.66 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "baseten", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "deepseek/deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "llmgateway", "model": "deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "meganova", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.7 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "submodel", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.28, "input": 0.56, "output": 1.68 } }, { "source": "models.dev", "provider": "wandb", "model": "deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 1.65 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.216, "input": 0.27, "output": 1 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 }, "extra": { "input_cost_per_token_cache_hit": 1.35e-7 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-v3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.672, "output": 2.016 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/DeepSeek-V3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.7 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-V3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 55000, "output": 165000 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1", "DeepSeek V3.1 TEE", "DeepSeek-V3.1", "deepseek-ai/DeepSeek-V3.1" ], "families": [ "deepseek" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "deepseek/deepseek-v3.1", "modelKey": "deepseek/deepseek-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-01-20", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.1", "modelKey": "deepseek-v3.1", "displayName": "DeepSeek-V3.1", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.1", "modelKey": "deepseek-v3.1", "displayName": "DeepSeek-V3.1", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "status": "deprecated", "metadata": { "lastUpdated": "2025-08-25", "openWeights": true, "releaseDate": "2025-08-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "deepseek/deepseek-v3.1", "modelKey": "deepseek/deepseek-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 32767 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "deepseek-v3.1", "modelKey": "deepseek-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-25", "openWeights": true, "releaseDate": "2025-08-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/deepseek-v3.1", "modelKey": "TEE/deepseek-v3.1", "displayName": "DeepSeek V3.1 TEE", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3.1", "modelKey": "deepseek/deepseek-v3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-21", "openWeights": true, "releaseDate": "2025-08-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek-v3.1", "modelKey": "deepseek-v3.1", "displayName": "DeepSeek-V3.1", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "deepseek-ai/DeepSeek-V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-23", "openWeights": false, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-V3.1", "modelKey": "hf:deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v3.1", "modelKey": "deepseek/deepseek-v3.1", "displayName": "DeepSeek-V3.1", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "deepseek-ai/DeepSeek-V3.1", "modelKey": "deepseek-ai/DeepSeek-V3.1", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-08-21" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/deepseek-ai/DeepSeek-V3.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/deepseek-ai/deepseek-v3.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/DeepSeek-V3.1", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/deepseek-ai/DeepSeek-V3.1", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/deepseek-v3-1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/deepseek-ai/DeepSeek-V3.1", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3.1-maas", "provider": "deepseek", "model": "deepseek-v3.1-maas", "displayName": "DeepSeek V3.1", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-deepseek_models" ], "aliases": [ "google-vertex/deepseek-ai/deepseek-v3.1-maas", "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-v3.1-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "deepseek-ai/deepseek-v3.1-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.7 } }, { "source": "litellm", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-v3.1-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.35, "output": 5.4 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1" ], "families": [ "deepseek" ], "modes": [ "chat" ], "releaseDate": "2025-08-28", "lastUpdated": "2025-08-28", "supportedRegions": [ "us-central1" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "deepseek-ai/deepseek-v3.1-maas", "modelKey": "deepseek-ai/deepseek-v3.1-maas", "displayName": "DeepSeek V3.1", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-v3.1-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supportedRegions": [ "us-central1" ] } } ] }, { "id": "deepseek/deepseek-v3.1-nex-n1", "provider": "deepseek", "model": "deepseek-v3.1-nex-n1", "displayName": "Nex AGI: DeepSeek V3.1 Nex N1", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "kilo", "nano-gpt" ], "aliases": [ "kilo/nex-agi/deepseek-v3.1-nex-n1", "nano-gpt/nex-agi/deepseek-v3.1-nex-n1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 128000, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nex-agi/deepseek-v3.1-nex-n1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "nex-agi/deepseek-v3.1-nex-n1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1 Nex N1", "Nex AGI: DeepSeek V3.1 Nex N1" ], "families": [ "deepseek" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nex-agi/deepseek-v3.1-nex-n1", "modelKey": "nex-agi/deepseek-v3.1-nex-n1", "displayName": "Nex AGI: DeepSeek V3.1 Nex N1", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nex-agi/deepseek-v3.1-nex-n1", "modelKey": "nex-agi/deepseek-v3.1-nex-n1", "displayName": "DeepSeek V3.1 Nex N1", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-10", "openWeights": false, "releaseDate": "2025-12-10" } } ] }, { "id": "deepseek/deepseek-v3.1-tee", "provider": "deepseek", "model": "deepseek-v3.1-tee", "displayName": "DeepSeek V3.1 TEE", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/deepseek-ai/DeepSeek-V3.1-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "deepseek-ai/DeepSeek-V3.1-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1 TEE" ], "families": [ "deepseek" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "deepseek-ai/DeepSeek-V3.1-TEE", "modelKey": "deepseek-ai/DeepSeek-V3.1-TEE", "displayName": "DeepSeek V3.1 TEE", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepseek/deepseek-v3.1-terminus", "provider": "deepseek", "model": "deepseek-v3.1-terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "alibaba-cn", "deepinfra", "helicone", "kilo", "nano-gpt", "novita", "novita-ai", "openrouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "vercel" ], "aliases": [ "abacus/deepseek-ai/DeepSeek-V3.1-Terminus", "alibaba-cn/siliconflow/deepseek-v3.1-terminus", "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "helicone/deepseek-v3.1-terminus", "kilo/deepseek/deepseek-v3.1-terminus", "nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus", "novita-ai/deepseek/deepseek-v3.1-terminus", "novita/deepseek/deepseek-v3.1-terminus", "openrouter/deepseek/deepseek-v3.1-terminus", "qiniu-ai/deepseek/deepseek-v3.1-terminus", "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "siliconflow-cn/deepseek-ai/DeepSeek-V3.1-Terminus", "siliconflow/deepseek-ai/DeepSeek-V3.1-Terminus", "synthetic/hf:deepseek-ai/DeepSeek-V3.1-Terminus", "vercel/deepseek/deepseek-v3.1-terminus" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 164000, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "siliconflow/deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "helicone", "model": "deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.21600000000000003, "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 0.21, "output": 0.79 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.7 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 0.27, "output": 0.95 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 1 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.216, "input": 0.27, "output": 1 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.135, "input": 0.27, "output": 1 }, "extra": { "input_cost_per_token_cache_hit": 1.35e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-v3.1-terminus", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "input": 0.27, "output": 0.95 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1 Terminus", "DeepSeek/DeepSeek-V3.1-Terminus", "DeepSeek: DeepSeek V3.1 Terminus", "Deepseek V3.1 Terminus", "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "deepseek-ai/DeepSeek-V3.1-Terminus", "siliconflow/deepseek-v3.1-terminus" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-06-01", "openWeights": true, "releaseDate": "2025-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "siliconflow/deepseek-v3.1-terminus", "modelKey": "siliconflow/deepseek-v3.1-terminus", "displayName": "siliconflow/deepseek-v3.1-terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-v3.1-terminus", "modelKey": "deepseek-v3.1-terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v3.1-terminus", "modelKey": "deepseek/deepseek-v3.1-terminus", "displayName": "DeepSeek: DeepSeek V3.1 Terminus", "metadata": { "lastUpdated": "2025-09-22", "openWeights": true, "releaseDate": "2025-09-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-08-02", "openWeights": false, "releaseDate": "2025-08-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3.1-terminus", "modelKey": "deepseek/deepseek-v3.1-terminus", "displayName": "Deepseek V3.1 Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-09-22", "openWeights": true, "releaseDate": "2025-09-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-v3.1-terminus", "modelKey": "deepseek/deepseek-v3.1-terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-09-22", "openWeights": true, "releaseDate": "2025-09-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-v3.1-terminus", "modelKey": "deepseek/deepseek-v3.1-terminus", "displayName": "DeepSeek/DeepSeek-V3.1-Terminus", "metadata": { "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "deepseek-ai/DeepSeek-V3.1-Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "deepseek-ai/DeepSeek-V3.1-Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-V3.1-Terminus", "modelKey": "hf:deepseek-ai/DeepSeek-V3.1-Terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v3.1-terminus", "modelKey": "deepseek/deepseek-v3.1-terminus", "displayName": "DeepSeek V3.1 Terminus", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-22", "openWeights": true, "releaseDate": "2025-09-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3.1-terminus", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-v3.1-terminus", "displayName": "DeepSeek: DeepSeek V3.1 Terminus", "metadata": { "canonicalSlug": "deepseek/deepseek-v3.1-terminus", "createdAt": "2025-09-22T13:37:55.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3.1-Terminus", "instructType": "deepseek-v3.1", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 163840, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-v3.1-terminus-thinking", "provider": "deepseek", "model": "deepseek-v3.1-terminus-thinking", "displayName": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/deepseek/deepseek-v3.1-terminus-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "DeepSeek/DeepSeek-V3.1-Terminus-Thinking" ], "releaseDate": "2025-09-22", "lastUpdated": "2025-09-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-v3.1-terminus-thinking", "modelKey": "deepseek/deepseek-v3.1-terminus-thinking", "displayName": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking", "metadata": { "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } } ] }, { "id": "deepseek/deepseek-v3.1-terminus:thinking", "provider": "deepseek", "model": "deepseek-v3.1-terminus:thinking", "displayName": "DeepSeek V3.1 Terminus (Thinking)", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1 Terminus (Thinking)" ], "families": [ "deepseek-thinking" ], "releaseDate": "2025-09-22", "lastUpdated": "2025-09-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking", "modelKey": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking", "displayName": "DeepSeek V3.1 Terminus (Thinking)", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } } ] }, { "id": "deepseek/deepseek-v3.1:671b", "provider": "deepseek", "model": "deepseek-v3.1:671b", "displayName": "deepseek-v3.1:671b", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/deepseek-v3.1:671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "deepseek-v3.1:671b" ], "families": [ "deepseek" ], "releaseDate": "2025-08-21", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "deepseek-v3.1:671b", "modelKey": "deepseek-v3.1:671b", "displayName": "deepseek-v3.1:671b", "family": "deepseek", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-08-21", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepseek/deepseek-v3.1:671b-cloud", "provider": "deepseek", "model": "deepseek-v3.1:671b-cloud", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/deepseek-v3.1:671b-cloud" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/deepseek-v3.1:671b-cloud", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/deepseek-v3.1:671b-cloud", "mode": "chat" } ] }, { "id": "deepseek/deepseek-v3.1:thinking", "provider": "deepseek", "model": "deepseek-v3.1:thinking", "displayName": "DeepSeek V3.1 Thinking", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek-ai/DeepSeek-V3.1:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/DeepSeek-V3.1:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.1 Thinking" ], "families": [ "deepseek-thinking" ], "releaseDate": "2025-08-21", "lastUpdated": "2025-08-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/DeepSeek-V3.1:thinking", "modelKey": "deepseek-ai/DeepSeek-V3.1:thinking", "displayName": "DeepSeek V3.1 Thinking", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } } ] }, { "id": "deepseek/deepseek-v3.2", "provider": "deepseek", "model": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "alibaba-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "azure", "azure-cognitive-services", "azure_ai", "cortecs", "crof", "deepinfra", "deepseek", "gmi", "helicone", "huggingface", "iflowcn", "kilo", "llmgateway", "meganova", "nano-gpt", "nebius", "novita", "novita-ai", "ollama-cloud", "openrouter", "poe", "routing-run", "siliconflow", "siliconflow-cn", "synthetic", "venice", "vercel", "vivgrid", "zenmux" ], "aliases": [ "302ai/deepseek-v3.2", "abacus/deepseek-ai/DeepSeek-V3.2", "alibaba-cn/siliconflow/deepseek-v3.2", "alibaba-token-plan-cn/deepseek-v3.2", "alibaba-token-plan/deepseek-v3.2", "azure-cognitive-services/deepseek-v3.2", "azure/deepseek-v3.2", "azure_ai/deepseek-v3.2", "cortecs/deepseek-v3.2", "crof/deepseek-v3.2", "deepinfra/deepseek-ai/DeepSeek-V3.2", "deepseek/deepseek-v3.2", "gmi/deepseek-ai/DeepSeek-V3.2", "helicone/deepseek-v3.2", "huggingface/deepseek-ai/DeepSeek-V3.2", "iflowcn/deepseek-v3.2", "kilo/deepseek/deepseek-v3.2", "llmgateway/deepseek-v3.2", "meganova/deepseek-ai/DeepSeek-V3.2", "nano-gpt/TEE/deepseek-v3.2", "nano-gpt/deepseek/deepseek-v3.2", "nebius/deepseek-ai/DeepSeek-V3.2", "novita-ai/deepseek/deepseek-v3.2", "novita/deepseek/deepseek-v3.2", "ollama-cloud/deepseek-v3.2", "openrouter/deepseek/deepseek-v3.2", "poe/novita/deepseek-v3.2", "routing-run/route/deepseek-v3.2", "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.2", "siliconflow-cn/deepseek-ai/DeepSeek-V3.2", "siliconflow/deepseek-ai/DeepSeek-V3.2", "synthetic/hf:deepseek-ai/DeepSeek-V3.2", "venice/deepseek-v3.2", "vercel/deepseek/deepseek-v3.2", "vivgrid/deepseek-v3.2", "zenmux/deepseek/deepseek-v3.2" ], "mergedProviderModelRecords": 36, "limits": { "contextTokens": 164000, "inputTokens": 164000, "maxTokens": 163840, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": true, "supports1MContext": false, "attachments": true, "openWeights": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.43 } }, { "source": "models.dev", "provider": "abacus", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.4 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "siliconflow/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.42 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 1.68 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 1.68 } }, { "source": "models.dev", "provider": "cortecs", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.266, "output": 0.444 } }, { "source": "models.dev", "provider": "crof", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.18, "output": 0.35 } }, { "source": "models.dev", "provider": "deepinfra", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 0.26, "output": 0.38 } }, { "source": "models.dev", "provider": "helicone", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "models.dev", "provider": "huggingface", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.4 } }, { "source": "models.dev", "provider": "iflowcn", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 0.26, "output": 0.38 } }, { "source": "models.dev", "provider": "llmgateway", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.056, "input": 0.28, "output": 0.42 } }, { "source": "models.dev", "provider": "meganova", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.26, "output": 0.38 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1 } }, { "source": "models.dev", "provider": "nebius", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 0.45, "reasoningOutput": 0.45 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1345, "input": 0.269, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2288, "output": 0.3432 } }, { "source": "models.dev", "provider": "poe", "model": "novita/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 0.27, "output": 0.4 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4928, "output": 0.7392 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.42 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.42 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.42 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.27, "cacheWrite": 0, "input": 0.27, "output": 0.4 } }, { "source": "models.dev", "provider": "venice", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.33, "output": 0.48 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.28, "output": 0.42 } }, { "source": "models.dev", "provider": "vivgrid", "model": "deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.42 } }, { "source": "models.dev", "provider": "zenmux", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.43 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/deepseek-v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.58, "output": 1.68 } }, { "source": "litellm", "provider": "deepseek", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.28, "output": 0.4 }, "extra": { "input_cost_per_token_cache_hit": 2.8e-8 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/deepseek-ai/DeepSeek-V3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.28, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1345, "input": 0.269, "output": 0.4 }, "extra": { "input_cost_per_token_cache_hit": 1.345e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.28, "output": 0.4 }, "extra": { "input_cost_per_token_cache_hit": 2.8e-8 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-v3.2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2288, "output": 0.3432 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2", "DeepSeek V3.2 TEE", "DeepSeek-V3.2", "DeepSeek-V3.2-Exp", "DeepSeek: DeepSeek V3.2", "Deepseek V3.2", "Pro/deepseek-ai/DeepSeek-V3.2", "deepseek-ai/DeepSeek-V3.2", "deepseek-v3.2", "siliconflow/deepseek-v3.2" ], "families": [ "deepseek" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 36 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "deepseek-v3.2", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-06-15", "openWeights": true, "releaseDate": "2025-06-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "siliconflow/deepseek-v3.2", "modelKey": "siliconflow/deepseek-v3.2", "displayName": "siliconflow/deepseek-v3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-03", "openWeights": false, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-05", "openWeights": true, "releaseDate": "2025-12-03", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-05", "openWeights": true, "releaseDate": "2025-12-03", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-07-22", "openWeights": false, "releaseDate": "2025-07-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek-V3.2", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-22", "openWeights": false, "releaseDate": "2025-09-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek-V3.2-Exp", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "DeepSeek: DeepSeek V3.2", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-09-29", "openWeights": true, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-03", "openWeights": true, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/deepseek-v3.2", "modelKey": "TEE/deepseek-v3.2", "displayName": "DeepSeek V3.2 TEE", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek-V3.2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-20", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "Deepseek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "deepseek-v3.2", "family": "deepseek", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-06-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/deepseek-v3.2", "modelKey": "novita/deepseek-v3.2", "displayName": "DeepSeek-V3.2", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/deepseek-v3.2", "modelKey": "route/deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "deepseek-ai/DeepSeek-V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-03", "openWeights": false, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/deepseek-ai/DeepSeek-V3.2", "modelKey": "Pro/deepseek-ai/DeepSeek-V3.2", "displayName": "Pro/deepseek-ai/DeepSeek-V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-03", "openWeights": false, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.2", "modelKey": "deepseek-ai/DeepSeek-V3.2", "displayName": "deepseek-ai/DeepSeek-V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-03", "openWeights": false, "releaseDate": "2025-12-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:deepseek-ai/DeepSeek-V3.2", "modelKey": "hf:deepseek-ai/DeepSeek-V3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-12-04", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "deepseek-v3.2", "modelKey": "deepseek-v3.2", "displayName": "DeepSeek-V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "deepseek/deepseek-v3.2", "modelKey": "deepseek/deepseek-v3.2", "displayName": "DeepSeek V3.2", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-05", "openWeights": false, "releaseDate": "2025-12-05", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/deepseek-v3.2", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepseek", "model": "deepseek/deepseek-v3.2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/deepseek-ai/DeepSeek-V3.2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3.2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-v3.2", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-v3.2", "displayName": "DeepSeek: DeepSeek V3.2", "metadata": { "canonicalSlug": "deepseek/deepseek-v3.2-20251201", "createdAt": "2025-12-01T13:10:42.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3.2", "links": { "details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 128000, "max_completion_tokens": 64000, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-v3.2-251201", "provider": "deepseek", "model": "deepseek-v3.2-251201", "displayName": "Deepseek/DeepSeek-V3.2", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/deepseek/deepseek-v3.2-251201" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Deepseek/DeepSeek-V3.2" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-v3.2-251201", "modelKey": "deepseek/deepseek-v3.2-251201", "displayName": "Deepseek/DeepSeek-V3.2", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "deepseek/deepseek-v3.2-exp", "provider": "deepseek", "model": "deepseek-v3.2-exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "meganova", "nano-gpt", "novita", "novita-ai", "openrouter", "qiniu-ai", "siliconflow", "zenmux" ], "aliases": [ "kilo/deepseek/deepseek-v3.2-exp", "meganova/deepseek-ai/DeepSeek-V3.2-Exp", "nano-gpt/deepseek-ai/deepseek-v3.2-exp", "novita-ai/deepseek/deepseek-v3.2-exp", "novita/deepseek/deepseek-v3.2-exp", "openrouter/deepseek/deepseek-v3.2-exp", "qiniu-ai/deepseek/deepseek-v3.2-exp", "siliconflow/deepseek-ai/DeepSeek-V3.2-Exp", "zenmux/deepseek/deepseek-v3.2-exp" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 164000, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 164000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v3.2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "models.dev", "provider": "meganova", "model": "deepseek-ai/DeepSeek-V3.2-Exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/deepseek-v3.2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v3.2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-v3.2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/DeepSeek-V3.2-Exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "models.dev", "provider": "zenmux", "model": "deepseek/deepseek-v3.2-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.33 } }, { "source": "litellm", "provider": "novita", "model": "novita/deepseek/deepseek-v3.2-exp", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 0.41 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-v3.2-exp", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 }, "extra": { "input_cost_per_token_cache_hit": 2e-8 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-v3.2-exp", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 0.41 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Exp", "DeepSeek-V3.2-Exp", "DeepSeek/DeepSeek-V3.2-Exp", "DeepSeek: DeepSeek V3.2 Exp", "Deepseek V3.2 Exp", "deepseek-ai/DeepSeek-V3.2-Exp" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-01-01", "lastUpdated": "2025-09-29", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v3.2-exp", "modelKey": "deepseek/deepseek-v3.2-exp", "displayName": "DeepSeek: DeepSeek V3.2 Exp", "metadata": { "lastUpdated": "2025-09-29", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "deepseek-ai/DeepSeek-V3.2-Exp", "modelKey": "deepseek-ai/DeepSeek-V3.2-Exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "metadata": { "lastUpdated": "2025-10-10", "openWeights": true, "releaseDate": "2025-10-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/deepseek-v3.2-exp", "modelKey": "deepseek-ai/deepseek-v3.2-exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v3.2-exp", "modelKey": "deepseek/deepseek-v3.2-exp", "displayName": "Deepseek V3.2 Exp", "metadata": { "lastUpdated": "2025-09-29", "openWeights": true, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-v3.2-exp", "modelKey": "deepseek/deepseek-v3.2-exp", "displayName": "DeepSeek V3.2 Exp", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": true, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-v3.2-exp", "modelKey": "deepseek/deepseek-v3.2-exp", "displayName": "DeepSeek/DeepSeek-V3.2-Exp", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V3.2-Exp", "modelKey": "deepseek-ai/DeepSeek-V3.2-Exp", "displayName": "deepseek-ai/DeepSeek-V3.2-Exp", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "deepseek/deepseek-v3.2-exp", "modelKey": "deepseek/deepseek-v3.2-exp", "displayName": "DeepSeek-V3.2-Exp", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/deepseek/deepseek-v3.2-exp", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/deepseek/deepseek-v3.2-exp", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-v3.2-exp", "displayName": "DeepSeek: DeepSeek V3.2 Exp", "metadata": { "canonicalSlug": "deepseek/deepseek-v3.2-exp", "createdAt": "2025-09-29T12:54:41.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V3.2-Exp", "instructType": "deepseek-v3.1", "knowledgeCutoff": "2025-07-31", "links": { "details": "/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 163840, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-v3.2-exp-thinking", "provider": "deepseek", "model": "deepseek-v3.2-exp-thinking", "displayName": "DeepSeek V3.2 Exp Thinking", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "qiniu-ai" ], "aliases": [ "nano-gpt/deepseek-ai/deepseek-v3.2-exp-thinking", "qiniu-ai/deepseek/deepseek-v3.2-exp-thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek-ai/deepseek-v3.2-exp-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Exp Thinking", "DeepSeek/DeepSeek-V3.2-Exp-Thinking" ], "families": [ "deepseek-thinking" ], "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek-ai/deepseek-v3.2-exp-thinking", "modelKey": "deepseek-ai/deepseek-v3.2-exp-thinking", "displayName": "DeepSeek V3.2 Exp Thinking", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "deepseek/deepseek-v3.2-exp-thinking", "modelKey": "deepseek/deepseek-v3.2-exp-thinking", "displayName": "DeepSeek/DeepSeek-V3.2-Exp-Thinking", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } } ] }, { "id": "deepseek/deepseek-v3.2-fast", "provider": "deepseek", "model": "deepseek-v3.2-fast", "displayName": "DeepSeek-V3.2-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/deepseek-ai/DeepSeek-V3.2-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "deepseek-ai/DeepSeek-V3.2-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "cacheWrite": 0.5, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "DeepSeek-V3.2-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-27", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "deepseek-ai/DeepSeek-V3.2-fast", "modelKey": "deepseek-ai/DeepSeek-V3.2-fast", "displayName": "DeepSeek-V3.2-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-01-27", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepseek/deepseek-v3.2-maas", "provider": "deepseek", "model": "deepseek-v3.2-maas", "displayName": "DeepSeek V3.2", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-deepseek_models" ], "aliases": [ "google-vertex/deepseek-ai/deepseek-v3.2-maas", "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-v3.2-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 32768, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "deepseek-ai/deepseek-v3.2-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.056, "input": 0.56, "output": 1.68 } }, { "source": "litellm", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-v3.2-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.56, "output": 1.68 }, "extra": { "input_cost_per_token_batches": 2.8e-7, "output_cost_per_token_batches": 8.4e-7 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2" ], "families": [ "deepseek" ], "modes": [ "chat" ], "releaseDate": "2025-12-17", "lastUpdated": "2026-04-04", "supportedRegions": [ "global" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "deepseek-ai/deepseek-v3.2-maas", "modelKey": "deepseek-ai/deepseek-v3.2-maas", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-04", "openWeights": true, "releaseDate": "2025-12-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-deepseek_models", "model": "vertex_ai/deepseek-ai/deepseek-v3.2-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supportedRegions": [ "global" ] } } ] }, { "id": "deepseek/deepseek-v3.2-nvfp4", "provider": "deepseek", "model": "deepseek-v3.2-nvfp4", "displayName": "DeepSeek V3.2", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "vultr" ], "aliases": [ "vultr/nvidia/DeepSeek-V3.2-NVFP4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vultr", "model": "nvidia/DeepSeek-V3.2-NVFP4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 1.65 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2" ], "families": [ "deepseek" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "nvidia/DeepSeek-V3.2-NVFP4", "modelKey": "nvidia/DeepSeek-V3.2-NVFP4", "displayName": "DeepSeek V3.2", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } } ] }, { "id": "deepseek/deepseek-v3.2-speciale", "provider": "deepseek", "model": "deepseek-v3.2-speciale", "displayName": "DeepSeek-V3.2-Speciale", "family": "deepseek", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "kilo", "nano-gpt" ], "aliases": [ "azure-cognitive-services/deepseek-v3.2-speciale", "azure/deepseek-v3.2-speciale", "azure_ai/deepseek-v3.2-speciale", "kilo/deepseek/deepseek-v3.2-speciale", "nano-gpt/deepseek/deepseek-v3.2-speciale" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "deepseek-v3.2-speciale", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 1.68 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v3.2-speciale", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 1.68 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v3.2-speciale", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.135, "input": 0.4, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v3.2-speciale", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/deepseek-v3.2-speciale", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.58, "output": 1.68 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Speciale", "DeepSeek-V3.2-Speciale", "DeepSeek: DeepSeek V3.2 Speciale" ], "families": [ "deepseek" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.2-speciale", "modelKey": "deepseek-v3.2-speciale", "displayName": "DeepSeek-V3.2-Speciale", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v3.2-speciale", "modelKey": "deepseek-v3.2-speciale", "displayName": "DeepSeek-V3.2-Speciale", "family": "deepseek", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v3.2-speciale", "modelKey": "deepseek/deepseek-v3.2-speciale", "displayName": "DeepSeek: DeepSeek V3.2 Speciale", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v3.2-speciale", "modelKey": "deepseek/deepseek-v3.2-speciale", "displayName": "DeepSeek V3.2 Speciale", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/deepseek-v3.2-speciale", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549" } } ] }, { "id": "deepseek/deepseek-v3.2-tee", "provider": "deepseek", "model": "deepseek-v3.2-tee", "displayName": "DeepSeek V3.2 TEE", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/deepseek-ai/DeepSeek-V3.2-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "deepseek-ai/DeepSeek-V3.2-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14, "input": 0.28, "output": 0.42 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 TEE" ], "families": [ "deepseek" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "deepseek-ai/DeepSeek-V3.2-TEE", "modelKey": "deepseek-ai/DeepSeek-V3.2-TEE", "displayName": "DeepSeek V3.2 TEE", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "deepseek/deepseek-v3.2-thinking", "provider": "deepseek", "model": "deepseek-v3.2-thinking", "displayName": "DeepSeek-V3.2-Thinking", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "302ai", "vercel" ], "aliases": [ "302ai/deepseek-v3.2-thinking", "vercel/deepseek/deepseek-v3.2-thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "deepseek-v3.2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.43 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v3.2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.62, "output": 1.85 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Thinking", "DeepSeek-V3.2-Thinking" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "deepseek-v3.2-thinking", "modelKey": "deepseek-v3.2-thinking", "displayName": "DeepSeek-V3.2-Thinking", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v3.2-thinking", "modelKey": "deepseek/deepseek-v3.2-thinking", "displayName": "DeepSeek V3.2 Thinking", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "deepseek/deepseek-v3.2:thinking", "provider": "deepseek", "model": "deepseek-v3.2:thinking", "displayName": "DeepSeek V3.2 Thinking", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek/deepseek-v3.2:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163000, "inputTokens": 163000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v3.2:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27999999999999997, "output": 0.42000000000000004 } } ] }, "metadata": { "displayNames": [ "DeepSeek V3.2 Thinking" ], "families": [ "deepseek" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v3.2:thinking", "modelKey": "deepseek/deepseek-v3.2:thinking", "displayName": "DeepSeek V3.2 Thinking", "family": "deepseek", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "deepseek/deepseek-v3p1", "provider": "deepseek", "model": "deepseek-v3p1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-v3p1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.56, "output": 1.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "deepseek/deepseek-v3p1-terminus", "provider": "deepseek", "model": "deepseek-v3p1-terminus", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.56, "output": 1.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "deepseek/deepseek-v3p2", "provider": "deepseek", "model": "deepseek-v3p2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/deepseek-v3p2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.56, "output": 1.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/deepseek-v3p2", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2" } } ] }, { "id": "deepseek/deepseek-v4-flash", "provider": "deepseek", "model": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "anyapi", "auriko", "azure", "cortecs", "crof", "deepinfra", "deepseek", "fireworks-ai", "gmicloud", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "novita-ai", "nvidia", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "routing-run", "siliconflow", "venice", "vercel", "wafer.ai", "zenmux" ], "aliases": [ "alibaba-cn/deepseek-v4-flash", "alibaba-token-plan-cn/deepseek-v4-flash", "alibaba-token-plan/deepseek-v4-flash", "anyapi/deepseek/deepseek-v4-flash", "auriko/deepseek-v4-flash", "azure/deepseek-v4-flash", "cortecs/deepseek-v4-flash", "crof/deepseek-v4-flash", "deepinfra/deepseek-ai/DeepSeek-V4-Flash", "deepseek/deepseek-v4-flash", "fireworks-ai/accounts/fireworks/models/deepseek-v4-flash", "gmicloud/deepseek-ai/DeepSeek-V4-Flash", "kilo/deepseek/deepseek-v4-flash", "llmgateway/deepseek-v4-flash", "merge-gateway/deepseek/deepseek-v4-flash", "nano-gpt/deepseek/deepseek-v4-flash", "novita-ai/deepseek/deepseek-v4-flash", "nvidia/deepseek-ai/deepseek-v4-flash", "ollama-cloud/deepseek-v4-flash", "opencode-go/deepseek-v4-flash", "opencode/deepseek-v4-flash", "openrouter/deepseek/deepseek-v4-flash", "orcarouter/deepseek/deepseek-v4-flash", "routing-run/route/deepseek-v4-flash", "siliconflow/deepseek-ai/deepseek-v4-flash", "venice/deepseek-v4-flash", "vercel/deepseek/deepseek-v4-flash", "wafer.ai/deepseek-v4-flash", "zenmux/deepseek/deepseek-v4-flash" ], "mergedProviderModelRecords": 29, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 1048576, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "auriko", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.19, "output": 0.51 } }, { "source": "models.dev", "provider": "cortecs", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.133, "output": 0.266 } }, { "source": "models.dev", "provider": "crof", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003, "input": 0.12, "output": 0.21 } }, { "source": "models.dev", "provider": "deepinfra", "model": "deepseek-ai/DeepSeek-V4-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.2 } }, { "source": "models.dev", "provider": "deepseek", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "gmicloud", "model": "deepseek-ai/DeepSeek-V4-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.022, "input": 0.112, "output": 0.224 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "llmgateway", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "nvidia", "model": "deepseek-ai/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "opencode-go", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "opencode", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.09, "output": 0.18 } }, { "source": "models.dev", "provider": "orcarouter", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.19, "output": 0.37 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.4928, "output": 0.7392 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "venice", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.17, "output": 0.35 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.14, "output": 0.28 } }, { "source": "models.dev", "provider": "zenmux", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-v4-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.09, "output": 0.18 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash", "DeepSeek-V4-Flash", "DeepSeek: DeepSeek V4 Flash", "deepseek-v4-flash" ], "families": [ "deepseek", "deepseek-flash" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 29 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek-V4-Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "deepseek-ai/DeepSeek-V4-Flash", "modelKey": "deepseek-ai/DeepSeek-V4-Flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepseek", "providerName": "DeepSeek", "providerApi": "https://api.deepseek.com", "providerDoc": "https://api-docs.deepseek.com/quick_start/pricing", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/deepseek-v4-flash", "modelKey": "accounts/fireworks/models/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "deepseek-ai/DeepSeek-V4-Flash", "modelKey": "deepseek-ai/DeepSeek-V4-Flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek: DeepSeek V4 Flash", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "metadata": { "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "minimal", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "deepseek-ai/deepseek-v4-flash", "modelKey": "deepseek-ai/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "deepseek-v4-flash", "family": "deepseek-flash", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/deepseek-v4-flash", "modelKey": "route/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/deepseek-v4-flash", "modelKey": "deepseek-ai/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "deepseek-v4-flash", "modelKey": "deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-05-30", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "deepseek/deepseek-v4-flash", "modelKey": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek V4 Flash", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-v4-flash", "displayName": "DeepSeek: DeepSeek V4 Flash", "metadata": { "canonicalSlug": "deepseek/deepseek-v4-flash-20260423", "createdAt": "2026-04-24T03:17:46.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V4-Flash", "links": { "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "xhigh", "high" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-v4-flash-6bit", "provider": "deepseek", "model": "deepseek-v4-flash-6bit", "displayName": "DeepSeek V4 Flash 6bit", "family": "deepseek-flash", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/deepseek-v4-flash-6bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/deepseek-v4-flash-6bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.4928, "output": 0.7392 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash 6bit" ], "families": [ "deepseek-flash" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/deepseek-v4-flash-6bit", "modelKey": "route/deepseek-v4-flash-6bit", "displayName": "DeepSeek V4 Flash 6bit", "family": "deepseek-flash", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "deepseek/deepseek-v4-flash-el", "provider": "deepseek", "model": "deepseek-v4-flash-el", "displayName": "DeepSeek-V4-Flash-EL", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/empiriolabs/deepseek-v4-flash-el" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "empiriolabs/deepseek-v4-flash-el", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "DeepSeek-V4-Flash-EL" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "empiriolabs/deepseek-v4-flash-el", "modelKey": "empiriolabs/deepseek-v4-flash-el", "displayName": "DeepSeek-V4-Flash-EL", "metadata": { "lastUpdated": "2026-05-02", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "deepseek/deepseek-v4-flash-free", "provider": "deepseek", "model": "deepseek-v4-flash-free", "displayName": "DeepSeek V4 Flash Free", "family": "deepseek-flash-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/deepseek-v4-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "deepseek-v4-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash Free" ], "families": [ "deepseek-flash-free" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "deepseek-v4-flash-free", "modelKey": "deepseek-v4-flash-free", "displayName": "DeepSeek V4 Flash Free", "family": "deepseek-flash-free", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } } ] }, { "id": "deepseek/deepseek-v4-flash:thinking", "provider": "deepseek", "model": "deepseek-v4-flash:thinking", "displayName": "DeepSeek V4 Flash (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek/deepseek-v4-flash:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-flash:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Flash (Thinking)" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-flash:thinking", "modelKey": "deepseek/deepseek-v4-flash:thinking", "displayName": "DeepSeek V4 Flash (Thinking)", "metadata": { "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } } ] }, { "id": "deepseek/deepseek-v4-pro", "provider": "deepseek", "model": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "anyapi", "auriko", "azure", "baseten", "cortecs", "crof", "deepinfra", "deepseek", "digitalocean", "fastrouter", "fireworks-ai", "frogbot", "gmicloud", "huggingface", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nebius", "novita-ai", "nvidia", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "routing-run", "siliconflow", "siliconflow-cn", "togetherai", "venice", "vercel", "vivgrid", "wafer.ai", "zenmux" ], "aliases": [ "alibaba-cn/deepseek-v4-pro", "alibaba-token-plan-cn/deepseek-v4-pro", "alibaba-token-plan/deepseek-v4-pro", "anyapi/deepseek/deepseek-v4-pro", "auriko/deepseek-v4-pro", "azure/deepseek-v4-pro", "baseten/deepseek-ai/DeepSeek-V4-Pro", "cortecs/deepseek-v4-pro", "crof/deepseek-v4-pro", "deepinfra/deepseek-ai/DeepSeek-V4-Pro", "deepseek/deepseek-v4-pro", "digitalocean/deepseek-v4-pro", "fastrouter/deepseek/deepseek-v4-pro", "fireworks-ai/accounts/fireworks/models/deepseek-v4-pro", "frogbot/deepseek-v4-pro", "gmicloud/deepseek-ai/DeepSeek-V4-Pro", "huggingface/deepseek-ai/DeepSeek-V4-Pro", "kilo/deepseek/deepseek-v4-pro", "llmgateway/deepseek-v4-pro", "merge-gateway/deepseek/deepseek-v4-pro", "nano-gpt/TEE/deepseek-v4-pro", "nano-gpt/deepseek/deepseek-v4-pro", "nebius/deepseek-ai/DeepSeek-V4-Pro", "novita-ai/deepseek/deepseek-v4-pro", "nvidia/deepseek-ai/deepseek-v4-pro", "ollama-cloud/deepseek-v4-pro", "opencode-go/deepseek-v4-pro", "opencode/deepseek-v4-pro", "openrouter/deepseek/deepseek-v4-pro", "orcarouter/deepseek/deepseek-v4-pro", "routing-run/route/deepseek-v4-pro", "siliconflow-cn/deepseek-ai/DeepSeek-V4-Pro", "siliconflow/deepseek-ai/deepseek-v4-pro", "togetherai/deepseek-ai/DeepSeek-V4-Pro", "venice/deepseek-v4-pro", "vercel/deepseek/deepseek-v4-pro", "vivgrid/deepseek-v4-pro", "wafer.ai/deepseek-v4-pro", "zenmux/deepseek/deepseek-v4-pro" ], "mergedProviderModelRecords": 39, "limits": { "contextTokens": 1049000, "inputTokens": 1048576, "outputTokens": 1048576, "supports1MContext": true }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "auriko", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "azure", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "baseten", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.145, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "cortecs", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 1.553, "output": 3.106 } }, { "source": "models.dev", "provider": "crof", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003, "input": 0.35, "output": 0.8 } }, { "source": "models.dev", "provider": "deepinfra", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 1.3, "output": 2.6 } }, { "source": "models.dev", "provider": "deepseek", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "digitalocean", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "fastrouter", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.145, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "frogbot", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "gmicloud", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.116, "input": 1.392, "output": 2.784 } }, { "source": "models.dev", "provider": "huggingface", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "kilo", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "llmgateway", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 2.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 5.25 } }, { "source": "models.dev", "provider": "nebius", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.75, "output": 3.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.69, "output": 3.38 } }, { "source": "models.dev", "provider": "nvidia", "model": "deepseek-ai/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "opencode-go", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0145, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "opencode", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.145, "input": 1.74, "output": 3.84 } }, { "source": "models.dev", "provider": "openrouter", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "orcarouter", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.56, "output": 1.12 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.4928, "output": 0.7392 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.145, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.145, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "togetherai", "model": "deepseek-ai/DeepSeek-V4-Pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "venice", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.33, "input": 1.73, "output": 3.796 } }, { "source": "models.dev", "provider": "vercel", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0036, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "vivgrid", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0, "input": 1.74, "output": 3.48 } }, { "source": "models.dev", "provider": "zenmux", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepseek/deepseek-v4-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro", "DeepSeek V4 Pro TEE", "DeepSeek v4 Pro", "DeepSeek-V4-Pro", "DeepSeek: DeepSeek V4 Pro", "Deepseek V4 Pro", "deepseek-ai/DeepSeek-V4-Pro", "deepseek-v4-pro" ], "families": [ "deepseek", "deepseek-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 39 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek-V4-Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "Deepseek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepseek", "providerName": "DeepSeek", "providerApi": "https://api.deepseek.com", "providerDoc": "https://api-docs.deepseek.com/quick_start/pricing", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/deepseek-v4-pro", "modelKey": "accounts/fireworks/models/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek v4 Pro", "family": "deepseek", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek: DeepSeek V4 Pro", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "metadata": { "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/deepseek-v4-pro", "modelKey": "TEE/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro TEE", "metadata": { "lastUpdated": "2026-04-25", "openWeights": false, "releaseDate": "2026-04-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "deepseek-ai/deepseek-v4-pro", "modelKey": "deepseek-ai/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "deepseek-v4-pro", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/deepseek-v4-pro", "modelKey": "route/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "deepseek-ai/DeepSeek-V4-Pro", "family": "deepseek-thinking", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/deepseek-v4-pro", "modelKey": "deepseek-ai/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "deepseek-ai/DeepSeek-V4-Pro", "modelKey": "deepseek-ai/DeepSeek-V4-Pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "deepseek-v4-pro", "modelKey": "deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-05-30", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "deepseek/deepseek-v4-pro", "modelKey": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepseek/deepseek-v4-pro", "displayName": "DeepSeek: DeepSeek V4 Pro", "metadata": { "canonicalSlug": "deepseek/deepseek-v4-pro-20260423", "createdAt": "2026-04-24T03:17:59.000Z", "huggingFaceId": "deepseek-ai/DeepSeek-V4-Pro", "links": { "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "xhigh", "high" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "DeepSeek", "topProvider": { "context_length": 1048576, "max_completion_tokens": 384000, "is_moderated": false } } } ] }, { "id": "deepseek/deepseek-v4-pro-6bit", "provider": "deepseek", "model": "deepseek-v4-pro-6bit", "displayName": "DeepSeek V4 Pro 6bit", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/deepseek-v4-pro-6bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/deepseek-v4-pro-6bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.4928, "output": 0.7392 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro 6bit" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/deepseek-v4-pro-6bit", "modelKey": "route/deepseek-v4-pro-6bit", "displayName": "DeepSeek V4 Pro 6bit", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "deepseek/deepseek-v4-pro-cheaper", "provider": "deepseek", "model": "deepseek-v4-pro-cheaper", "displayName": "DeepSeek V4 Pro Cheaper", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek/deepseek-v4-pro-cheaper" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-pro-cheaper", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro Cheaper" ], "releaseDate": "2026-04-25", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-pro-cheaper", "modelKey": "deepseek/deepseek-v4-pro-cheaper", "displayName": "DeepSeek V4 Pro Cheaper", "metadata": { "lastUpdated": "2026-04-25", "openWeights": false, "releaseDate": "2026-04-25" } } ] }, { "id": "deepseek/deepseek-v4-pro-cheaper:thinking", "provider": "deepseek", "model": "deepseek-v4-pro-cheaper:thinking", "displayName": "DeepSeek V4 Pro Cheaper (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepseek/deepseek-v4-pro-cheaper:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-pro-cheaper:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.003625, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro Cheaper (Thinking)" ], "releaseDate": "2026-04-25", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-pro-cheaper:thinking", "modelKey": "deepseek/deepseek-v4-pro-cheaper:thinking", "displayName": "DeepSeek V4 Pro Cheaper (Thinking)", "metadata": { "lastUpdated": "2026-04-25", "openWeights": false, "releaseDate": "2026-04-25" } } ] }, { "id": "deepseek/deepseek-v4-pro-el", "provider": "deepseek", "model": "deepseek-v4-pro-el", "displayName": "DeepSeek-V4-Pro-EL", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/empiriolabs/deepseek-v4-pro-el" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "empiriolabs/deepseek-v4-pro-el", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.67, "output": 3.33 } } ] }, "metadata": { "displayNames": [ "DeepSeek-V4-Pro-EL" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "empiriolabs/deepseek-v4-pro-el", "modelKey": "empiriolabs/deepseek-v4-pro-el", "displayName": "DeepSeek-V4-Pro-EL", "metadata": { "lastUpdated": "2026-05-02", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "deepseek/deepseek-v4-pro-lightning", "provider": "deepseek", "model": "deepseek-v4-pro-lightning", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/deepseek-v4-pro-lightning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "deepseek-v4-pro-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro" ], "families": [ "deepseek-thinking" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "deepseek-v4-pro-lightning", "modelKey": "deepseek-v4-pro-lightning", "displayName": "DeepSeek V4 Pro", "family": "deepseek-thinking", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "deepseek/deepseek-v4-pro:thinking", "provider": "deepseek", "model": "deepseek-v4-pro:thinking", "displayName": "DeepSeek V4 Pro (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/deepseek-v4-pro:thinking", "nano-gpt/deepseek/deepseek-v4-pro:thinking" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepseek/deepseek-v4-pro:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 2.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/deepseek-v4-pro:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 5.25 } } ] }, "metadata": { "displayNames": [ "DeepSeek V4 Pro (Thinking)", "DeepSeek V4 Pro Thinking TEE" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepseek/deepseek-v4-pro:thinking", "modelKey": "deepseek/deepseek-v4-pro:thinking", "displayName": "DeepSeek V4 Pro (Thinking)", "metadata": { "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/deepseek-v4-pro:thinking", "modelKey": "TEE/deepseek-v4-pro:thinking", "displayName": "DeepSeek V4 Pro Thinking TEE", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2026-04-29" } } ] }, { "id": "deepseek/deepseek-vl2", "provider": "deepseek", "model": "deepseek-vl2", "displayName": "deepseek-ai/deepseek-vl2", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "siliconflow", "siliconflow-cn" ], "aliases": [ "siliconflow-cn/deepseek-ai/deepseek-vl2", "siliconflow/deepseek-ai/deepseek-vl2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "deepseek-ai/deepseek-vl2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "siliconflow", "model": "deepseek-ai/deepseek-vl2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "deepseek-ai/deepseek-vl2" ], "families": [ "deepseek" ], "releaseDate": "2024-12-13", "lastUpdated": "2025-11-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/deepseek-vl2", "modelKey": "deepseek-ai/deepseek-vl2", "displayName": "deepseek-ai/deepseek-vl2", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "deepseek-ai/deepseek-vl2", "modelKey": "deepseek-ai/deepseek-vl2", "displayName": "deepseek-ai/deepseek-vl2", "family": "deepseek", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2024-12-13" } } ] }, { "id": "digitalocean/alibaba-qwen3-32b", "provider": "digitalocean", "model": "alibaba-qwen3-32b", "displayName": "Qwen3-32B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/alibaba-qwen3-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "alibaba-qwen3-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.55 } } ] }, "metadata": { "displayNames": [ "Qwen3-32B" ], "families": [ "qwen" ], "releaseDate": "2025-04-30", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "alibaba-qwen3-32b", "modelKey": "alibaba-qwen3-32b", "displayName": "Qwen3-32B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2025-04-30", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } } ] }, { "id": "digitalocean/all-mini-lm-l6-v2", "provider": "digitalocean", "model": "all-mini-lm-l6-v2", "displayName": "All-MiniLM-L6-v2", "family": "text-embedding", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/all-mini-lm-l6-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256, "outputTokens": 384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "all-mini-lm-l6-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.009, "output": 0 } } ] }, "metadata": { "displayNames": [ "All-MiniLM-L6-v2" ], "families": [ "text-embedding" ], "releaseDate": "2021-08-30", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "all-mini-lm-l6-v2", "modelKey": "all-mini-lm-l6-v2", "displayName": "All-MiniLM-L6-v2", "family": "text-embedding", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2021-08-30" } } ] }, { "id": "digitalocean/anthropic-claude-3-opus", "provider": "digitalocean", "model": "anthropic-claude-3-opus", "displayName": "Claude 3 Opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-3-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-3-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude 3 Opus" ], "families": [ "claude-opus" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-08", "releaseDate": "2024-02-29", "lastUpdated": "2024-02-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-3-opus", "modelKey": "anthropic-claude-3-opus", "displayName": "Claude 3 Opus", "family": "claude-opus", "status": "deprecated", "metadata": { "knowledgeCutoff": "2023-08", "lastUpdated": "2024-02-29", "openWeights": false, "releaseDate": "2024-02-29" } } ] }, { "id": "digitalocean/anthropic-claude-3.5-haiku", "provider": "digitalocean", "model": "anthropic-claude-3.5-haiku", "displayName": "Claude 3.5 Haiku", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-3.5-haiku" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-3.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 1, "input": 0.8, "output": 4 } } ] }, "metadata": { "displayNames": [ "Claude 3.5 Haiku" ], "families": [ "claude-haiku" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-11-05", "lastUpdated": "2024-11-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-3.5-haiku", "modelKey": "anthropic-claude-3.5-haiku", "displayName": "Claude 3.5 Haiku", "family": "claude-haiku", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-11-05", "openWeights": false, "releaseDate": "2024-11-05" } } ] }, { "id": "digitalocean/anthropic-claude-3.5-sonnet", "provider": "digitalocean", "model": "anthropic-claude-3.5-sonnet", "displayName": "Claude 3.5 Sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-3.5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-3.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude 3.5 Sonnet" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-06-20", "lastUpdated": "2024-10-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-3.5-sonnet", "modelKey": "anthropic-claude-3.5-sonnet", "displayName": "Claude 3.5 Sonnet", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-06-20" } } ] }, { "id": "digitalocean/anthropic-claude-3.7-sonnet", "provider": "digitalocean", "model": "anthropic-claude-3.7-sonnet", "displayName": "Claude 3.7 Sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-3.7-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-3.7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Claude 3.7 Sonnet" ], "families": [ "claude-sonnet" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-11", "releaseDate": "2025-02-24", "lastUpdated": "2025-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-3.7-sonnet", "modelKey": "anthropic-claude-3.7-sonnet", "displayName": "Claude 3.7 Sonnet", "family": "claude-sonnet", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-4.1-opus", "provider": "digitalocean", "model": "anthropic-claude-4.1-opus", "displayName": "Claude Opus 4.1", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-4.1-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-4.1-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.1" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-4.1-opus", "modelKey": "anthropic-claude-4.1-opus", "displayName": "Claude Opus 4.1", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-4.5-haiku", "provider": "digitalocean", "model": "anthropic-claude-4.5-haiku", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-4.5-haiku" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-4.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-4.5-haiku", "modelKey": "anthropic-claude-4.5-haiku", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-4.5-sonnet", "provider": "digitalocean", "model": "anthropic-claude-4.5-sonnet", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-4.5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-4.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.5" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-4.5-sonnet", "modelKey": "anthropic-claude-4.5-sonnet", "displayName": "Claude Sonnet 4.5", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-4.6-sonnet", "provider": "digitalocean", "model": "anthropic-claude-4.6-sonnet", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-4.6-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-4.6-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4.6" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-4.6-sonnet", "modelKey": "anthropic-claude-4.6-sonnet", "displayName": "Claude Sonnet 4.6", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-fable-5", "provider": "digitalocean", "model": "anthropic-claude-fable-5", "displayName": "Anthropic Claude Fable 5", "family": "claude-fable", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-fable-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "Anthropic Claude Fable 5" ], "families": [ "claude-fable" ], "releaseDate": "2026-06-09", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-fable-5", "modelKey": "anthropic-claude-fable-5", "displayName": "Anthropic Claude Fable 5", "family": "claude-fable", "metadata": { "lastUpdated": "2026-06-12", "openWeights": false, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-haiku-4.5", "provider": "digitalocean", "model": "anthropic-claude-haiku-4.5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-haiku-4.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-haiku-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Claude Haiku 4.5" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-haiku-4.5", "modelKey": "anthropic-claude-haiku-4.5", "displayName": "Claude Haiku 4.5", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-opus-4", "provider": "digitalocean", "model": "anthropic-claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-opus-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-opus-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-opus-4", "modelKey": "anthropic-claude-opus-4", "displayName": "Claude Opus 4", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-opus-4.5", "provider": "digitalocean", "model": "anthropic-claude-opus-4.5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-opus-4.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-opus-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.5" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-opus-4.5", "modelKey": "anthropic-claude-opus-4.5", "displayName": "Claude Opus 4.5", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-opus-4.6", "provider": "digitalocean", "model": "anthropic-claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-opus-4.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-opus-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 }, "tiered": { "contextOver200K": { "input": 10, "output": 37.5, "cache_read": 0.5, "cache_write": 6.25 }, "tiers": [ { "input": 10, "output": 37.5, "cache_read": 0.5, "cache_write": 6.25, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.6" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-opus-4.6", "modelKey": "anthropic-claude-opus-4.6", "displayName": "Claude Opus 4.6", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-opus-4.7", "provider": "digitalocean", "model": "anthropic-claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-opus-4.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-opus-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.7" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-opus-4.7", "modelKey": "anthropic-claude-opus-4.7", "displayName": "Claude Opus 4.7", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-opus-4.8", "provider": "digitalocean", "model": "anthropic-claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-opus-4.8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-opus-4.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Claude Opus 4.8" ], "families": [ "claude-opus" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-opus-4.8", "modelKey": "anthropic-claude-opus-4.8", "displayName": "Claude Opus 4.8", "family": "claude-opus", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/anthropic-claude-sonnet-4", "provider": "digitalocean", "model": "anthropic-claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/anthropic-claude-sonnet-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "anthropic-claude-sonnet-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 }, "tiered": { "contextOver200K": { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75 }, "tiers": [ { "input": 6, "output": 22.5, "cache_read": 0.3, "cache_write": 3.75, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Claude Sonnet 4" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "anthropic-claude-sonnet-4", "modelKey": "anthropic-claude-sonnet-4", "displayName": "Claude Sonnet 4", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/arcee-trinity-large-thinking", "provider": "digitalocean", "model": "arcee-trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/arcee-trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "arcee-trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.25, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Trinity Large Thinking" ], "families": [ "trinity" ], "statuses": [ "beta" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "arcee-trinity-large-thinking", "modelKey": "arcee-trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "status": "beta", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/bge-m3", "provider": "digitalocean", "model": "bge-m3", "displayName": "BGE M3", "family": "bge", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/bge-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "bge-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE M3" ], "families": [ "bge" ], "releaseDate": "2024-01-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "bge-m3", "modelKey": "bge-m3", "displayName": "BGE M3", "family": "bge", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2024-01-30" } } ] }, { "id": "digitalocean/bge-reranker-v2-m3", "provider": "digitalocean", "model": "bge-reranker-v2-m3", "displayName": "BGE Reranker v2 M3", "family": "bge", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/bge-reranker-v2-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "bge-reranker-v2-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Reranker v2 M3" ], "families": [ "bge" ], "releaseDate": "2024-03-12", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "bge-reranker-v2-m3", "modelKey": "bge-reranker-v2-m3", "displayName": "BGE Reranker v2 M3", "family": "bge", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2024-03-12" } } ] }, { "id": "digitalocean/e5-large-v2", "provider": "digitalocean", "model": "e5-large-v2", "displayName": "E5 Large v2", "family": "text-embedding", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/e5-large-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "e5-large-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "displayNames": [ "E5 Large v2" ], "families": [ "text-embedding" ], "releaseDate": "2023-05-19", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "e5-large-v2", "modelKey": "e5-large-v2", "displayName": "E5 Large v2", "family": "text-embedding", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2023-05-19" } } ] }, { "id": "digitalocean/fast-sdxl", "provider": "digitalocean", "model": "fast-sdxl", "displayName": "Fast SDXL", "family": "stable-diffusion", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/fal-ai/fast-sdxl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Fast SDXL" ], "families": [ "stable-diffusion" ], "releaseDate": "2023-07-26", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "fal-ai/fast-sdxl", "modelKey": "fal-ai/fast-sdxl", "displayName": "Fast SDXL", "family": "stable-diffusion", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2023-07-26" } } ] }, { "id": "digitalocean/gemma-4-31b-it", "provider": "digitalocean", "model": "gemma-4-31b-it", "displayName": "Gemma 4 31B", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/gemma-4-31B-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B" ], "families": [ "gemma" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "gemma-4-31B-it", "modelKey": "gemma-4-31B-it", "displayName": "Gemma 4 31B", "family": "gemma", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "digitalocean/gte-large-en-v1.5", "provider": "digitalocean", "model": "gte-large-en-v1.5", "displayName": "GTE Large (v1.5)", "family": "text-embedding", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/gte-large-en-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "gte-large-en-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0 } } ] }, "metadata": { "displayNames": [ "GTE Large (v1.5)" ], "families": [ "text-embedding" ], "releaseDate": "2024-03-27", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "gte-large-en-v1.5", "modelKey": "gte-large-en-v1.5", "displayName": "GTE Large (v1.5)", "family": "text-embedding", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2024-03-27" } } ] }, { "id": "digitalocean/llama3-8b-instruct", "provider": "digitalocean", "model": "llama3-8b-instruct", "displayName": "Llama 3.1 Instruct (8B)", "family": "llama", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/llama3-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "llama3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.198, "output": 0.198 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 Instruct (8B)" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "llama3-8b-instruct", "modelKey": "llama3-8b-instruct", "displayName": "Llama 3.1 Instruct (8B)", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "digitalocean/llama3.3-70b-instruct", "provider": "digitalocean", "model": "llama3.3-70b-instruct", "displayName": "Llama 3.3 Instruct 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/llama3.3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "llama3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 Instruct 70B" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "llama3.3-70b-instruct", "modelKey": "llama3.3-70b-instruct", "displayName": "Llama 3.3 Instruct 70B", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } } ] }, { "id": "digitalocean/multi-qa-mpnet-base-dot-v1", "provider": "digitalocean", "model": "multi-qa-mpnet-base-dot-v1", "displayName": "Multi-QA-mpnet-base-dot-v1", "family": "text-embedding", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/multi-qa-mpnet-base-dot-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "multi-qa-mpnet-base-dot-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.009, "output": 0 } } ] }, "metadata": { "displayNames": [ "Multi-QA-mpnet-base-dot-v1" ], "families": [ "text-embedding" ], "releaseDate": "2021-08-30", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "multi-qa-mpnet-base-dot-v1", "modelKey": "multi-qa-mpnet-base-dot-v1", "displayName": "Multi-QA-mpnet-base-dot-v1", "family": "text-embedding", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2021-08-30" } } ] }, { "id": "digitalocean/multilingual-v2", "provider": "digitalocean", "model": "multilingual-v2", "displayName": "ElevenLabs Multilingual TTS v2", "family": "elevenlabs", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/fal-ai/elevenlabs/tts/multilingual-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ElevenLabs Multilingual TTS v2" ], "families": [ "elevenlabs" ], "releaseDate": "2023-08-22", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "fal-ai/elevenlabs/tts/multilingual-v2", "modelKey": "fal-ai/elevenlabs/tts/multilingual-v2", "displayName": "ElevenLabs Multilingual TTS v2", "family": "elevenlabs", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2023-08-22" } } ] }, { "id": "digitalocean/nemotron-3-nano-30b", "provider": "digitalocean", "model": "nemotron-3-nano-30b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/nemotron-3-nano-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Nemotron 3 Nano 30B A3B" ], "families": [ "nemotron" ], "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "nemotron-3-nano-30b", "modelKey": "nemotron-3-nano-30b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "metadata": { "lastUpdated": "2025-04-14", "openWeights": true, "releaseDate": "2025-04-14", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } } ] }, { "id": "digitalocean/nemotron-3-nano-omni", "provider": "digitalocean", "model": "nemotron-3-nano-omni", "displayName": "Nemotron Nano 3 Omni", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/nemotron-3-nano-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "nemotron-3-nano-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Nemotron Nano 3 Omni" ], "families": [ "nemotron" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "nemotron-3-nano-omni", "modelKey": "nemotron-3-nano-omni", "displayName": "Nemotron Nano 3 Omni", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-04-28", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } } ] }, { "id": "digitalocean/nemotron-3-ultra-550b", "provider": "digitalocean", "model": "nemotron-3-ultra-550b", "displayName": "Nemotron 3 Ultra", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/nemotron-3-ultra-550b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Nemotron 3 Ultra" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "nemotron-3-ultra-550b", "modelKey": "nemotron-3-ultra-550b", "displayName": "Nemotron 3 Ultra", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-12", "openWeights": false, "releaseDate": "2026-06-04" } } ] }, { "id": "digitalocean/nemotron-nano-12b-v2-vl", "provider": "digitalocean", "model": "nemotron-nano-12b-v2-vl", "displayName": "Nemotron Nano 12B v2 VL", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/nemotron-nano-12b-v2-vl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "nemotron-nano-12b-v2-vl", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Nemotron Nano 12B v2 VL" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-01", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "nemotron-nano-12b-v2-vl", "modelKey": "nemotron-nano-12b-v2-vl", "displayName": "Nemotron Nano 12B v2 VL", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-12-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } } ] }, { "id": "digitalocean/nvidia-nemotron-3-super-120b", "provider": "digitalocean", "model": "nvidia-nemotron-3-super-120b", "displayName": "Nemotron-3-Super-120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/nvidia-nemotron-3-super-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "nvidia-nemotron-3-super-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "Nemotron-3-Super-120B" ], "families": [ "nemotron" ], "statuses": [ "beta" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-03-11", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "nvidia-nemotron-3-super-120b", "modelKey": "nvidia-nemotron-3-super-120b", "displayName": "Nemotron-3-Super-120B", "family": "nemotron", "status": "beta", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-4.1", "provider": "digitalocean", "model": "openai-gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1047576, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "GPT-4.1" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-4.1", "modelKey": "openai-gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } } ] }, { "id": "digitalocean/openai-gpt-4o", "provider": "digitalocean", "model": "openai-gpt-4o", "displayName": "GPT-4o", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-4o" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-4o" ], "families": [ "gpt" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-05-13", "lastUpdated": "2024-08-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-4o", "modelKey": "openai-gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } } ] }, { "id": "digitalocean/openai-gpt-4o-mini", "provider": "digitalocean", "model": "openai-gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-4o-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "GPT-4o mini" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-07-18", "lastUpdated": "2024-07-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-4o-mini", "modelKey": "openai-gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } } ] }, { "id": "digitalocean/openai-gpt-5", "provider": "digitalocean", "model": "openai-gpt-5", "displayName": "GPT-5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-5" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5", "modelKey": "openai-gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5-mini", "provider": "digitalocean", "model": "openai-gpt-5-mini", "displayName": "GPT-5 mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "GPT-5 mini" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5-mini", "modelKey": "openai-gpt-5-mini", "displayName": "GPT-5 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5-nano", "provider": "digitalocean", "model": "openai-gpt-5-nano", "displayName": "GPT-5 nano", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GPT-5 nano" ], "families": [ "gpt-nano" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5-nano", "modelKey": "openai-gpt-5-nano", "displayName": "GPT-5 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.1-codex-max", "provider": "digitalocean", "model": "openai-gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.1-codex-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-5.1 Codex Max" ], "families": [ "gpt-codex" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.1-codex-max", "modelKey": "openai-gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.2", "provider": "digitalocean", "model": "openai-gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.2" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.2", "modelKey": "openai-gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.2-pro", "provider": "digitalocean", "model": "openai-gpt-5.2-pro", "displayName": "GPT-5.2 pro", "family": "gpt-pro", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } } ] }, "metadata": { "displayNames": [ "GPT-5.2 pro" ], "families": [ "gpt-pro" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.2-pro", "modelKey": "openai-gpt-5.2-pro", "displayName": "GPT-5.2 pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.3-codex", "provider": "digitalocean", "model": "openai-gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.3-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Codex" ], "families": [ "gpt-codex" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.3-codex", "modelKey": "openai-gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.4", "provider": "digitalocean", "model": "openai-gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } } ] }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.4", "modelKey": "openai-gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.4-mini", "provider": "digitalocean", "model": "openai-gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.4-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 mini" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.4-mini", "modelKey": "openai-gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.4-nano", "provider": "digitalocean", "model": "openai-gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.4-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 nano" ], "families": [ "gpt-nano" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.4-nano", "modelKey": "openai-gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.4-pro", "provider": "digitalocean", "model": "openai-gpt-5.4-pro", "displayName": "GPT-5.4 pro", "family": "gpt-pro", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.4-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 pro" ], "families": [ "gpt-pro" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.4-pro", "modelKey": "openai-gpt-5.4-pro", "displayName": "GPT-5.4 pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-5.5", "provider": "digitalocean", "model": "openai-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-5.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-5.5", "modelKey": "openai-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-image-1", "provider": "digitalocean", "model": "openai-gpt-image-1", "displayName": "GPT Image 1", "family": "gpt-image", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-image-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-image-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 40 } } ] }, "metadata": { "displayNames": [ "GPT Image 1" ], "families": [ "gpt-image" ], "releaseDate": "2025-04-24", "lastUpdated": "2025-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-image-1", "modelKey": "openai-gpt-image-1", "displayName": "GPT Image 1", "family": "gpt-image", "metadata": { "lastUpdated": "2025-04-24", "openWeights": false, "releaseDate": "2025-04-24" } } ] }, { "id": "digitalocean/openai-gpt-image-1.5", "provider": "digitalocean", "model": "openai-gpt-image-1.5", "displayName": "GPT Image 1.5", "family": "gpt-image", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-image-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-image-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "input": 5, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT Image 1.5" ], "families": [ "gpt-image" ], "releaseDate": "2025-11-25", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-image-1.5", "modelKey": "openai-gpt-image-1.5", "displayName": "GPT Image 1.5", "family": "gpt-image", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } } ] }, { "id": "digitalocean/openai-gpt-image-2", "provider": "digitalocean", "model": "openai-gpt-image-2", "displayName": "GPT Image 2", "family": "gpt-image", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-image-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT Image 2" ], "families": [ "gpt-image" ], "releaseDate": "2025-04-24", "lastUpdated": "2025-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-image-2", "modelKey": "openai-gpt-image-2", "displayName": "GPT Image 2", "family": "gpt-image", "metadata": { "lastUpdated": "2025-04-24", "openWeights": false, "releaseDate": "2025-04-24" } } ] }, { "id": "digitalocean/openai-gpt-oss-120b", "provider": "digitalocean", "model": "openai-gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-oss-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "gpt-oss-120b" ], "families": [ "gpt-oss" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-oss-120b", "modelKey": "openai-gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-gpt-oss-20b", "provider": "digitalocean", "model": "openai-gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-gpt-oss-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.45 } } ] }, "metadata": { "displayNames": [ "gpt-oss-20b" ], "families": [ "gpt-oss" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-gpt-oss-20b", "modelKey": "openai-gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-o1", "provider": "digitalocean", "model": "openai-o1", "displayName": "o1", "family": "o", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "o1" ], "families": [ "o" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-o1", "modelKey": "openai-o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-o3", "provider": "digitalocean", "model": "openai-o3", "displayName": "o3", "family": "o", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "o3" ], "families": [ "o" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-o3", "modelKey": "openai-o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/openai-o3-mini", "provider": "digitalocean", "model": "openai-o3-mini", "displayName": "o3-mini", "family": "o-mini", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/openai-o3-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "openai-o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "o3-mini" ], "families": [ "o-mini" ], "knowledgeCutoff": "2024-05", "releaseDate": "2024-12-20", "lastUpdated": "2025-01-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "openai-o3-mini", "modelKey": "openai-o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "digitalocean/schnell", "provider": "digitalocean", "model": "schnell", "displayName": "FLUX.1 [schnell]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/fal-ai/flux/schnell" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.1 [schnell]" ], "families": [ "flux" ], "releaseDate": "2024-08-01", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "fal-ai/flux/schnell", "modelKey": "fal-ai/flux/schnell", "displayName": "FLUX.1 [schnell]", "family": "flux", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2024-08-01" } } ] }, { "id": "digitalocean/stable-diffusion-3.5-large", "provider": "digitalocean", "model": "stable-diffusion-3.5-large", "displayName": "Stable Diffusion 3.5 Large", "family": "stable-diffusion", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/stable-diffusion-3.5-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256, "outputTokens": 1, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "stable-diffusion-3.5-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0 } } ] }, "metadata": { "displayNames": [ "Stable Diffusion 3.5 Large" ], "families": [ "stable-diffusion" ], "releaseDate": "2024-10-22", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "stable-diffusion-3.5-large", "modelKey": "stable-diffusion-3.5-large", "displayName": "Stable Diffusion 3.5 Large", "family": "stable-diffusion", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2024-10-22" } } ] }, { "id": "digitalocean/text-to-audio", "provider": "digitalocean", "model": "text-to-audio", "displayName": "Stable Audio 2.5 (Text-to-Audio)", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/fal-ai/stable-audio-25/text-to-audio" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Stable Audio 2.5 (Text-to-Audio)" ], "releaseDate": "2025-10-08", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "fal-ai/stable-audio-25/text-to-audio", "modelKey": "fal-ai/stable-audio-25/text-to-audio", "displayName": "Stable Audio 2.5 (Text-to-Audio)", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2025-10-08" } } ] }, { "id": "digitalocean/wan2-2-t2v-a14b", "provider": "digitalocean", "model": "wan2-2-t2v-a14b", "displayName": "Wan2.2-T2V-A14B", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/wan2-2-t2v-a14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 100, "outputTokens": 1, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "wan2-2-t2v-a14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 0 } } ] }, "metadata": { "displayNames": [ "Wan2.2-T2V-A14B" ], "releaseDate": "2025-07-28", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "wan2-2-t2v-a14b", "modelKey": "wan2-2-t2v-a14b", "displayName": "Wan2.2-T2V-A14B", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-07-28" } } ] }, { "id": "duckduckgo/search", "provider": "duckduckgo", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "duckduckgo" ], "aliases": [ "duckduckgo/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "duckduckgo", "model": "duckduckgo/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "duckduckgo", "model": "duckduckgo/search", "mode": "search", "metadata": { "metadata": { "notes": "DuckDuckGo Instant Answer API is free and does not require an API key." } } } ] }, { "id": "elevenlabs/eleven-multilingual-v2", "provider": "elevenlabs", "model": "eleven-multilingual-v2", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "elevenlabs" ], "aliases": [ "elevenlabs/eleven_multilingual_v2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "elevenlabs", "model": "elevenlabs/eleven_multilingual_v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00018 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "elevenlabs", "model": "elevenlabs/eleven_multilingual_v2", "mode": "audio_speech", "metadata": { "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "source": "https://elevenlabs.io/pricing", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "elevenlabs/eleven-v3", "provider": "elevenlabs", "model": "eleven-v3", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "elevenlabs" ], "aliases": [ "elevenlabs/eleven_v3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "elevenlabs", "model": "elevenlabs/eleven_v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00018 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "elevenlabs", "model": "elevenlabs/eleven_v3", "mode": "audio_speech", "metadata": { "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "source": "https://elevenlabs.io/pricing", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "elevenlabs/scribe-v1", "provider": "elevenlabs", "model": "scribe-v1", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "elevenlabs" ], "aliases": [ "elevenlabs/scribe_v1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "elevenlabs", "model": "elevenlabs/scribe_v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0000611 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "elevenlabs", "model": "elevenlabs/scribe_v1", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", "original_pricing_per_hour": 0.22 }, "source": "https://elevenlabs.io/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "elevenlabs/scribe-v1-experimental", "provider": "elevenlabs", "model": "scribe-v1-experimental", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "elevenlabs" ], "aliases": [ "elevenlabs/scribe_v1_experimental" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "elevenlabs", "model": "elevenlabs/scribe_v1_experimental", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0000611 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "elevenlabs", "model": "elevenlabs/scribe_v1_experimental", "mode": "audio_transcription", "metadata": { "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", "original_pricing_per_hour": 0.22 }, "source": "https://elevenlabs.io/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "evroc/kb-whisper-large", "provider": "evroc", "model": "kb-whisper-large", "displayName": "KB Whisper", "family": "whisper", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/KBLab/kb-whisper-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 448, "outputTokens": 448, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "KBLab/kb-whisper-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.00236, "output": 0.00236, "outputAudio": 2.36 } } ] }, "metadata": { "displayNames": [ "KB Whisper" ], "families": [ "whisper" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "KBLab/kb-whisper-large", "modelKey": "KBLab/kb-whisper-large", "displayName": "KB Whisper", "family": "whisper", "metadata": { "lastUpdated": "2024-10-01", "openWeights": true, "releaseDate": "2024-10-01" } } ] }, { "id": "evroc/multilingual-e5-large-instruct", "provider": "evroc", "model": "multilingual-e5-large-instruct", "displayName": "E5 Multi-Lingual Large Embeddings 0.6B", "family": "text-embedding", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/intfloat/multilingual-e5-large-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "intfloat/multilingual-e5-large-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "E5 Multi-Lingual Large Embeddings 0.6B" ], "families": [ "text-embedding" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "intfloat/multilingual-e5-large-instruct", "modelKey": "intfloat/multilingual-e5-large-instruct", "displayName": "E5 Multi-Lingual Large Embeddings 0.6B", "family": "text-embedding", "metadata": { "lastUpdated": "2024-06-01", "openWeights": true, "releaseDate": "2024-06-01" } } ] }, { "id": "evroc/phi-4-multimodal-instruct", "provider": "evroc", "model": "phi-4-multimodal-instruct", "displayName": "Phi-4 15B", "family": "phi", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/microsoft/Phi-4-multimodal-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "microsoft/Phi-4-multimodal-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.47 } } ] }, "metadata": { "displayNames": [ "Phi-4 15B" ], "families": [ "phi" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "microsoft/Phi-4-multimodal-instruct", "modelKey": "microsoft/Phi-4-multimodal-instruct", "displayName": "Phi-4 15B", "family": "phi", "metadata": { "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "exa-ai/search", "provider": "exa-ai", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "exa_ai" ], "aliases": [ "exa_ai/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "exa_ai", "model": "exa_ai/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "exa_ai", "model": "exa_ai/search", "mode": "search" } ] }, { "id": "fal-ai/3.2", "provider": "fal-ai", "model": "3.2", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/bria/text-to-image/3.2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/bria/text-to-image/3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.0398 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/bria/text-to-image/3.2", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/fast", "provider": "fal-ai", "model": "fast", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/imagen4/preview/fast" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview/fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview/fast", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/nano-banana", "provider": "fal-ai", "model": "nano-banana", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/nano-banana" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/nano-banana", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.039 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/nano-banana", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/preview", "provider": "fal-ai", "model": "preview", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/imagen4/preview" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.0398 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/schnell", "provider": "fal-ai", "model": "schnell", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/flux/schnell" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux/schnell", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.003 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux/schnell", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/stable-diffusion-v35-medium", "provider": "fal-ai", "model": "stable-diffusion-v35-medium", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/stable-diffusion-v35-medium" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/stable-diffusion-v35-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.0398 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/stable-diffusion-v35-medium", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/text-to-image", "provider": "fal-ai", "model": "text-to-image", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image", "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image", "fal_ai/fal-ai/recraft/v3/text-to-image" ], "mergedProviderModelRecords": 3, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.03 } }, { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.03 } }, { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/recraft/v3/text-to-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.0398 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/recraft/v3/text-to-image", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/ultra", "provider": "fal-ai", "model": "ultra", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/imagen4/preview/ultra" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview/ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/imagen4/preview/ultra", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/v1.1", "provider": "fal-ai", "model": "v1.1", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/flux-pro/v1.1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux-pro/v1.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux-pro/v1.1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/v1.1-ultra", "provider": "fal-ai", "model": "v1.1-ultra", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/flux-pro/v1.1-ultra" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux-pro/v1.1-ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/flux-pro/v1.1-ultra", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fal-ai/v3", "provider": "fal-ai", "model": "v3", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/ideogram/v3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/ideogram/v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/ideogram/v3", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "fastrouter/lucid-origin", "provider": "fastrouter", "model": "lucid-origin", "displayName": "Lucid Origin", "family": "lucid", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/leonardo-ai/lucid-origin" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Lucid Origin" ], "families": [ "lucid" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "leonardo-ai/lucid-origin", "modelKey": "leonardo-ai/lucid-origin", "displayName": "Lucid Origin", "family": "lucid", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "fastrouter/lucid-realism", "provider": "fastrouter", "model": "lucid-realism", "displayName": "Lucid Realism", "family": "lucid", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/leonardo-ai/lucid-realism" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Lucid Realism" ], "families": [ "lucid" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "leonardo-ai/lucid-realism", "modelKey": "leonardo-ai/lucid-realism", "displayName": "Lucid Realism", "family": "lucid", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "fastrouter/sarvam-105b", "provider": "fastrouter", "model": "sarvam-105b", "displayName": "Sarvam 105B", "family": "sarvam", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/sarvam/sarvam-105b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "sarvam/sarvam-105b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "Sarvam 105B" ], "families": [ "sarvam" ], "releaseDate": "2025-09-01", "lastUpdated": "2025-09-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "sarvam/sarvam-105b", "modelKey": "sarvam/sarvam-105b", "displayName": "Sarvam 105B", "family": "sarvam", "metadata": { "lastUpdated": "2025-09-01", "openWeights": true, "releaseDate": "2025-09-01" } } ] }, { "id": "fastrouter/sarvam-30b", "provider": "fastrouter", "model": "sarvam-30b", "displayName": "Sarvam 30B", "family": "sarvam", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/sarvam/sarvam-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "sarvam/sarvam-30b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Sarvam 30B" ], "families": [ "sarvam" ], "releaseDate": "2026-02-18", "lastUpdated": "2026-02-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "sarvam/sarvam-30b", "modelKey": "sarvam/sarvam-30b", "displayName": "Sarvam 30B", "family": "sarvam", "metadata": { "lastUpdated": "2026-02-18", "openWeights": true, "releaseDate": "2026-02-18" } } ] }, { "id": "fastrouter/seedance-2", "provider": "fastrouter", "model": "seedance-2", "displayName": "Seedance 2", "family": "seed", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/bytedance/seedance-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance 2" ], "families": [ "seed" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "bytedance/seedance-2", "modelKey": "bytedance/seedance-2", "displayName": "Seedance 2", "family": "seed", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } } ] }, { "id": "featherless-ai/qwerky-72b", "provider": "featherless-ai", "model": "qwerky-72b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "featherless_ai" ], "aliases": [ "featherless_ai/featherless-ai/Qwerky-72B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "featherless_ai", "model": "featherless_ai/featherless-ai/Qwerky-72B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "featherless_ai", "model": "featherless_ai/featherless-ai/Qwerky-72B", "mode": "chat" } ] }, { "id": "featherless-ai/qwerky-qwq-32b", "provider": "featherless-ai", "model": "qwerky-qwq-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "featherless_ai" ], "aliases": [ "featherless_ai/featherless-ai/Qwerky-QwQ-32B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "featherless_ai", "model": "featherless_ai/featherless-ai/Qwerky-QwQ-32B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "featherless_ai", "model": "featherless_ai/featherless-ai/Qwerky-QwQ-32B", "mode": "chat" } ] }, { "id": "firecrawl/search", "provider": "firecrawl", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "firecrawl" ], "aliases": [ "firecrawl/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "firecrawl", "model": "firecrawl/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "firecrawl", "model": "firecrawl/search", "mode": "search", "metadata": { "metadata": { "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" } } } ] }, { "id": "fireworks-ai-embedding-models/fireworks-ai-embedding-150m-to-350m", "provider": "fireworks-ai-embedding-models", "model": "fireworks-ai-embedding-150m-to-350m", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks-ai-embedding-150m-to-350m" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks-ai-embedding-150m-to-350m", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.016, "output": 0 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks-ai-embedding-150m-to-350m" } ] }, { "id": "fireworks-ai-embedding-models/fireworks-ai-embedding-up-to-150m", "provider": "fireworks-ai-embedding-models", "model": "fireworks-ai-embedding-up-to-150m", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks-ai-embedding-up-to-150m" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks-ai-embedding-up-to-150m", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks-ai-embedding-up-to-150m" } ] }, { "id": "fireworks-ai-embedding-models/gte-base", "provider": "fireworks-ai-embedding-models", "model": "gte-base", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks_ai/thenlper/gte-base" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/thenlper/gte-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/thenlper/gte-base", "mode": "embedding", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai-embedding-models/gte-large", "provider": "fireworks-ai-embedding-models", "model": "gte-large", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks_ai/thenlper/gte-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/thenlper/gte-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.016, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/thenlper/gte-large", "mode": "embedding", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai-embedding-models/nomic-embed-text-v1", "provider": "fireworks-ai-embedding-models", "model": "nomic-embed-text-v1", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks_ai/nomic-ai/nomic-embed-text-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/nomic-ai/nomic-embed-text-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/nomic-ai/nomic-embed-text-v1", "mode": "embedding", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai-embedding-models/nomic-embed-text-v1.5", "provider": "fireworks-ai-embedding-models", "model": "nomic-embed-text-v1.5", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks_ai/nomic-ai/nomic-embed-text-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/nomic-ai/nomic-embed-text-v1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/nomic-ai/nomic-embed-text-v1.5", "mode": "embedding", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai-embedding-models/uae-large-v1", "provider": "fireworks-ai-embedding-models", "model": "uae-large-v1", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai-embedding-models" ], "aliases": [ "fireworks_ai-embedding-models/fireworks_ai/WhereIsAI/UAE-Large-V1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/WhereIsAI/UAE-Large-V1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.016, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai-embedding-models", "model": "fireworks_ai/WhereIsAI/UAE-Large-V1", "mode": "embedding", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai/chronos-hermes-13b-v2", "provider": "fireworks-ai", "model": "chronos-hermes-13b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-13b", "provider": "fireworks-ai", "model": "code-llama-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-13b-instruct", "provider": "fireworks-ai", "model": "code-llama-13b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-13b-python", "provider": "fireworks-ai", "model": "code-llama-13b-python", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-13b-python" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b-python", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-13b-python", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-34b", "provider": "fireworks-ai", "model": "code-llama-34b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-34b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-34b-instruct", "provider": "fireworks-ai", "model": "code-llama-34b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-34b-python", "provider": "fireworks-ai", "model": "code-llama-34b-python", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-34b-python" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b-python", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-34b-python", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-70b", "provider": "fireworks-ai", "model": "code-llama-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-70b-instruct", "provider": "fireworks-ai", "model": "code-llama-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-70b-python", "provider": "fireworks-ai", "model": "code-llama-70b-python", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-70b-python" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b-python", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-70b-python", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-7b", "provider": "fireworks-ai", "model": "code-llama-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-7b-instruct", "provider": "fireworks-ai", "model": "code-llama-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/code-llama-7b-python", "provider": "fireworks-ai", "model": "code-llama-7b-python", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-llama-7b-python" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b-python", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-llama-7b-python", "mode": "chat" } ] }, { "id": "fireworks-ai/code-qwen-1p5-7b", "provider": "fireworks-ai", "model": "code-qwen-1p5-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/codegemma-2b", "provider": "fireworks-ai", "model": "codegemma-2b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/codegemma-2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/codegemma-2b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/codegemma-2b", "mode": "chat" } ] }, { "id": "fireworks-ai/codegemma-7b", "provider": "fireworks-ai", "model": "codegemma-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/codegemma-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/codegemma-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/codegemma-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-671b-v2-p1", "provider": "fireworks-ai", "model": "cogito-671b-v2-p1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-v1-preview-llama-3b", "provider": "fireworks-ai", "model": "cogito-v1-preview-llama-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-v1-preview-llama-70b", "provider": "fireworks-ai", "model": "cogito-v1-preview-llama-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-v1-preview-llama-8b", "provider": "fireworks-ai", "model": "cogito-v1-preview-llama-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-v1-preview-qwen-14b", "provider": "fireworks-ai", "model": "cogito-v1-preview-qwen-14b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b", "mode": "chat" } ] }, { "id": "fireworks-ai/cogito-v1-preview-qwen-32b", "provider": "fireworks-ai", "model": "cogito-v1-preview-qwen-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b", "mode": "chat" } ] }, { "id": "fireworks-ai/dbrx-instruct", "provider": "fireworks-ai", "model": "dbrx-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/dbrx-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dbrx-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dbrx-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/dobby-mini-unhinged-plus-llama-3-1-8b", "provider": "fireworks-ai", "model": "dobby-mini-unhinged-plus-llama-3-1-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b", "mode": "chat" } ] }, { "id": "fireworks-ai/dobby-unhinged-llama-3-3-70b-new", "provider": "fireworks-ai", "model": "dobby-unhinged-llama-3-3-70b-new", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new", "mode": "chat" } ] }, { "id": "fireworks-ai/dolphin-2-9-2-qwen2-72b", "provider": "fireworks-ai", "model": "dolphin-2-9-2-qwen2-72b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b", "mode": "chat" } ] }, { "id": "fireworks-ai/dolphin-2p6-mixtral-8x7b", "provider": "fireworks-ai", "model": "dolphin-2p6-mixtral-8x7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b", "mode": "chat" } ] }, { "id": "fireworks-ai/ernie-4p5-21b-a3b-pt", "provider": "fireworks-ai", "model": "ernie-4p5-21b-a3b-pt", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt", "mode": "chat" } ] }, { "id": "fireworks-ai/ernie-4p5-300b-a47b-pt", "provider": "fireworks-ai", "model": "ernie-4p5-300b-a47b-pt", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt", "mode": "chat" } ] }, { "id": "fireworks-ai/fare-20b", "provider": "fireworks-ai", "model": "fare-20b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/fare-20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fare-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fare-20b", "mode": "chat" } ] }, { "id": "fireworks-ai/firefunction-v1", "provider": "fireworks-ai", "model": "firefunction-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/firefunction-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firefunction-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firefunction-v1", "mode": "chat" } ] }, { "id": "fireworks-ai/firefunction-v2", "provider": "fireworks-ai", "model": "firefunction-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/firefunction-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firefunction-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firefunction-v2", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai/firellava-13b", "provider": "fireworks-ai", "model": "firellava-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/firellava-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firellava-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firellava-13b", "mode": "chat" } ] }, { "id": "fireworks-ai/firesearch-ocr-v6", "provider": "fireworks-ai", "model": "firesearch-ocr-v6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6", "mode": "chat" } ] }, { "id": "fireworks-ai/fireworks-ai-4.1b-to-16b", "provider": "fireworks-ai", "model": "fireworks-ai-4.1b-to-16b", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-4.1b-to-16b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-4.1b-to-16b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-4.1b-to-16b" } ] }, { "id": "fireworks-ai/fireworks-ai-56b-to-176b", "provider": "fireworks-ai", "model": "fireworks-ai-56b-to-176b", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-56b-to-176b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-56b-to-176b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-56b-to-176b" } ] }, { "id": "fireworks-ai/fireworks-ai-above-16b", "provider": "fireworks-ai", "model": "fireworks-ai-above-16b", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-above-16b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-above-16b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-above-16b" } ] }, { "id": "fireworks-ai/fireworks-ai-default", "provider": "fireworks-ai", "model": "fireworks-ai-default", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-default" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-default", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-default" } ] }, { "id": "fireworks-ai/fireworks-ai-moe-up-to-56b", "provider": "fireworks-ai", "model": "fireworks-ai-moe-up-to-56b", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-moe-up-to-56b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-moe-up-to-56b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-moe-up-to-56b" } ] }, { "id": "fireworks-ai/fireworks-ai-up-to-4b", "provider": "fireworks-ai", "model": "fireworks-ai-up-to-4b", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/fireworks-ai-up-to-4b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks-ai-up-to-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks-ai-up-to-4b" } ] }, { "id": "fireworks-ai/fireworks-asr-large", "provider": "fireworks-ai", "model": "fireworks-asr-large", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/fireworks-asr-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fireworks-asr-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fireworks-asr-large", "mode": "audio_transcription" } ] }, { "id": "fireworks-ai/fireworks-asr-v2", "provider": "fireworks-ai", "model": "fireworks-asr-v2", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2", "mode": "audio_transcription" } ] }, { "id": "fireworks-ai/flux-1-dev", "provider": "fireworks-ai", "model": "flux-1-dev", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-1-dev" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev", "mode": "chat" } ] }, { "id": "fireworks-ai/flux-1-dev-controlnet-union", "provider": "fireworks-ai", "model": "flux-1-dev-controlnet-union", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.001, "output": 0.001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union", "mode": "chat" } ] }, { "id": "fireworks-ai/flux-1-dev-fp8", "provider": "fireworks-ai", "model": "flux-1-dev-fp8", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.0005, "output": 0.0005 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8", "mode": "image_generation" } ] }, { "id": "fireworks-ai/flux-1-schnell", "provider": "fireworks-ai", "model": "flux-1-schnell", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-1-schnell" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-schnell", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-schnell", "mode": "chat" } ] }, { "id": "fireworks-ai/flux-1-schnell-fp8", "provider": "fireworks-ai", "model": "flux-1-schnell-fp8", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00035, "output": 0.00035 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8", "mode": "image_generation" } ] }, { "id": "fireworks-ai/flux-kontext-max", "provider": "fireworks-ai", "model": "flux-kontext-max", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-kontext-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-kontext-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.08 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-kontext-max", "mode": "image_generation" } ] }, { "id": "fireworks-ai/flux-kontext-pro", "provider": "fireworks-ai", "model": "flux-kontext-pro", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/flux-kontext-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-kontext-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/flux-kontext-pro", "mode": "image_generation" } ] }, { "id": "fireworks-ai/gemma-2b-it", "provider": "fireworks-ai", "model": "gemma-2b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gemma-2b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-2b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-2b-it", "mode": "chat" } ] }, { "id": "fireworks-ai/gemma-3-27b-it", "provider": "fireworks-ai", "model": "gemma-3-27b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it", "mode": "chat" } ] }, { "id": "fireworks-ai/gemma-7b", "provider": "fireworks-ai", "model": "gemma-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gemma-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/gemma-7b-it", "provider": "fireworks-ai", "model": "gemma-7b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gemma-7b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-7b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma-7b-it", "mode": "chat" } ] }, { "id": "fireworks-ai/gemma2-9b-it", "provider": "fireworks-ai", "model": "gemma2-9b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gemma2-9b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma2-9b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gemma2-9b-it", "mode": "chat" } ] }, { "id": "fireworks-ai/hermes-2-pro-mistral-7b", "provider": "fireworks-ai", "model": "hermes-2-pro-mistral-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/internvl3-38b", "provider": "fireworks-ai", "model": "internvl3-38b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/internvl3-38b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-38b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-38b", "mode": "chat" } ] }, { "id": "fireworks-ai/internvl3-78b", "provider": "fireworks-ai", "model": "internvl3-78b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/internvl3-78b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-78b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-78b", "mode": "chat" } ] }, { "id": "fireworks-ai/internvl3-8b", "provider": "fireworks-ai", "model": "internvl3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/internvl3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/internvl3-8b", "mode": "chat" } ] }, { "id": "fireworks-ai/japanese-stable-diffusion-xl", "provider": "fireworks-ai", "model": "japanese-stable-diffusion-xl", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00013, "output": 0.00013 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl", "mode": "image_generation" } ] }, { "id": "fireworks-ai/kat-coder", "provider": "fireworks-ai", "model": "kat-coder", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/kat-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-coder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-coder", "mode": "chat" } ] }, { "id": "fireworks-ai/kat-dev-32b", "provider": "fireworks-ai", "model": "kat-dev-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/kat-dev-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-dev-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-dev-32b", "mode": "chat" } ] }, { "id": "fireworks-ai/kat-dev-72b-exp", "provider": "fireworks-ai", "model": "kat-dev-72b-exp", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp", "mode": "chat" } ] }, { "id": "fireworks-ai/llama4-maverick-instruct-basic", "provider": "fireworks-ai", "model": "llama4-maverick-instruct-basic", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai/llama4-scout-instruct-basic", "provider": "fireworks-ai", "model": "llama4-scout-instruct-basic", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai/llamaguard-7b", "provider": "fireworks-ai", "model": "llamaguard-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llamaguard-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llamaguard-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llamaguard-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/llava-yi-34b", "provider": "fireworks-ai", "model": "llava-yi-34b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llava-yi-34b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llava-yi-34b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llava-yi-34b", "mode": "chat" } ] }, { "id": "fireworks-ai/models", "provider": "fireworks-ai", "model": "models", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "inputTokens": 40960, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/", "mode": "embedding" } ] }, { "id": "fireworks-ai/mythomax-l2-13b", "provider": "fireworks-ai", "model": "mythomax-l2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b", "mode": "chat" } ] }, { "id": "fireworks-ai/nemotron-nano-v2-12b-vl", "provider": "fireworks-ai", "model": "nemotron-nano-v2-12b-vl", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-capybara-7b-v1p9", "provider": "fireworks-ai", "model": "nous-capybara-7b-v1p9", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-hermes-2-mixtral-8x7b-dpo", "provider": "fireworks-ai", "model": "nous-hermes-2-mixtral-8x7b-dpo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-hermes-2-yi-34b", "provider": "fireworks-ai", "model": "nous-hermes-2-yi-34b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-hermes-llama2-13b", "provider": "fireworks-ai", "model": "nous-hermes-llama2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-hermes-llama2-70b", "provider": "fireworks-ai", "model": "nous-hermes-llama2-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b", "mode": "chat" } ] }, { "id": "fireworks-ai/nous-hermes-llama2-7b", "provider": "fireworks-ai", "model": "nous-hermes-llama2-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/nvidia-nemotron-nano-12b-v2", "provider": "fireworks-ai", "model": "nvidia-nemotron-nano-12b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2", "mode": "chat" } ] }, { "id": "fireworks-ai/nvidia-nemotron-nano-9b-v2", "provider": "fireworks-ai", "model": "nvidia-nemotron-nano-9b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2", "mode": "chat" } ] }, { "id": "fireworks-ai/openchat-3p5-0106-7b", "provider": "fireworks-ai", "model": "openchat-3p5-0106-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/openhermes-2-mistral-7b", "provider": "fireworks-ai", "model": "openhermes-2-mistral-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/openhermes-2p5-mistral-7b", "provider": "fireworks-ai", "model": "openhermes-2p5-mistral-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/openorca-7b", "provider": "fireworks-ai", "model": "openorca-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/openorca-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openorca-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/openorca-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/phi-2-3b", "provider": "fireworks-ai", "model": "phi-2-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phi-2-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-2-3b", "mode": "chat" } ] }, { "id": "fireworks-ai/phi-3-mini-128k-instruct", "provider": "fireworks-ai", "model": "phi-3-mini-128k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/phi-3-vision-128k-instruct", "provider": "fireworks-ai", "model": "phi-3-vision-128k-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32064, "inputTokens": 32064, "maxTokens": 32064, "outputTokens": 32064, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct", "mode": "chat" } ] }, { "id": "fireworks-ai/phind-code-llama-34b-python-v1", "provider": "fireworks-ai", "model": "phind-code-llama-34b-python-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1", "mode": "chat" } ] }, { "id": "fireworks-ai/phind-code-llama-34b-v1", "provider": "fireworks-ai", "model": "phind-code-llama-34b-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1", "mode": "chat" } ] }, { "id": "fireworks-ai/phind-code-llama-34b-v2", "provider": "fireworks-ai", "model": "phind-code-llama-34b-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2", "mode": "chat" } ] }, { "id": "fireworks-ai/playground-v2-1024px-aesthetic", "provider": "fireworks-ai", "model": "playground-v2-1024px-aesthetic", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00013, "output": 0.00013 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic", "mode": "image_generation" } ] }, { "id": "fireworks-ai/playground-v2-5-1024px-aesthetic", "provider": "fireworks-ai", "model": "playground-v2-5-1024px-aesthetic", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00013, "output": 0.00013 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic", "mode": "image_generation" } ] }, { "id": "fireworks-ai/pythia-12b", "provider": "fireworks-ai", "model": "pythia-12b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/pythia-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/pythia-12b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/pythia-12b", "mode": "chat" } ] }, { "id": "fireworks-ai/rolm-ocr", "provider": "fireworks-ai", "model": "rolm-ocr", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/rolm-ocr" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/rolm-ocr", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/rolm-ocr", "mode": "chat" } ] }, { "id": "fireworks-ai/snorkel-mistral-7b-pairrm-dpo", "provider": "fireworks-ai", "model": "snorkel-mistral-7b-pairrm-dpo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo", "mode": "chat" } ] }, { "id": "fireworks-ai/ssd-1b", "provider": "fireworks-ai", "model": "ssd-1b", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/SSD-1B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/SSD-1B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00013, "output": 0.00013 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/SSD-1B", "mode": "image_generation" } ] }, { "id": "fireworks-ai/stable-diffusion-xl-1024-v1-0", "provider": "fireworks-ai", "model": "stable-diffusion-xl-1024-v1-0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00013, "output": 0.00013 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0", "mode": "image_generation" } ] }, { "id": "fireworks-ai/stablecode-3b", "provider": "fireworks-ai", "model": "stablecode-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/stablecode-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/stablecode-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/stablecode-3b", "mode": "chat" } ] }, { "id": "fireworks-ai/starcoder-16b", "provider": "fireworks-ai", "model": "starcoder-16b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/starcoder-16b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder-16b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder-16b", "mode": "chat" } ] }, { "id": "fireworks-ai/starcoder-7b", "provider": "fireworks-ai", "model": "starcoder-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/starcoder-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/starcoder2-15b", "provider": "fireworks-ai", "model": "starcoder2-15b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/starcoder2-15b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-15b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-15b", "mode": "chat" } ] }, { "id": "fireworks-ai/starcoder2-3b", "provider": "fireworks-ai", "model": "starcoder2-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/starcoder2-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-3b", "mode": "chat" } ] }, { "id": "fireworks-ai/starcoder2-7b", "provider": "fireworks-ai", "model": "starcoder2-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/starcoder2-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/starcoder2-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/toppy-m-7b", "provider": "fireworks-ai", "model": "toppy-m-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/toppy-m-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/toppy-m-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/toppy-m-7b", "mode": "chat" } ] }, { "id": "fireworks-ai/yi-34b", "provider": "fireworks-ai", "model": "yi-34b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/yi-34b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b", "mode": "chat" } ] }, { "id": "fireworks-ai/yi-34b-200k-capybara", "provider": "fireworks-ai", "model": "yi-34b-200k-capybara", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara", "mode": "chat" } ] }, { "id": "fireworks-ai/yi-34b-chat", "provider": "fireworks-ai", "model": "yi-34b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/yi-34b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-34b-chat", "mode": "chat" } ] }, { "id": "fireworks-ai/yi-6b", "provider": "fireworks-ai", "model": "yi-6b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/yi-6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-6b", "mode": "chat" } ] }, { "id": "fireworks-ai/yi-large", "provider": "fireworks-ai", "model": "yi-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/yi-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/yi-large", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "fireworks-ai/zephyr-7b-beta", "provider": "fireworks-ai", "model": "zephyr-7b-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta", "mode": "chat" } ] }, { "id": "frogbot/zai-glm-5-1", "provider": "frogbot", "model": "zai-glm-5-1", "displayName": "Z.AI GLM-5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "frogbot" ], "aliases": [ "frogbot/zai-glm-5-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "zai-glm-5-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "Z.AI GLM-5.1" ], "families": [ "glm" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-01-20", "lastUpdated": "2025-02-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "zai-glm-5-1", "modelKey": "zai-glm-5-1", "displayName": "Z.AI GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-02-22", "openWeights": true, "releaseDate": "2025-01-20" } } ] }, { "id": "gigachat/embeddings", "provider": "gigachat", "model": "embeddings", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/Embeddings" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/Embeddings", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/Embeddings", "mode": "embedding" } ] }, { "id": "gigachat/embeddings-2", "provider": "gigachat", "model": "embeddings-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/Embeddings-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/Embeddings-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/Embeddings-2", "mode": "embedding" } ] }, { "id": "gigachat/embeddingsgigar", "provider": "gigachat", "model": "embeddingsgigar", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/EmbeddingsGigaR" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 2560, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/EmbeddingsGigaR", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/EmbeddingsGigaR", "mode": "embedding" } ] }, { "id": "gigachat/gigachat-2-lite", "provider": "gigachat", "model": "gigachat-2-lite", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/GigaChat-2-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/GigaChat-2-Lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/GigaChat-2-Lite", "mode": "chat" } ] }, { "id": "gigachat/gigachat-2-max", "provider": "gigachat", "model": "gigachat-2-max", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/GigaChat-2-Max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/GigaChat-2-Max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/GigaChat-2-Max", "mode": "chat" } ] }, { "id": "gigachat/gigachat-2-pro", "provider": "gigachat", "model": "gigachat-2-pro", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gigachat" ], "aliases": [ "gigachat/GigaChat-2-Pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gigachat", "model": "gigachat/GigaChat-2-Pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gigachat", "model": "gigachat/GigaChat-2-Pro", "mode": "chat" } ] }, { "id": "github-models/ai21-jamba-1.5-large", "provider": "github-models", "model": "ai21-jamba-1.5-large", "displayName": "AI21 Jamba 1.5 Large", "family": "jamba", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/ai21-labs/ai21-jamba-1.5-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "ai21-labs/ai21-jamba-1.5-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "AI21 Jamba 1.5 Large" ], "families": [ "jamba" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-08-29", "lastUpdated": "2024-08-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "ai21-labs/ai21-jamba-1.5-large", "modelKey": "ai21-labs/ai21-jamba-1.5-large", "displayName": "AI21 Jamba 1.5 Large", "family": "jamba", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-29", "openWeights": false, "releaseDate": "2024-08-29" } } ] }, { "id": "github-models/ai21-jamba-1.5-mini", "provider": "github-models", "model": "ai21-jamba-1.5-mini", "displayName": "AI21 Jamba 1.5 Mini", "family": "jamba", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/ai21-labs/ai21-jamba-1.5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "ai21-labs/ai21-jamba-1.5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "AI21 Jamba 1.5 Mini" ], "families": [ "jamba" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-08-29", "lastUpdated": "2024-08-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "ai21-labs/ai21-jamba-1.5-mini", "modelKey": "ai21-labs/ai21-jamba-1.5-mini", "displayName": "AI21 Jamba 1.5 Mini", "family": "jamba", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-08-29", "openWeights": false, "releaseDate": "2024-08-29" } } ] }, { "id": "github-models/jais-30b-chat", "provider": "github-models", "model": "jais-30b-chat", "displayName": "JAIS 30b Chat", "family": "jais", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/core42/jais-30b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "core42/jais-30b-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "JAIS 30b Chat" ], "families": [ "jais" ], "knowledgeCutoff": "2023-03", "releaseDate": "2023-08-30", "lastUpdated": "2023-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "core42/jais-30b-chat", "modelKey": "core42/jais-30b-chat", "displayName": "JAIS 30b Chat", "family": "jais", "metadata": { "knowledgeCutoff": "2023-03", "lastUpdated": "2023-08-30", "openWeights": true, "releaseDate": "2023-08-30" } } ] }, { "id": "github-models/mai-ds-r1", "provider": "github-models", "model": "mai-ds-r1", "displayName": "MAI-DS-R1", "family": "mai", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/mai-ds-r1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/mai-ds-r1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MAI-DS-R1" ], "families": [ "mai" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-01-20", "lastUpdated": "2025-01-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/mai-ds-r1", "modelKey": "microsoft/mai-ds-r1", "displayName": "MAI-DS-R1", "family": "mai", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-01-20", "openWeights": false, "releaseDate": "2025-01-20" } } ] }, { "id": "github-models/phi-3-medium-128k-instruct", "provider": "github-models", "model": "phi-3-medium-128k-instruct", "displayName": "Phi-3-medium instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-medium-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-medium-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-medium-128k-instruct", "modelKey": "microsoft/phi-3-medium-128k-instruct", "displayName": "Phi-3-medium instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3-medium-4k-instruct", "provider": "github-models", "model": "phi-3-medium-4k-instruct", "displayName": "Phi-3-medium instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-medium-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-medium-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-medium instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-medium-4k-instruct", "modelKey": "microsoft/phi-3-medium-4k-instruct", "displayName": "Phi-3-medium instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3-mini-128k-instruct", "provider": "github-models", "model": "phi-3-mini-128k-instruct", "displayName": "Phi-3-mini instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-mini-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-mini-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-mini-128k-instruct", "modelKey": "microsoft/phi-3-mini-128k-instruct", "displayName": "Phi-3-mini instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3-mini-4k-instruct", "provider": "github-models", "model": "phi-3-mini-4k-instruct", "displayName": "Phi-3-mini instruct (4k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-mini-4k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-mini-4k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-mini instruct (4k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-mini-4k-instruct", "modelKey": "microsoft/phi-3-mini-4k-instruct", "displayName": "Phi-3-mini instruct (4k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3-small-128k-instruct", "provider": "github-models", "model": "phi-3-small-128k-instruct", "displayName": "Phi-3-small instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-small-128k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-small-128k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-small instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-small-128k-instruct", "modelKey": "microsoft/phi-3-small-128k-instruct", "displayName": "Phi-3-small instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3-small-8k-instruct", "provider": "github-models", "model": "phi-3-small-8k-instruct", "displayName": "Phi-3-small instruct (8k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3-small-8k-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3-small-8k-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3-small instruct (8k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-04-23", "lastUpdated": "2024-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3-small-8k-instruct", "modelKey": "microsoft/phi-3-small-8k-instruct", "displayName": "Phi-3-small instruct (8k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-04-23", "openWeights": true, "releaseDate": "2024-04-23" } } ] }, { "id": "github-models/phi-3.5-mini-instruct", "provider": "github-models", "model": "phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3.5-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3.5-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-mini instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3.5-mini-instruct", "modelKey": "microsoft/phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "github-models/phi-3.5-moe-instruct", "provider": "github-models", "model": "phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3.5-moe-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3.5-moe-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-MoE instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3.5-moe-instruct", "modelKey": "microsoft/phi-3.5-moe-instruct", "displayName": "Phi-3.5-MoE instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "github-models/phi-3.5-vision-instruct", "provider": "github-models", "model": "phi-3.5-vision-instruct", "displayName": "Phi-3.5-vision instruct (128k)", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-3.5-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-3.5-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-3.5-vision instruct (128k)" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-08-20", "lastUpdated": "2024-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-3.5-vision-instruct", "modelKey": "microsoft/phi-3.5-vision-instruct", "displayName": "Phi-3.5-vision instruct (128k)", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-08-20", "openWeights": true, "releaseDate": "2024-08-20" } } ] }, { "id": "github-models/phi-4", "provider": "github-models", "model": "phi-4", "displayName": "Phi-4", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-4", "modelKey": "microsoft/phi-4", "displayName": "Phi-4", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "github-models/phi-4-mini-instruct", "provider": "github-models", "model": "phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-4-mini-instruct", "modelKey": "microsoft/phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "github-models/phi-4-mini-reasoning", "provider": "github-models", "model": "phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-4-mini-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-4-mini-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini-reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-4-mini-reasoning", "modelKey": "microsoft/phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "github-models/phi-4-multimodal-instruct", "provider": "github-models", "model": "phi-4-multimodal-instruct", "displayName": "Phi-4-multimodal-instruct", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-4-multimodal-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-4-multimodal-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4-multimodal-instruct" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-4-multimodal-instruct", "modelKey": "microsoft/phi-4-multimodal-instruct", "displayName": "Phi-4-multimodal-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "github-models/phi-4-reasoning", "provider": "github-models", "model": "phi-4-reasoning", "displayName": "Phi-4-Reasoning", "family": "phi", "sources": [ "models.dev" ], "providers": [ "github-models" ], "aliases": [ "github-models/microsoft/phi-4-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "microsoft/phi-4-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4-Reasoning" ], "families": [ "phi" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "microsoft/phi-4-reasoning", "modelKey": "microsoft/phi-4-reasoning", "displayName": "Phi-4-Reasoning", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "gitlab/duo-chat-gpt-5-1", "provider": "gitlab", "model": "duo-chat-gpt-5-1", "displayName": "Agentic Chat (GPT-5.1)", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.1)" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-1", "modelKey": "duo-chat-gpt-5-1", "displayName": "Agentic Chat (GPT-5.1)", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2026-01-22", "openWeights": false, "releaseDate": "2026-01-22" } } ] }, { "id": "gitlab/duo-chat-gpt-5-2", "provider": "gitlab", "model": "duo-chat-gpt-5-2", "displayName": "Agentic Chat (GPT-5.2)", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.2)" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-01-23", "lastUpdated": "2026-01-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-2", "modelKey": "duo-chat-gpt-5-2", "displayName": "Agentic Chat (GPT-5.2)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23" } } ] }, { "id": "gitlab/duo-chat-gpt-5-2-codex", "provider": "gitlab", "model": "duo-chat-gpt-5-2-codex", "displayName": "Agentic Chat (GPT-5.2 Codex)", "family": "gpt-codex", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-2-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.2 Codex)" ], "families": [ "gpt-codex" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-2-codex", "modelKey": "duo-chat-gpt-5-2-codex", "displayName": "Agentic Chat (GPT-5.2 Codex)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-22", "openWeights": false, "releaseDate": "2026-01-22" } } ] }, { "id": "gitlab/duo-chat-gpt-5-3-codex", "provider": "gitlab", "model": "duo-chat-gpt-5-3-codex", "displayName": "Agentic Chat (GPT-5.3 Codex)", "family": "gpt-codex", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-3-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.3 Codex)" ], "families": [ "gpt-codex" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-3-codex", "modelKey": "duo-chat-gpt-5-3-codex", "displayName": "Agentic Chat (GPT-5.3 Codex)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "gitlab/duo-chat-gpt-5-4", "provider": "gitlab", "model": "duo-chat-gpt-5-4", "displayName": "Agentic Chat (GPT-5.4)", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.4)" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-4", "modelKey": "duo-chat-gpt-5-4", "displayName": "Agentic Chat (GPT-5.4)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } } ] }, { "id": "gitlab/duo-chat-gpt-5-4-mini", "provider": "gitlab", "model": "duo-chat-gpt-5-4-mini", "displayName": "Agentic Chat (GPT-5.4 Mini)", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-4-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.4 Mini)" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-4-mini", "modelKey": "duo-chat-gpt-5-4-mini", "displayName": "Agentic Chat (GPT-5.4 Mini)", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "gitlab/duo-chat-gpt-5-4-nano", "provider": "gitlab", "model": "duo-chat-gpt-5-4-nano", "displayName": "Agentic Chat (GPT-5.4 Nano)", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-4-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.4 Nano)" ], "families": [ "gpt-nano" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-4-nano", "modelKey": "duo-chat-gpt-5-4-nano", "displayName": "Agentic Chat (GPT-5.4 Nano)", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "gitlab/duo-chat-gpt-5-5", "provider": "gitlab", "model": "duo-chat-gpt-5-5", "displayName": "Agentic Chat (GPT-5.5)", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5.5)" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-5", "modelKey": "duo-chat-gpt-5-5", "displayName": "Agentic Chat (GPT-5.5)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "gitlab/duo-chat-gpt-5-codex", "provider": "gitlab", "model": "duo-chat-gpt-5-codex", "displayName": "Agentic Chat (GPT-5 Codex)", "family": "gpt-codex", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5 Codex)" ], "families": [ "gpt-codex" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-codex", "modelKey": "duo-chat-gpt-5-codex", "displayName": "Agentic Chat (GPT-5 Codex)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2026-01-22", "openWeights": false, "releaseDate": "2026-01-22" } } ] }, { "id": "gitlab/duo-chat-gpt-5-mini", "provider": "gitlab", "model": "duo-chat-gpt-5-mini", "displayName": "Agentic Chat (GPT-5 Mini)", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (GPT-5 Mini)" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-gpt-5-mini", "modelKey": "duo-chat-gpt-5-mini", "displayName": "Agentic Chat (GPT-5 Mini)", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2026-01-22", "openWeights": false, "releaseDate": "2026-01-22" } } ] }, { "id": "gitlab/duo-chat-haiku-4-5", "provider": "gitlab", "model": "duo-chat-haiku-4-5", "displayName": "Agentic Chat (Claude Haiku 4.5)", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-haiku-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-haiku-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Haiku 4.5)" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2026-01-08", "lastUpdated": "2026-01-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-haiku-4-5", "modelKey": "duo-chat-haiku-4-5", "displayName": "Agentic Chat (Claude Haiku 4.5)", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2026-01-08", "openWeights": false, "releaseDate": "2026-01-08" } } ] }, { "id": "gitlab/duo-chat-opus-4-5", "provider": "gitlab", "model": "duo-chat-opus-4-5", "displayName": "Agentic Chat (Claude Opus 4.5)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-opus-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-opus-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Opus 4.5)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2026-01-08", "lastUpdated": "2026-01-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-opus-4-5", "modelKey": "duo-chat-opus-4-5", "displayName": "Agentic Chat (Claude Opus 4.5)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2026-01-08", "openWeights": false, "releaseDate": "2026-01-08" } } ] }, { "id": "gitlab/duo-chat-opus-4-6", "provider": "gitlab", "model": "duo-chat-opus-4-6", "displayName": "Agentic Chat (Claude Opus 4.6)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-opus-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-opus-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Opus 4.6)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-opus-4-6", "modelKey": "duo-chat-opus-4-6", "displayName": "Agentic Chat (Claude Opus 4.6)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "gitlab/duo-chat-opus-4-7", "provider": "gitlab", "model": "duo-chat-opus-4-7", "displayName": "Agentic Chat (Claude Opus 4.7)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-opus-4-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Opus 4.7)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-opus-4-7", "modelKey": "duo-chat-opus-4-7", "displayName": "Agentic Chat (Claude Opus 4.7)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "gitlab/duo-chat-opus-4-8", "provider": "gitlab", "model": "duo-chat-opus-4-8", "displayName": "Agentic Chat (Claude Opus 4.8)", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-opus-4-8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-opus-4-8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Opus 4.8)" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-opus-4-8", "modelKey": "duo-chat-opus-4-8", "displayName": "Agentic Chat (Claude Opus 4.8)", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } } ] }, { "id": "gitlab/duo-chat-sonnet-4-5", "provider": "gitlab", "model": "duo-chat-sonnet-4-5", "displayName": "Agentic Chat (Claude Sonnet 4.5)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-sonnet-4-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-sonnet-4-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Sonnet 4.5)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2026-01-08", "lastUpdated": "2026-01-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-sonnet-4-5", "modelKey": "duo-chat-sonnet-4-5", "displayName": "Agentic Chat (Claude Sonnet 4.5)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2026-01-08", "openWeights": false, "releaseDate": "2026-01-08" } } ] }, { "id": "gitlab/duo-chat-sonnet-4-6", "provider": "gitlab", "model": "duo-chat-sonnet-4-6", "displayName": "Agentic Chat (Claude Sonnet 4.6)", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "gitlab" ], "aliases": [ "gitlab/duo-chat-sonnet-4-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gitlab", "model": "duo-chat-sonnet-4-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Agentic Chat (Claude Sonnet 4.6)" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gitlab", "providerName": "GitLab Duo", "providerDoc": "https://docs.gitlab.com/user/duo_agent_platform/", "model": "duo-chat-sonnet-4-6", "modelKey": "duo-chat-sonnet-4-6", "displayName": "Agentic Chat (Claude Sonnet 4.6)", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "google-pse/search", "provider": "google-pse", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "google_pse" ], "aliases": [ "google_pse/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "google_pse", "model": "google_pse/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.005 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "google_pse", "model": "google_pse/search", "mode": "search" } ] }, { "id": "google/deep-research-pro-preview-12-2025", "provider": "google", "model": "deep-research-pro-preview-12-2025", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/deep-research-pro-preview-12-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/deep-research-pro-preview-12-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/deep-research-pro-preview-12-2025", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "google/flan-t5-xl-3b", "provider": "google", "model": "flan-t5-xl-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/google/flan-t5-xl-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/google/flan-t5-xl-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/google/flan-t5-xl-3b", "mode": "chat" } ] }, { "id": "google/gemini-1.5-flash", "provider": "google", "model": "gemini-1.5-flash", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-1.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "multimodal": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-1.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0 }, "extra": { "input_cost_per_token_above_128k_tokens": 1.5e-7 } } ] }, "metadata": { "modes": [ "embedding" ], "deprecationDate": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-1.5-flash", "mode": "embedding", "metadata": { "deprecationDate": "2025-09-29", "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal" } } ] }, { "id": "google/gemini-2-5-flash", "provider": "google", "model": "gemini-2-5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gemini-2-5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gemini-2-5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash" ], "families": [ "gemini-flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-2-5-flash", "modelKey": "gemini-2-5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } } ] }, { "id": "google/gemini-2-5-pro", "provider": "google", "model": "gemini-2-5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gemini-2-5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gemini-2-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-2-5-pro", "modelKey": "gemini-2-5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } } ] }, { "id": "google/gemini-2.0-flash", "provider": "google", "model": "gemini-2.0-flash", "displayName": "Gemini 2.0 Flash", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "google", "llmgateway", "poe", "qiniu-ai", "vercel_ai_gateway", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-2.0-flash", "google/gemini-2.0-flash", "llmgateway/gemini-2.0-flash", "poe/google/gemini-2.0-flash", "qiniu-ai/gemini-2.0-flash", "vercel_ai_gateway/google/gemini-2.0-flash", "vertex_ai-language-models/gemini-2.0-flash" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 8192, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google", "model": "gemini-2.0-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-2.0-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-2.0-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.42 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.0-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.7, "output": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.0-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.7, "output": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Flash", "Gemini-2.0-Flash" ], "families": [ "gemini-flash" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-06", "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "deprecationDate": "2026-06-01", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.0-flash", "modelKey": "gemini-2.0-flash", "displayName": "Gemini 2.0 Flash", "family": "gemini-flash", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-2.0-flash", "modelKey": "gemini-2.0-flash", "displayName": "Gemini 2.0 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-2.0-flash", "modelKey": "google/gemini-2.0-flash", "displayName": "Gemini-2.0-Flash", "family": "gemini-flash", "metadata": { "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.0-flash", "modelKey": "gemini-2.0-flash", "displayName": "Gemini 2.0 Flash", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.0-flash", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://ai.google.dev/pricing#2_0flash" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.0-flash", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://ai.google.dev/pricing#2_0flash" } } ] }, { "id": "google/gemini-2.0-flash-001", "provider": "google", "model": "gemini-2.0-flash-001", "displayName": "Google: Gemini 2.0 Flash", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "deepinfra", "gemini", "kilo", "nano-gpt", "openrouter", "vertex_ai-language-models" ], "aliases": [ "deepinfra/google/gemini-2.0-flash-001", "gemini/gemini-2.0-flash-001", "kilo/google/gemini-2.0-flash-001", "nano-gpt/gemini-2.0-flash-001", "openrouter/google/gemini-2.0-flash-001", "vertex_ai-language-models/gemini-2.0-flash-001" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 1000000, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "promptCaching": true, "responseSchema": true, "systemMessages": true, "vision": true, "webSearch": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.0-flash-001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.083333, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-flash-001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.408 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.0-flash-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.0-flash-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.7, "output": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-2.0-flash-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "inputAudio": 0.7, "output": 0.4 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0375, "input": 0.15, "inputAudio": 1, "output": 0.6 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Flash", "Google: Gemini 2.0 Flash" ], "modes": [ "chat" ], "releaseDate": "2024-12-11", "lastUpdated": "2026-03-15", "deprecationDate": "2026-06-01", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.0-flash-001", "modelKey": "google/gemini-2.0-flash-001", "displayName": "Google: Gemini 2.0 Flash", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-flash-001", "modelKey": "gemini-2.0-flash-001", "displayName": "Gemini 2.0 Flash", "metadata": { "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.0-flash-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.0-flash-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://ai.google.dev/pricing#2_0flash" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-2.0-flash-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/gemini-2.0-flash-exp-image-generation", "provider": "google", "model": "gemini-2.0-flash-exp-image-generation", "displayName": "Gemini Text + Image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "nano-gpt" ], "aliases": [ "gemini/gemini-2.0-flash-exp-image-generation", "nano-gpt/gemini-2.0-flash-exp-image-generation" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxImagesPerPrompt": 3000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-flash-exp-image-generation", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-2.0-flash-exp-image-generation", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perImage": { "output": 0.039 }, "extra": { "max_images_per_prompt": 3000 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.0-flash-exp-image-generation", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perImage": { "output": 0.039 }, "extra": { "max_images_per_prompt": 3000 } } ] }, "metadata": { "displayNames": [ "Gemini Text + Image" ], "modes": [ "image_generation" ], "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-flash-exp-image-generation", "modelKey": "gemini-2.0-flash-exp-image-generation", "displayName": "Gemini Text + Image", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-2.0-flash-exp-image-generation", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.0-flash-exp-image-generation", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/pricing" } } ] }, { "id": "google/gemini-2.0-flash-lite", "provider": "google", "model": "gemini-2.0-flash-lite", "displayName": "Gemini 2.0 Flash-Lite", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "gemini", "google", "llmgateway", "poe", "qiniu-ai", "vercel_ai_gateway", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-2.0-flash-lite", "gemini/gemini-2.0-flash-lite", "google/gemini-2.0-flash-lite", "llmgateway/gemini-2.0-flash-lite", "poe/google/gemini-2.0-flash-lite", "qiniu-ai/gemini-2.0-flash-lite", "vercel_ai_gateway/google/gemini-2.0-flash-lite", "vertex_ai-language-models/gemini-2.0-flash-lite" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 2000000, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 50, "maxTokens": 8192, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.0-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "google", "model": "gemini-2.0-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-2.0-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-2.0-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.052, "output": 0.21 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.0-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01875, "input": 0.075, "inputAudio": 0.075, "output": 0.3 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.0-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01875, "input": 0.075, "inputAudio": 0.075, "output": 0.3 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Flash Lite", "Gemini 2.0 Flash-Lite", "Gemini-2.0-Flash-Lite", "gemini-2.0-flash-lite" ], "families": [ "gemini-flash-lite" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-11", "releaseDate": "2025-06-16", "lastUpdated": "2025-06-16", "deprecationDate": "2026-06-01", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.0-flash-lite", "modelKey": "gemini-2.0-flash-lite", "displayName": "gemini-2.0-flash-lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-06-16", "openWeights": false, "releaseDate": "2025-06-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.0-flash-lite", "modelKey": "gemini-2.0-flash-lite", "displayName": "Gemini 2.0 Flash-Lite", "family": "gemini-flash-lite", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-2.0-flash-lite", "modelKey": "gemini-2.0-flash-lite", "displayName": "Gemini 2.0 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-12-11", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-2.0-flash-lite", "modelKey": "google/gemini-2.0-flash-lite", "displayName": "Gemini-2.0-Flash-Lite", "family": "gemini-flash-lite", "metadata": { "lastUpdated": "2025-02-05", "openWeights": false, "releaseDate": "2025-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.0-flash-lite", "modelKey": "gemini-2.0-flash-lite", "displayName": "Gemini 2.0 Flash Lite", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.0-flash-lite", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.0-flash-lite", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-lite", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash" } } ] }, { "id": "google/gemini-2.0-flash-lite-001", "provider": "google", "model": "gemini-2.0-flash-lite-001", "displayName": "Google: Gemini 2.0 Flash Lite", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "kilo", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-2.0-flash-lite-001", "kilo/google/gemini-2.0-flash-lite-001", "vertex_ai-language-models/gemini-2.0-flash-lite-001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 50, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.0-flash-lite-001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.0-flash-lite-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01875, "input": 0.075, "inputAudio": 0.075, "output": 0.3 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-lite-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01875, "input": 0.075, "inputAudio": 0.075, "output": 0.3 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Google: Gemini 2.0 Flash Lite" ], "modes": [ "chat" ], "releaseDate": "2024-12-11", "lastUpdated": "2026-03-15", "deprecationDate": "2026-06-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.0-flash-lite-001", "modelKey": "google/gemini-2.0-flash-lite-001", "displayName": "Google: Gemini 2.0 Flash Lite", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.0-flash-lite-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.0-flash-lite-001", "mode": "chat", "metadata": { "deprecationDate": "2026-06-01", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash" } } ] }, { "id": "google/gemini-2.0-flash-thinking-exp-01-21", "provider": "google", "model": "gemini-2.0-flash-thinking-exp-01-21", "displayName": "Gemini 2.0 Flash Thinking 0121", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.0-flash-thinking-exp-01-21" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-flash-thinking-exp-01-21", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 1.003 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Flash Thinking 0121" ], "releaseDate": "2025-01-21", "lastUpdated": "2025-01-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-flash-thinking-exp-01-21", "modelKey": "gemini-2.0-flash-thinking-exp-01-21", "displayName": "Gemini 2.0 Flash Thinking 0121", "metadata": { "lastUpdated": "2025-01-21", "openWeights": false, "releaseDate": "2025-01-21" } } ] }, { "id": "google/gemini-2.0-flash-thinking-exp-1219", "provider": "google", "model": "gemini-2.0-flash-thinking-exp-1219", "displayName": "Gemini 2.0 Flash Thinking 1219", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.0-flash-thinking-exp-1219" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32767, "inputTokens": 32767, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-flash-thinking-exp-1219", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Flash Thinking 1219" ], "releaseDate": "2024-12-19", "lastUpdated": "2024-12-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-flash-thinking-exp-1219", "modelKey": "gemini-2.0-flash-thinking-exp-1219", "displayName": "Gemini 2.0 Flash Thinking 1219", "metadata": { "lastUpdated": "2024-12-19", "openWeights": false, "releaseDate": "2024-12-19" } } ] }, { "id": "google/gemini-2.0-pro-exp-02-05", "provider": "google", "model": "gemini-2.0-pro-exp-02-05", "displayName": "Gemini 2.0 Pro 0205", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.0-pro-exp-02-05" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2097152, "inputTokens": 2097152, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-pro-exp-02-05", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.989, "output": 7.956 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Pro 0205" ], "releaseDate": "2025-02-05", "lastUpdated": "2025-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-pro-exp-02-05", "modelKey": "gemini-2.0-pro-exp-02-05", "displayName": "Gemini 2.0 Pro 0205", "metadata": { "lastUpdated": "2025-02-05", "openWeights": false, "releaseDate": "2025-02-05" } } ] }, { "id": "google/gemini-2.0-pro-reasoner", "provider": "google", "model": "gemini-2.0-pro-reasoner", "displayName": "Gemini 2.0 Pro Reasoner", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.0-pro-reasoner" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.0-pro-reasoner", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.292, "output": 4.998 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Pro Reasoner" ], "releaseDate": "2025-02-05", "lastUpdated": "2025-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.0-pro-reasoner", "modelKey": "gemini-2.0-pro-reasoner", "displayName": "Gemini 2.0 Pro Reasoner", "metadata": { "lastUpdated": "2025-02-05", "openWeights": false, "releaseDate": "2025-02-05" } } ] }, { "id": "google/gemini-2.5-computer-use-preview-10-2025", "provider": "google", "model": "gemini-2.5-computer-use-preview-10-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-2.5-computer-use-preview-10-2025", "vertex_ai-language-models/gemini-2.5-computer-use-preview-10-2025" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxImagesPerPrompt": 3000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "computerUse": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-computer-use-preview-10-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.0000025, "max_images_per_prompt": 3000, "output_cost_per_token_above_200k_tokens": 0.000015 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-computer-use-preview-10-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 }, "extra": { "input_cost_per_token_above_200k_tokens": 0.0000025, "max_images_per_prompt": 3000, "output_cost_per_token_above_200k_tokens": 0.000015 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-computer-use-preview-10-2025", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/computer-use", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-computer-use-preview-10-2025", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use" } } ] }, { "id": "google/gemini-2.5-flash", "provider": "google", "model": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "auriko", "deepinfra", "fastrouter", "frogbot", "gemini", "google", "google-vertex", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openrouter", "orcarouter", "perplexity-agent", "poe", "qihang-ai", "qiniu-ai", "replicate", "requesty", "sap-ai-core", "vercel", "vercel_ai_gateway", "vertex_ai-language-models", "zenmux" ], "aliases": [ "302ai/gemini-2.5-flash", "abacus/gemini-2.5-flash", "aihubmix/gemini-2.5-flash", "anyapi/google/gemini-2.5-flash", "auriko/gemini-2.5-flash", "deepinfra/google/gemini-2.5-flash", "fastrouter/google/gemini-2.5-flash", "frogbot/gemini-2.5-flash", "gemini/gemini-2.5-flash", "google-vertex/gemini-2.5-flash", "google/gemini-2.5-flash", "helicone/gemini-2.5-flash", "jiekou/gemini-2.5-flash", "kilo/google/gemini-2.5-flash", "llmgateway/gemini-2.5-flash", "merge-gateway/google/gemini-2.5-flash", "nano-gpt/gemini-2.5-flash", "nearai/google/gemini-2.5-flash", "openrouter/google/gemini-2.5-flash", "orcarouter/google/gemini-2.5-flash", "perplexity-agent/google/gemini-2.5-flash", "poe/google/gemini-2.5-flash", "qihang-ai/gemini-2.5-flash", "qiniu-ai/gemini-2.5-flash", "replicate/google/gemini-2.5-flash", "requesty/google/gemini-2.5-flash", "sap-ai-core/gemini-2.5-flash", "vercel/google/gemini-2.5-flash", "vercel_ai_gateway/google/gemini-2.5-flash", "vertex_ai-language-models/gemini-2.5-flash", "zenmux/google/gemini-2.5-flash" ], "mergedProviderModelRecords": 31, "limits": { "contextTokens": 1065535, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 1000000, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "webSearch": true, "promptCaching": true, "serviceTier": true, "urlContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "abacus", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "auriko", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0375, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "frogbot", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.383, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "google", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "helicone", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.3, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 2.25 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.083333, "input": 0.3, "output": 2.5, "reasoningOutput": 2.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.083333, "input": 0.3, "output": 2.5, "reasoningOutput": 2.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.021, "input": 0.21, "output": 1.8 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.71 }, "tiered": { "contextOver200K": { "input": 0.09, "output": 0.71 }, "tiers": [ { "input": 0.09, "output": 0.71, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "requesty", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.55, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-2.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "cacheWrite": 1, "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 0.7, "output": 2.5 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/google/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 2.5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.0833333333333, "input": 0.3, "internalReasoning": 2.5, "output": 2.5 }, "other": { "audio": 0.000001, "image": 3e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash", "Gemini-2.5-Flash", "Google Gemini 2.5 Flash", "Google: Gemini 2.5 Flash", "gemini-2.5-flash" ], "families": [ "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 31 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-07-17", "openWeights": false, "releaseDate": "2025-07-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Google Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "family": "gemini-flash", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Google: Gemini 2.5 Flash", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-07-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini-2.5-Flash", "family": "gemini-flash", "metadata": { "lastUpdated": "2025-04-26", "openWeights": false, "releaseDate": "2025-04-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gemini-2.5-flash", "modelKey": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-2.5-flash", "modelKey": "google/gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.5-flash", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-2.5-flash", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/google/gemini-2.5-flash", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.5-flash", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-flash", "displayName": "Google: Gemini 2.5 Flash", "metadata": { "canonicalSlug": "google/gemini-2.5-flash", "createdAt": "2025-06-17T15:01:28.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65535, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-flash-image", "provider": "google", "model": "gemini-2.5-flash-image", "displayName": "Nano Banana", "family": "gemini-flash", "mode": "image_generation", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "gemini", "google", "kilo", "openrouter", "qiniu-ai", "vercel", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-2.5-flash-image", "gemini/gemini-2.5-flash-image", "google/gemini-2.5-flash-image", "kilo/google/gemini-2.5-flash-image", "openrouter/google/gemini-2.5-flash-image", "qiniu-ai/gemini-2.5-flash-image", "vercel/google/gemini-2.5-flash-image", "vertex_ai-language-models/gemini-2.5-flash-image", "vertex_ai-language-models/vertex_ai/gemini-2.5-flash-image" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 32768, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": true, "moderation": false, "promptCaching": true, "rerank": false, "serviceTier": true, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 30 } }, { "source": "models.dev", "provider": "google", "model": "gemini-2.5-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 30 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.083333, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-2.5-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "outputImage": 30, "reasoningOutput": 2.5 }, "perImage": { "output": 0.039 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "outputImage": 30, "reasoningOutput": 2.5 }, "perImage": { "output": 0.039 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-2.5-flash-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "outputImage": 30, "reasoningOutput": 2.5 }, "perImage": { "output": 0.039 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-flash-image", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.0833333333333, "input": 0.3, "internalReasoning": 2.5, "output": 2.5 }, "other": { "audio": 0.000001, "image": 3e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Image", "Google: Nano Banana (Gemini 2.5 Flash Image)", "Nano Banana", "Nano Banana (Gemini 2.5 Flash Image)", "gemini-2.5-flash-image" ], "families": [ "gemini-flash" ], "modes": [ "image_generation" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-10-08", "lastUpdated": "2025-10-08", "supportedParameters": [ "max_tokens", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-flash-image", "modelKey": "gemini-2.5-flash-image", "displayName": "gemini-2.5-flash-image", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-10-08", "openWeights": false, "releaseDate": "2025-10-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-flash-image", "modelKey": "gemini-2.5-flash-image", "displayName": "Nano Banana", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-flash-image", "modelKey": "google/gemini-2.5-flash-image", "displayName": "Google: Nano Banana (Gemini 2.5 Flash Image)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-10-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-flash-image", "modelKey": "google/gemini-2.5-flash-image", "displayName": "Nano Banana", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.5-flash-image", "modelKey": "gemini-2.5-flash-image", "displayName": "Gemini 2.5 Flash Image", "metadata": { "lastUpdated": "2025-10-22", "openWeights": false, "releaseDate": "2025-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-2.5-flash-image", "modelKey": "google/gemini-2.5-flash-image", "displayName": "Nano Banana (Gemini 2.5 Flash Image)", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-image", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-image", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-2.5-flash-image", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-flash-image", "displayName": "Google: Nano Banana (Gemini 2.5 Flash Image)", "metadata": { "canonicalSlug": "google/gemini-2.5-flash-image", "createdAt": "2025-10-07T20:53:51.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-flash-image/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 32768, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-flash-lite", "provider": "google", "model": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "gemini", "google", "google-vertex", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openrouter", "orcarouter", "poe", "qiniu-ai", "sap-ai-core", "vercel", "vertex_ai-language-models", "zenmux" ], "aliases": [ "anyapi/google/gemini-2.5-flash-lite", "gemini/gemini-2.5-flash-lite", "google-vertex/gemini-2.5-flash-lite", "google/gemini-2.5-flash-lite", "helicone/gemini-2.5-flash-lite", "jiekou/gemini-2.5-flash-lite", "kilo/google/gemini-2.5-flash-lite", "llmgateway/gemini-2.5-flash-lite", "merge-gateway/google/gemini-2.5-flash-lite", "nano-gpt/gemini-2.5-flash-lite", "nearai/google/gemini-2.5-flash-lite", "openrouter/google/gemini-2.5-flash-lite", "orcarouter/google/gemini-2.5-flash-lite", "poe/google/gemini-2.5-flash-lite", "qiniu-ai/gemini-2.5-flash-lite", "sap-ai-core/gemini-2.5-flash-lite", "vercel/google/gemini-2.5-flash-lite", "vertex_ai-language-models/gemini-2.5-flash-lite", "zenmux/google/gemini-2.5-flash-lite" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "serviceTier": true, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "google", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "helicone", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.024999999999999998, "cacheWrite": 0.09999999999999999, "input": 0.09999999999999999, "output": 0.39999999999999997 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.083333, "input": 0.1, "output": 0.4, "reasoningOutput": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.083333, "input": 0.1, "output": 0.4, "reasoningOutput": 0.4 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 1, "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.0833333333333, "input": 0.1, "internalReasoning": 0.4, "output": 0.4 }, "other": { "audio": 3e-7, "image": 1e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Lite", "Gemini 2.5 Flash-Lite", "Gemini-2.5-Flash-Lite", "Google Gemini 2.5 Flash Lite", "Google: Gemini 2.5 Flash Lite", "gemini-2.5-flash-lite" ], "families": [ "gemini-flash-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Google Gemini 2.5 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-22", "openWeights": false, "releaseDate": "2025-07-22", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "gemini-2.5-flash-lite", "family": "gemini-flash-lite", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Google: Gemini 2.5 Flash Lite", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash Lite", "metadata": { "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash-Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini-2.5-Flash-Lite", "family": "gemini-flash-lite", "metadata": { "lastUpdated": "2025-06-19", "openWeights": false, "releaseDate": "2025-06-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash Lite", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gemini-2.5-flash-lite", "modelKey": "gemini-2.5-flash-lite", "displayName": "gemini-2.5-flash-lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-2.5-flash-lite", "modelKey": "google/gemini-2.5-flash-lite", "displayName": "Gemini 2.5 Flash Lite", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-22", "openWeights": false, "releaseDate": "2025-07-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite", "displayName": "Google: Gemini 2.5 Flash Lite", "metadata": { "canonicalSlug": "google/gemini-2.5-flash-lite", "createdAt": "2025-07-22T16:04:36.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65535, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-flash-lite-preview-06-17", "provider": "google", "model": "gemini-2.5-flash-lite-preview-06-17", "displayName": "gemini-2.5-flash-lite-preview-06-17", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "jiekou", "nano-gpt", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-2.5-flash-lite-preview-06-17", "jiekou/gemini-2.5-flash-lite-preview-06-17", "nano-gpt/gemini-2.5-flash-lite-preview-06-17", "vertex_ai-language-models/gemini-2.5-flash-lite-preview-06-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-flash-lite-preview-06-17", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-lite-preview-06-17", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite-preview-06-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.5, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite-preview-06-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.5, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Lite Preview", "gemini-2.5-flash-lite-preview-06-17" ], "families": [ "gemini-flash-lite" ], "modes": [ "chat" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "deprecationDate": "2025-11-18", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-flash-lite-preview-06-17", "modelKey": "gemini-2.5-flash-lite-preview-06-17", "displayName": "gemini-2.5-flash-lite-preview-06-17", "family": "gemini-flash-lite", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-lite-preview-06-17", "modelKey": "gemini-2.5-flash-lite-preview-06-17", "displayName": "Gemini 2.5 Flash Lite Preview", "metadata": { "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite-preview-06-17", "mode": "chat", "metadata": { "deprecationDate": "2025-11-18", "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite-preview-06-17", "mode": "chat", "metadata": { "deprecationDate": "2025-11-18", "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "google/gemini-2.5-flash-lite-preview-09-2025", "provider": "google", "model": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "gemini-2.5-flash-lite-preview-09-2025", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "gemini", "jiekou", "kilo", "nano-gpt", "openrouter", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-2.5-flash-lite-preview-09-2025", "gemini/gemini-2.5-flash-lite-preview-09-2025", "jiekou/gemini-2.5-flash-lite-preview-09-2025", "kilo/google/gemini-2.5-flash-lite-preview-09-2025", "nano-gpt/gemini-2.5-flash-lite-preview-09-2025", "openrouter/google/gemini-2.5-flash-lite-preview-09-2025", "vertex_ai-language-models/gemini-2.5-flash-lite-preview-09-2025" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.083333, "input": 0.1, "output": 0.4, "reasoningOutput": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.083333, "input": 0.1, "output": 0.4, "reasoningOutput": 0.4 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.0833333333333, "input": 0.1, "internalReasoning": 0.4, "output": 0.4 }, "other": { "audio": 3e-7, "image": 1e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Lite Preview (09/2025)", "Gemini 2.5 Flash Lite Preview 09-2025", "Google: Gemini 2.5 Flash Lite Preview 09-2025", "gemini-2.5-flash-lite-preview-09-2025" ], "families": [ "gemini-flash-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-26", "lastUpdated": "2025-09-26", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-flash-lite-preview-09-2025", "modelKey": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "gemini-2.5-flash-lite-preview-09-2025", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-26", "openWeights": false, "releaseDate": "2025-09-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-flash-lite-preview-09-2025", "modelKey": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "gemini-2.5-flash-lite-preview-09-2025", "family": "gemini-flash-lite", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "modelKey": "google/gemini-2.5-flash-lite-preview-09-2025", "displayName": "Google: Gemini 2.5 Flash Lite Preview 09-2025", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-lite-preview-09-2025", "modelKey": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "Gemini 2.5 Flash Lite Preview (09/2025)", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "modelKey": "google/gemini-2.5-flash-lite-preview-09-2025", "displayName": "Gemini 2.5 Flash Lite Preview 09-2025", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-lite-preview-09-2025", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-lite-preview-09-2025", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-flash-lite-preview-09-2025", "displayName": "Google: Gemini 2.5 Flash Lite Preview 09-2025", "metadata": { "canonicalSlug": "google/gemini-2.5-flash-lite-preview-09-2025", "createdAt": "2025-09-25T17:01:26.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-flash-lite-preview-09-2025/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65535, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-flash-lite-preview-09-2025-thinking", "provider": "google", "model": "gemini-2.5-flash-lite-preview-09-2025-thinking", "displayName": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-lite-preview-09-2025-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-lite-preview-09-2025-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-lite-preview-09-2025-thinking", "modelKey": "gemini-2.5-flash-lite-preview-09-2025-thinking", "displayName": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "google/gemini-2.5-flash-native-audio-latest", "provider": "google", "model": "gemini-2.5-flash-native-audio-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-2.5-flash-native-audio-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-latest", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-latest", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "google/gemini-2.5-flash-native-audio-preview-09-2025", "provider": "google", "model": "gemini-2.5-flash-native-audio-preview-09-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-2.5-flash-native-audio-preview-09-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-preview-09-2025", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-preview-09-2025", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "google/gemini-2.5-flash-native-audio-preview-12-2025", "provider": "google", "model": "gemini-2.5-flash-native-audio-preview-12-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-2.5-flash-native-audio-preview-12-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-preview-12-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-preview-12-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "inputAudio": 1, "output": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-2.5-flash-native-audio-preview-12-2025", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-native-audio-preview-12-2025", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "google/gemini-2.5-flash-nothink", "provider": "google", "model": "gemini-2.5-flash-nothink", "displayName": "gemini-2.5-flash-nothink", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/gemini-2.5-flash-nothink" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-flash-nothink", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "gemini-2.5-flash-nothink" ], "families": [ "gemini-flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-24", "lastUpdated": "2025-06-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-flash-nothink", "modelKey": "gemini-2.5-flash-nothink", "displayName": "gemini-2.5-flash-nothink", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-24", "openWeights": false, "releaseDate": "2025-06-24" } } ] }, { "id": "google/gemini-2.5-flash-nothinking", "provider": "google", "model": "gemini-2.5-flash-nothinking", "displayName": "Gemini 2.5 Flash (No Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-nothinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-nothinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash (No Thinking)" ], "releaseDate": "2025-06-05", "lastUpdated": "2025-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-nothinking", "modelKey": "gemini-2.5-flash-nothinking", "displayName": "Gemini 2.5 Flash (No Thinking)", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } } ] }, { "id": "google/gemini-2.5-flash-preview-04-17", "provider": "google", "model": "gemini-2.5-flash-preview-04-17", "displayName": "Gemini 2.5 Flash Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-preview-04-17" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-04-17", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Preview" ], "releaseDate": "2025-04-17", "lastUpdated": "2025-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-04-17", "modelKey": "gemini-2.5-flash-preview-04-17", "displayName": "Gemini 2.5 Flash Preview", "metadata": { "lastUpdated": "2025-04-17", "openWeights": false, "releaseDate": "2025-04-17" } } ] }, { "id": "google/gemini-2.5-flash-preview-04-17:thinking", "provider": "google", "model": "gemini-2.5-flash-preview-04-17:thinking", "displayName": "Gemini 2.5 Flash Preview Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-preview-04-17:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-04-17:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Preview Thinking" ], "releaseDate": "2025-04-17", "lastUpdated": "2025-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-04-17:thinking", "modelKey": "gemini-2.5-flash-preview-04-17:thinking", "displayName": "Gemini 2.5 Flash Preview Thinking", "metadata": { "lastUpdated": "2025-04-17", "openWeights": false, "releaseDate": "2025-04-17" } } ] }, { "id": "google/gemini-2.5-flash-preview-05-20", "provider": "google", "model": "gemini-2.5-flash-preview-05-20", "displayName": "gemini-2.5-flash-preview-05-20", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "jiekou", "nano-gpt" ], "aliases": [ "jiekou/gemini-2.5-flash-preview-05-20", "nano-gpt/gemini-2.5-flash-preview-05-20" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048576, "inputTokens": 1048000, "outputTokens": 200000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-flash-preview-05-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.135, "output": 3.15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-05-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash 0520", "gemini-2.5-flash-preview-05-20" ], "families": [ "gemini-flash" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-flash-preview-05-20", "modelKey": "gemini-2.5-flash-preview-05-20", "displayName": "gemini-2.5-flash-preview-05-20", "family": "gemini-flash", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-05-20", "modelKey": "gemini-2.5-flash-preview-05-20", "displayName": "Gemini 2.5 Flash 0520", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "google/gemini-2.5-flash-preview-05-20:thinking", "provider": "google", "model": "gemini-2.5-flash-preview-05-20:thinking", "displayName": "Gemini 2.5 Flash 0520 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-preview-05-20:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048000, "inputTokens": 1048000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-05-20:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash 0520 Thinking" ], "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-05-20:thinking", "modelKey": "gemini-2.5-flash-preview-05-20:thinking", "displayName": "Gemini 2.5 Flash 0520 Thinking", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "google/gemini-2.5-flash-preview-09-2025", "provider": "google", "model": "gemini-2.5-flash-preview-09-2025", "displayName": "gemini-2.5-flash-preview-09-2025", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "gemini", "nano-gpt", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-2.5-flash-preview-09-2025", "gemini/gemini-2.5-flash-preview-09-2025", "nano-gpt/gemini-2.5-flash-preview-09-2025", "vertex_ai-language-models/gemini-2.5-flash-preview-09-2025" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-flash-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-09-2025", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-preview-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Preview (09/2025)", "gemini-2.5-flash-preview-09-2025" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-26", "lastUpdated": "2025-09-26", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-flash-preview-09-2025", "modelKey": "gemini-2.5-flash-preview-09-2025", "displayName": "gemini-2.5-flash-preview-09-2025", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-26", "openWeights": false, "releaseDate": "2025-09-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-09-2025", "modelKey": "gemini-2.5-flash-preview-09-2025", "displayName": "Gemini 2.5 Flash Preview (09/2025)", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-preview-09-2025", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-flash-preview-09-2025", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "google/gemini-2.5-flash-preview-09-2025-thinking", "provider": "google", "model": "gemini-2.5-flash-preview-09-2025-thinking", "displayName": "Gemini 2.5 Flash Preview (09/2025) – Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-flash-preview-09-2025-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-flash-preview-09-2025-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Preview (09/2025) – Thinking" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-flash-preview-09-2025-thinking", "modelKey": "gemini-2.5-flash-preview-09-2025-thinking", "displayName": "Gemini 2.5 Flash Preview (09/2025) – Thinking", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "google/gemini-2.5-flash-preview-tts", "provider": "google", "model": "gemini-2.5-flash-preview-tts", "displayName": "Gemini 2.5 Flash Preview TTS", "family": "gemini-flash", "mode": "audio_speech", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "google" ], "aliases": [ "gemini/gemini-2.5-flash-preview-tts", "google/gemini-2.5-flash-preview-tts" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google", "model": "gemini-2.5-flash-preview-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 10 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-2.5-flash-preview-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-flash-preview-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash Preview TTS" ], "families": [ "gemini-flash" ], "modes": [ "audio_speech" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-05-01", "lastUpdated": "2025-05-01", "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-flash-preview-tts", "modelKey": "gemini-2.5-flash-preview-tts", "displayName": "Gemini 2.5 Flash Preview TTS", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-05-01", "openWeights": false, "releaseDate": "2025-05-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-2.5-flash-preview-tts", "mode": "audio_speech", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/audio/speech" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-flash-preview-tts", "mode": "audio_speech", "metadata": { "source": "https://ai.google.dev/pricing", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "google/gemini-2.5-flash-tts", "provider": "google", "model": "gemini-2.5-flash-tts", "displayName": "Gemini 2.5 Flash TTS", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "google-vertex" ], "aliases": [ "google-vertex/gemini-2.5-flash-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-2.5-flash-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Flash TTS" ], "families": [ "gemini-flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-30", "lastUpdated": "2025-12-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-2.5-flash-tts", "modelKey": "gemini-2.5-flash-tts", "displayName": "Gemini 2.5 Flash TTS", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-10", "openWeights": false, "releaseDate": "2025-09-30" } } ] }, { "id": "google/gemini-2.5-pro", "provider": "google", "model": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "auriko", "cortecs", "deepinfra", "fastrouter", "frogbot", "gemini", "github-copilot", "github_copilot", "google", "google-vertex", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openrouter", "orcarouter", "perplexity-agent", "poe", "qiniu-ai", "requesty", "sap-ai-core", "vercel", "vercel_ai_gateway", "vertex_ai-language-models", "zenmux" ], "aliases": [ "302ai/gemini-2.5-pro", "abacus/gemini-2.5-pro", "aihubmix/gemini-2.5-pro", "anyapi/google/gemini-2.5-pro", "auriko/gemini-2.5-pro", "cortecs/gemini-2.5-pro", "deepinfra/google/gemini-2.5-pro", "fastrouter/google/gemini-2.5-pro", "frogbot/gemini-2.5-pro", "gemini/gemini-2.5-pro", "github-copilot/gemini-2.5-pro", "github_copilot/gemini-2.5-pro", "google-vertex/gemini-2.5-pro", "google/gemini-2.5-pro", "helicone/gemini-2.5-pro", "jiekou/gemini-2.5-pro", "kilo/google/gemini-2.5-pro", "llmgateway/gemini-2.5-pro", "merge-gateway/google/gemini-2.5-pro", "nano-gpt/gemini-2.5-pro", "nearai/google/gemini-2.5-pro", "openrouter/google/gemini-2.5-pro", "orcarouter/google/gemini-2.5-pro", "perplexity-agent/google/gemini-2.5-pro", "poe/google/gemini-2.5-pro", "qiniu-ai/gemini-2.5-pro", "requesty/google/gemini-2.5-pro", "sap-ai-core/gemini-2.5-pro", "vercel/google/gemini-2.5-pro", "vercel_ai_gateway/google/gemini-2.5-pro", "vertex_ai-language-models/gemini-2.5-pro", "zenmux/google/gemini-2.5-pro" ], "mergedProviderModelRecords": 32, "limits": { "contextTokens": 1065535, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 1000000, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true, "webSearch": true, "promptCaching": true, "serviceTier": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "abacus", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "auriko", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "cortecs", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.654, "output": 11.024 } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.31, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "frogbot", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.31, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "helicone", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3125, "cacheWrite": 1.25, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.087, "input": 0.87, "output": 7 } }, { "source": "models.dev", "provider": "requesty", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.31, "cacheWrite": 2.375, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 15, "cache_read": 0.25 }, "tiers": [ { "input": 2.5, "output": 15, "cache_read": 0.25, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.31, "cacheWrite": 4.5, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000125, "input_cost_per_token_above_200k_tokens_priority": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.00001, "output_cost_per_token_above_200k_tokens_priority": 0.000015 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "inputAudio": 0.7, "output": 10 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "internalReasoning": 10, "output": 10 }, "other": { "audio": 0.00000125, "image": 0.00000125, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro", "Gemini-2.5-Pro", "Google Gemini 2.5 Pro", "Google: Gemini 2.5 Pro", "gemini-2.5-pro" ], "families": [ "gemini-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-17", "lastUpdated": "2025-06-17", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 32 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Google Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "family": "gemini-pro", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Google: Gemini 2.5 Pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini-2.5-Pro", "family": "gemini-pro", "metadata": { "lastUpdated": "2025-02-05", "openWeights": false, "releaseDate": "2025-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gemini-2.5-pro", "modelKey": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-03-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-2.5-pro", "modelKey": "google/gemini-2.5-pro", "displayName": "Gemini 2.5 Pro", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemini-2.5-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-pro", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gemini-2.5-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-2.5-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-2.5-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-pro", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-pro", "displayName": "Google: Gemini 2.5 Pro", "metadata": { "canonicalSlug": "google/gemini-2.5-pro", "createdAt": "2025-06-17T14:12:24.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-pro-exp-03-25", "provider": "google", "model": "gemini-2.5-pro-exp-03-25", "displayName": "Gemini 2.5 Pro Experimental 0325", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-pro-exp-03-25" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-pro-exp-03-25", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Experimental 0325" ], "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-pro-exp-03-25", "modelKey": "gemini-2.5-pro-exp-03-25", "displayName": "Gemini 2.5 Pro Experimental 0325", "metadata": { "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "google/gemini-2.5-pro-preview", "provider": "google", "model": "gemini-2.5-pro-preview", "displayName": "Google: Gemini 2.5 Pro Preview 06-05", "family": "gemini", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/google/gemini-2.5-pro-preview", "openrouter/google/gemini-2.5-pro-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "internalReasoning": 10, "output": 10 }, "other": { "audio": 0.00000125, "image": 0.00000125, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Preview 06-05", "Google: Gemini 2.5 Pro Preview 06-05" ], "families": [ "gemini" ], "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-06-05", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-pro-preview", "modelKey": "google/gemini-2.5-pro-preview", "displayName": "Google: Gemini 2.5 Pro Preview 06-05", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-06-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-pro-preview", "modelKey": "google/gemini-2.5-pro-preview", "displayName": "Gemini 2.5 Pro Preview 06-05", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview", "displayName": "Google: Gemini 2.5 Pro Preview 06-05", "metadata": { "canonicalSlug": "google/gemini-2.5-pro-preview-06-05", "createdAt": "2025-06-05T15:27:37.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-pro-preview-03-25", "provider": "google", "model": "gemini-2.5-pro-preview-03-25", "displayName": "Gemini 2.5 Pro Preview 0325", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemini-2.5-pro-preview-03-25" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-pro-preview-03-25", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Preview 0325" ], "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-pro-preview-03-25", "modelKey": "gemini-2.5-pro-preview-03-25", "displayName": "Gemini 2.5 Pro Preview 0325", "metadata": { "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "google/gemini-2.5-pro-preview-05-06", "provider": "google", "model": "gemini-2.5-pro-preview-05-06", "displayName": "Google: Gemini 2.5 Pro Preview 05-06", "family": "gemini-pro", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/google/gemini-2.5-pro-preview-05-06", "nano-gpt/gemini-2.5-pro-preview-05-06", "openrouter/google/gemini-2.5-pro-preview-05-06" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemini-2.5-pro-preview-05-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-pro-preview-05-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview-05-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "output": 10, "reasoningOutput": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview-05-06", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "cacheWrite": 0.375, "input": 1.25, "internalReasoning": 10, "output": 10 }, "other": { "audio": 0.00000125, "image": 0.00000125, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Preview 05-06", "Gemini 2.5 Pro Preview 0506", "Google: Gemini 2.5 Pro Preview 05-06" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-05-06", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-2.5-pro-preview-05-06", "modelKey": "google/gemini-2.5-pro-preview-05-06", "displayName": "Google: Gemini 2.5 Pro Preview 05-06", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-05-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-pro-preview-05-06", "modelKey": "gemini-2.5-pro-preview-05-06", "displayName": "Gemini 2.5 Pro Preview 0506", "metadata": { "lastUpdated": "2025-05-06", "openWeights": false, "releaseDate": "2025-05-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-2.5-pro-preview-05-06", "modelKey": "google/gemini-2.5-pro-preview-05-06", "displayName": "Gemini 2.5 Pro Preview 05-06", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-2.5-pro-preview-05-06", "displayName": "Google: Gemini 2.5 Pro Preview 05-06", "metadata": { "canonicalSlug": "google/gemini-2.5-pro-preview-03-25", "createdAt": "2025-05-07T00:41:53.000Z", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65535, "is_moderated": false } } } ] }, { "id": "google/gemini-2.5-pro-preview-06-05", "provider": "google", "model": "gemini-2.5-pro-preview-06-05", "displayName": "gemini-2.5-pro-preview-06-05", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "jiekou", "nano-gpt" ], "aliases": [ "jiekou/gemini-2.5-pro-preview-06-05", "nano-gpt/gemini-2.5-pro-preview-06-05" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 200000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "gemini-2.5-pro-preview-06-05", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-2.5-pro-preview-06-05", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Preview 0605", "gemini-2.5-pro-preview-06-05" ], "families": [ "gemini-pro" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-2.5-pro-preview-06-05", "modelKey": "gemini-2.5-pro-preview-06-05", "displayName": "gemini-2.5-pro-preview-06-05", "family": "gemini-pro", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-2.5-pro-preview-06-05", "modelKey": "gemini-2.5-pro-preview-06-05", "displayName": "Gemini 2.5 Pro Preview 0605", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } } ] }, { "id": "google/gemini-2.5-pro-preview-tts", "provider": "google", "model": "gemini-2.5-pro-preview-tts", "displayName": "Gemini 2.5 Pro Preview TTS", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "google", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-2.5-pro-preview-tts", "google/gemini-2.5-pro-preview-tts", "vertex_ai-language-models/gemini-2.5-pro-preview-tts" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65535, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google", "model": "gemini-2.5-pro-preview-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 20 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-2.5-pro-preview-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "inputAudio": 0.7, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-2.5-pro-preview-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "inputAudio": 0.7, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro Preview TTS" ], "families": [ "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-05-01", "lastUpdated": "2025-05-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-2.5-pro-preview-tts", "modelKey": "gemini-2.5-pro-preview-tts", "displayName": "Gemini 2.5 Pro Preview TTS", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-05-01", "openWeights": false, "releaseDate": "2025-05-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-2.5-pro-preview-tts", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-2.5-pro-preview-tts", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview" } } ] }, { "id": "google/gemini-2.5-pro-tts", "provider": "google", "model": "gemini-2.5-pro-tts", "displayName": "Gemini 2.5 Pro TTS", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "google-vertex" ], "aliases": [ "google-vertex/gemini-2.5-pro-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-2.5-pro-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 20 } } ] }, "metadata": { "displayNames": [ "Gemini 2.5 Pro TTS" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-30", "lastUpdated": "2025-12-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-2.5-pro-tts", "modelKey": "gemini-2.5-pro-tts", "displayName": "Gemini 2.5 Pro TTS", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-10", "openWeights": false, "releaseDate": "2025-09-30" } } ] }, { "id": "google/gemini-25-flash-image", "provider": "google", "model": "gemini-25-flash-image", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "fal_ai" ], "aliases": [ "fal_ai/fal-ai/gemini-25-flash-image" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fal_ai", "model": "fal_ai/fal-ai/gemini-25-flash-image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.039 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fal_ai", "model": "fal_ai/fal-ai/gemini-25-flash-image", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "google/gemini-3-1-flash-lite", "provider": "google", "model": "gemini-3-1-flash-lite", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gemini-3-1-flash-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gemini-3-1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Lite Preview" ], "families": [ "gemini-flash-lite" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-3-1-flash-lite", "modelKey": "gemini-3-1-flash-lite", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "google/gemini-3-1-pro", "provider": "google", "model": "gemini-3-1-pro", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gemini-3-1-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gemini-3-1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro Preview Custom Tools" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "lastUpdated": "2026-02-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-3-1-pro", "modelKey": "gemini-3-1-pro", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "google/gemini-3-1-pro-preview", "provider": "google", "model": "gemini-3-1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "frogbot", "venice" ], "aliases": [ "frogbot/gemini-3-1-pro-preview", "venice/gemini-3-1-pro-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "gemini-3-1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "venice", "model": "gemini-3-1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 0.5, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5, "cache_write": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "cache_write": 0.5, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro Preview" ], "families": [ "gemini", "gemini-pro" ], "knowledgeCutoff": "2026-01", "releaseDate": "2026-02-18", "lastUpdated": "2026-02-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gemini-3-1-pro-preview", "modelKey": "gemini-3-1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-18", "openWeights": false, "releaseDate": "2026-02-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "gemini-3-1-pro-preview", "modelKey": "gemini-3-1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "google/gemini-3-5-flash", "provider": "google", "model": "gemini-3-5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/gemini-3-5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "gemini-3-5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.155, "cacheWrite": 0.086, "input": 1.55, "output": 9.45 } } ] }, "metadata": { "displayNames": [ "Gemini 3.5 Flash" ], "families": [ "gemini" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-22", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "gemini-3-5-flash", "modelKey": "gemini-3-5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-22", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "google/gemini-3-flash", "provider": "google", "model": "gemini-3-flash", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "neon", "opencode", "poe", "vercel" ], "aliases": [ "neon/gemini-3-flash", "opencode/gemini-3-flash", "poe/google/gemini-3-flash", "vercel/google/gemini-3-flash" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gemini-3-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "opencode", "model": "gemini-3-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-3-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2.4 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Flash", "Gemini 3 Flash Preview", "Gemini-3-Flash" ], "families": [ "gemini-flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-3-flash", "modelKey": "gemini-3-flash", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gemini-3-flash", "modelKey": "gemini-3-flash", "displayName": "Gemini 3 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-3-flash", "modelKey": "google/gemini-3-flash", "displayName": "Gemini-3-Flash", "metadata": { "lastUpdated": "2025-10-07", "openWeights": false, "releaseDate": "2025-10-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3-flash", "modelKey": "google/gemini-3-flash", "displayName": "Gemini 3 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } } ] }, { "id": "google/gemini-3-flash-preview", "provider": "google", "model": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "frogbot", "gemini", "github-copilot", "gmi", "google", "google-vertex", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "ollama-cloud", "openrouter", "orcarouter", "perplexity-agent", "qihang-ai", "requesty", "venice", "vertex_ai", "vertex_ai-language-models", "zenmux" ], "aliases": [ "302ai/gemini-3-flash-preview", "abacus/gemini-3-flash-preview", "aihubmix/gemini-3-flash-preview", "anyapi/google/gemini-3-flash-preview", "frogbot/gemini-3-flash-preview", "gemini/gemini-3-flash-preview", "github-copilot/gemini-3-flash-preview", "gmi/google/gemini-3-flash-preview", "google-vertex/gemini-3-flash-preview", "google/gemini-3-flash-preview", "jiekou/gemini-3-flash-preview", "kilo/google/gemini-3-flash-preview", "llmgateway/gemini-3-flash-preview", "merge-gateway/google/gemini-3-flash-preview", "nano-gpt/google/gemini-3-flash-preview", "ollama-cloud/gemini-3-flash-preview", "openrouter/google/gemini-3-flash-preview", "orcarouter/google/gemini-3-flash-preview", "perplexity-agent/google/gemini-3-flash-preview", "qihang-ai/gemini-3-flash-preview", "requesty/google/gemini-3-flash-preview", "venice/gemini-3-flash-preview", "vertex_ai-language-models/gemini-3-flash-preview", "vertex_ai/gemini-3-flash-preview", "zenmux/google/gemini-3-flash-preview" ], "mergedProviderModelRecords": 25, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true, "nativeStreaming": true, "serviceTier": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "abacus", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 0.5, "output": 3, "cache_read": 0.05 }, "tiers": [ { "input": 0.5, "output": 3, "cache_read": 0.05, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "frogbot", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.083333, "input": 0.5, "output": 3, "reasoningOutput": 3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.083333, "input": 0.5, "output": 3, "reasoningOutput": 3 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 }, "tiered": { "contextOver200K": { "input": 0.5, "output": 3, "cache_read": 0.05 }, "tiers": [ { "input": 0.5, "output": 3, "cache_read": 0.05, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.43 }, "tiered": { "contextOver200K": { "input": 0.07, "output": 0.43 }, "tiers": [ { "input": 0.07, "output": 0.43, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "requesty", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 1, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "venice", "model": "gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.7, "output": 3.75 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 1, "input": 0.5, "output": 3 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3, "reasoningOutput": 3 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/google/gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3, "reasoningOutput": 3 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3, "reasoningOutput": 3 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "inputAudio": 1, "output": 3 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3-flash-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.0833333333333, "input": 0.5, "internalReasoning": 3, "output": 3 }, "other": { "audio": 0.000001, "image": 5e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Flash", "Gemini 3 Flash (Preview)", "Gemini 3 Flash Preview", "Google: Gemini 3 Flash Preview", "gemini-3-flash-preview" ], "families": [ "gemini", "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-12-18", "lastUpdated": "2025-12-18", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 25 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 256, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "family": "gemini-flash", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Google: Gemini 3 Flash Preview", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash (Preview)", "family": "gemini-flash", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-08", "openWeights": true, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "gemini-3-flash-preview", "modelKey": "gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2025-12-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-3-flash-preview", "modelKey": "google/gemini-3-flash-preview", "displayName": "Gemini 3 Flash Preview", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3-flash-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/google/gemini-3-flash-preview", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-3-flash-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3-flash-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-3-flash-preview", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3-flash-preview", "displayName": "Google: Gemini 3 Flash Preview", "metadata": { "canonicalSlug": "google/gemini-3-flash-preview-20251217", "createdAt": "2025-12-17T15:57:58.000Z", "links": { "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65535, "is_moderated": false } } } ] }, { "id": "google/gemini-3-flash-preview-thinking", "provider": "google", "model": "gemini-3-flash-preview-thinking", "displayName": "Gemini 3 Flash Thinking", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemini-3-flash-preview-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3-flash-preview-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Flash Thinking" ], "families": [ "gemini-flash" ], "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3-flash-preview-thinking", "modelKey": "google/gemini-3-flash-preview-thinking", "displayName": "Gemini 3 Flash Thinking", "family": "gemini-flash", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17" } } ] }, { "id": "google/gemini-3-pro", "provider": "google", "model": "gemini-3-pro", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "nearai", "neon", "opencode", "poe", "replicate" ], "aliases": [ "nearai/google/gemini-3-pro", "neon/gemini-3-pro", "opencode/gemini-3-pro", "poe/google/gemini-3-pro", "replicate/google/gemini-3-pro" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nearai", "model": "google/gemini-3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 1.25, "output": 15 } }, { "source": "models.dev", "provider": "neon", "model": "gemini-3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "gemini-3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 9.6 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/google/gemini-3-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Pro", "Gemini 3 Pro Preview", "Gemini-3-Pro" ], "families": [ "gemini-pro" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-11-18", "lastUpdated": "2025-11-18", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-3-pro", "modelKey": "google/gemini-3-pro", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gemini-3-pro", "modelKey": "gemini-3-pro", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gemini-3-pro", "modelKey": "gemini-3-pro", "displayName": "Gemini 3 Pro", "family": "gemini-pro", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-3-pro", "modelKey": "google/gemini-3-pro", "displayName": "Gemini-3-Pro", "family": "gemini-pro", "status": "deprecated", "metadata": { "lastUpdated": "2025-10-22", "openWeights": false, "releaseDate": "2025-10-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/google/gemini-3-pro", "mode": "chat" } ] }, { "id": "google/gemini-3-pro-image", "provider": "google", "model": "gemini-3-pro-image", "displayName": "Nano Banana Pro (Gemini 3 Pro Image)", "family": "gemini", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter", "vercel" ], "aliases": [ "openrouter/google/gemini-3-pro-image", "vercel/google/gemini-3-pro-image" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3-pro-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3-pro-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3-pro-image", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "internalReasoning": 12, "output": 12 }, "other": { "audio": 0.000002, "image": 0.000002, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Google: Nano Banana Pro (Gemini 3 Pro Image)", "Nano Banana Pro (Gemini 3 Pro Image)" ], "families": [ "gemini", "gemini-pro" ], "knowledgeCutoff": "2025-03", "releaseDate": "2026-06-18", "lastUpdated": "2026-06-18", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3-pro-image", "modelKey": "google/gemini-3-pro-image", "displayName": "Nano Banana Pro (Gemini 3 Pro Image)", "family": "gemini", "metadata": { "lastUpdated": "2026-06-18", "openWeights": false, "releaseDate": "2026-06-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3-pro-image", "modelKey": "google/gemini-3-pro-image", "displayName": "Nano Banana Pro (Gemini 3 Pro Image)", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-09", "openWeights": false, "releaseDate": "2025-09-01" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3-pro-image", "displayName": "Google: Nano Banana Pro (Gemini 3 Pro Image)", "metadata": { "canonicalSlug": "google/gemini-3-pro-image-20260528", "createdAt": "2026-06-18T03:40:54.000Z", "links": { "details": "/api/v1/models/google/gemini-3-pro-image-20260528/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 65536, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "google/gemini-3-pro-image-preview", "provider": "google", "model": "gemini-3-pro-image-preview", "displayName": "Nano Banana Pro", "family": "gemini-pro", "mode": "image_generation", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "fastrouter", "gemini", "google", "kilo", "nano-gpt", "openrouter", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-3-pro-image-preview", "fastrouter/google/gemini-3-pro-image-preview", "gemini/gemini-3-pro-image-preview", "google/gemini-3-pro-image-preview", "kilo/google/gemini-3-pro-image-preview", "nano-gpt/gemini-3-pro-image-preview", "openrouter/google/gemini-3-pro-image-preview", "vertex_ai-language-models/gemini-3-pro-image-preview", "vertex_ai-language-models/vertex_ai/gemini-3-pro-image-preview" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxTokens": 32768, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": true, "embedding": false, "functionCalling": false, "imageGeneration": true, "moderation": false, "promptCaching": true, "rerank": false, "serviceTier": true, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 120 } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 120 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3-pro-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3-pro-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3-pro-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3-pro-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3-pro-image-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "internalReasoning": 12, "output": 12 }, "other": { "audio": 0.000002, "image": 0.000002, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Pro Image", "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "Nano Banana Pro", "gemini-3-pro-image-preview" ], "families": [ "gemini-pro" ], "modes": [ "image_generation" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-11-20", "lastUpdated": "2025-11-20", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-3-pro-image-preview", "modelKey": "gemini-3-pro-image-preview", "displayName": "gemini-3-pro-image-preview", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-3-pro-image-preview", "modelKey": "google/gemini-3-pro-image-preview", "displayName": "Nano Banana Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3-pro-image-preview", "modelKey": "gemini-3-pro-image-preview", "displayName": "Nano Banana Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3-pro-image-preview", "modelKey": "google/gemini-3-pro-image-preview", "displayName": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-3-pro-image-preview", "modelKey": "gemini-3-pro-image-preview", "displayName": "Gemini 3 Pro Image", "metadata": { "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3-pro-image-preview", "modelKey": "google/gemini-3-pro-image-preview", "displayName": "Nano Banana Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3-pro-image-preview", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3-pro-image-preview", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3-pro-image-preview", "mode": "image_generation", "metadata": { "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3-pro-image-preview", "displayName": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "metadata": { "canonicalSlug": "google/gemini-3-pro-image-preview-20251120", "createdAt": "2025-11-20T15:49:57.000Z", "links": { "details": "/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 65536, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "google/gemini-3-pro-preview", "provider": "google", "model": "gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "anyapi", "gemini", "github_copilot", "gmi", "google", "helicone", "jiekou", "merge-gateway", "openrouter", "orcarouter", "qihang-ai", "requesty", "vercel", "vertex_ai", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-3-pro-preview", "anyapi/google/gemini-3-pro-preview", "gemini/gemini-3-pro-preview", "github_copilot/gemini-3-pro-preview", "gmi/google/gemini-3-pro-preview", "google/gemini-3-pro-preview", "helicone/gemini-3-pro-preview", "jiekou/gemini-3-pro-preview", "merge-gateway/google/gemini-3-pro-preview", "openrouter/google/gemini-3-pro-preview", "orcarouter/google/gemini-3-pro-preview", "qihang-ai/gemini-3-pro-preview", "requesty/google/gemini-3-pro-preview", "vercel/google/gemini-3-pro-preview", "vertex_ai-language-models/gemini-3-pro-preview", "vertex_ai/gemini-3-pro-preview" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "parallelFunctionCalling": true, "nativeStreaming": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "helicone", "model": "gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19999999999999998, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "jiekou", "model": "gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.8, "output": 10.8 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 4, "output": 18 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 3.43 } }, { "source": "models.dev", "provider": "requesty", "model": "google/gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 4.5, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/google/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } } ] }, "metadata": { "displayNames": [ "Gemini 3 Pro", "Gemini 3 Pro Preview", "Google Gemini 3 Pro Preview", "gemini-3-pro-preview" ], "families": [ "gemini-pro" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-11-19", "lastUpdated": "2025-11-19", "deprecationDate": "2026-03-09", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-3-pro-preview", "modelKey": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "google/gemini-3-pro-preview", "modelKey": "google/gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3-pro-preview", "modelKey": "gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemini-3-pro-preview", "modelKey": "gemini-3-pro-preview", "displayName": "Google Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gemini-3-pro-preview", "modelKey": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "family": "gemini-pro", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3-pro-preview", "modelKey": "google/gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-3-pro-preview", "modelKey": "google/gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gemini-3-pro-preview", "modelKey": "gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "google/gemini-3-pro-preview", "modelKey": "google/gemini-3-pro-preview", "displayName": "Gemini 3 Pro", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3-pro-preview", "modelKey": "google/gemini-3-pro-preview", "displayName": "Gemini 3 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3-pro-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-03-09", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gemini-3-pro-preview", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/google/gemini-3-pro-preview", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-3-pro-preview", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3-pro-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-03-26", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-3-pro-preview", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "google/gemini-3.0-flash-preview", "provider": "google", "model": "gemini-3.0-flash-preview", "displayName": "Gemini 3.0 Flash Preview", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/gemini-3.0-flash-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "metadata": { "displayNames": [ "Gemini 3.0 Flash Preview" ], "releaseDate": "2025-12-18", "lastUpdated": "2025-12-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-3.0-flash-preview", "modelKey": "gemini-3.0-flash-preview", "displayName": "Gemini 3.0 Flash Preview", "metadata": { "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18" } } ] }, { "id": "google/gemini-3.0-pro-image-preview", "provider": "google", "model": "gemini-3.0-pro-image-preview", "displayName": "Gemini 3.0 Pro Image Preview", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/gemini-3.0-pro-image-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Gemini 3.0 Pro Image Preview" ], "releaseDate": "2025-11-20", "lastUpdated": "2025-11-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-3.0-pro-image-preview", "modelKey": "gemini-3.0-pro-image-preview", "displayName": "Gemini 3.0 Pro Image Preview", "metadata": { "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } } ] }, { "id": "google/gemini-3.0-pro-preview", "provider": "google", "model": "gemini-3.0-pro-preview", "displayName": "Gemini 3.0 Pro Preview", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/gemini-3.0-pro-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "metadata": { "displayNames": [ "Gemini 3.0 Pro Preview" ], "releaseDate": "2025-11-19", "lastUpdated": "2025-11-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gemini-3.0-pro-preview", "modelKey": "gemini-3.0-pro-preview", "displayName": "Gemini 3.0 Pro Preview", "metadata": { "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } } ] }, { "id": "google/gemini-3.1-flash-image", "provider": "google", "model": "gemini-3.1-flash-image", "displayName": "Nano Banana 2 (Gemini 3.1 Flash Image)", "family": "gemini", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter", "vercel" ], "aliases": [ "openrouter/google/gemini-3.1-flash-image", "vercel/google/gemini-3.1-flash-image" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.1-flash-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-flash-image", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 3 }, "other": { "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Image (Nano Banana 2)", "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", "Nano Banana 2 (Gemini 3.1 Flash Image)" ], "families": [ "gemini" ], "releaseDate": "2026-06-18", "lastUpdated": "2026-06-18", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-flash-image", "modelKey": "google/gemini-3.1-flash-image", "displayName": "Nano Banana 2 (Gemini 3.1 Flash Image)", "family": "gemini", "metadata": { "lastUpdated": "2026-06-18", "openWeights": false, "releaseDate": "2026-06-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.1-flash-image", "modelKey": "google/gemini-3.1-flash-image", "displayName": "Gemini 3.1 Flash Image (Nano Banana 2)", "family": "gemini", "metadata": { "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-flash-image", "displayName": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", "metadata": { "canonicalSlug": "google/gemini-3.1-flash-image-20260528", "createdAt": "2026-06-18T03:41:05.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "minimal" ], "default_effort": "minimal" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 65536, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-flash-image-preview", "provider": "google", "model": "gemini-3.1-flash-image-preview", "displayName": "Nano Banana 2", "family": "gemini-flash", "mode": "image_generation", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "fastrouter", "gemini", "google", "kilo", "openrouter", "vercel", "vertex_ai-language-models" ], "aliases": [ "302ai/gemini-3.1-flash-image-preview", "fastrouter/google/gemini-3.1-flash-image-preview", "gemini/gemini-3.1-flash-image-preview", "google/gemini-3.1-flash-image-preview", "kilo/google/gemini-3.1-flash-image-preview", "openrouter/google/gemini-3.1-flash-image-preview", "vercel/google/gemini-3.1-flash-image-preview", "vertex_ai-language-models/gemini-3.1-flash-image-preview", "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-image-preview" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 131072, "inputTokens": 65536, "maxTokens": 32768, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": true, "embedding": false, "functionCalling": false, "imageGeneration": true, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 60 } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 60 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.1-flash-image-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 3 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-flash-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.5, "outputImage": 60 }, "perImage": { "output": 0.045 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "input_cost_per_token_batches": 1.25e-7, "output_cost_per_image_token_batches": 0.00003, "output_cost_per_token_batches": 7.5e-7 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 3, "outputImage": 60 }, "perImage": { "input": 0.00056, "output": 0.0672 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-image-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 3, "outputImage": 60 }, "perImage": { "input": 0.00056, "output": 0.0672 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-flash-image-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 3 }, "other": { "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", "Nano Banana 2", "gemini-3.1-flash-image-preview" ], "families": [ "gemini", "gemini-flash" ], "modes": [ "image_generation" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-27", "lastUpdated": "2026-02-27", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gemini-3.1-flash-image-preview", "modelKey": "gemini-3.1-flash-image-preview", "displayName": "gemini-3.1-flash-image-preview", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-27", "openWeights": false, "releaseDate": "2026-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-3.1-flash-image-preview", "modelKey": "google/gemini-3.1-flash-image-preview", "displayName": "Nano Banana 2", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.1-flash-image-preview", "modelKey": "gemini-3.1-flash-image-preview", "displayName": "Nano Banana 2", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.1-flash-image-preview", "modelKey": "google/gemini-3.1-flash-image-preview", "displayName": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-flash-image-preview", "modelKey": "google/gemini-3.1-flash-image-preview", "displayName": "Nano Banana 2", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.1-flash-image-preview", "modelKey": "google/gemini-3.1-flash-image-preview", "displayName": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-flash-image-preview", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-image-preview", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-image-preview", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-flash-image-preview", "displayName": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", "metadata": { "canonicalSlug": "google/gemini-3.1-flash-image-preview-20260226", "createdAt": "2026-02-26T15:25:58.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "minimal" ], "default_effort": "minimal" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 65536, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-flash-lite", "provider": "google", "model": "gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "gemini", "google", "google-vertex", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openrouter", "poe", "vercel", "vertex_ai-language-models", "zenmux" ], "aliases": [ "aihubmix/gemini-3.1-flash-lite", "gemini/gemini-3.1-flash-lite", "google-vertex/gemini-3.1-flash-lite", "google/gemini-3.1-flash-lite", "kilo/google/gemini-3.1-flash-lite", "llmgateway/gemini-3.1-flash-lite", "merge-gateway/google/gemini-3.1-flash-lite", "nano-gpt/google/gemini-3.1-flash-lite", "nearai/google/gemini-3.1-flash-lite", "openrouter/google/gemini-3.1-flash-lite", "poe/google/gemini-3.1-flash-lite", "vercel/google/gemini-3.1-flash-lite", "vertex_ai-language-models/gemini-3.1-flash-lite", "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-lite", "zenmux/google/gemini-3.1-flash-lite" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "codeExecution": true, "embedding": false, "fileSearch": true, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true, "nativeStreaming": true, "serviceTier": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 1, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.08333, "input": 0.25, "output": 1.5, "reasoningOutput": 1.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.083333, "input": 0.25, "output": 1.5, "reasoningOutput": 1.5 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "extra": { "cache_read_input_token_cost_per_audio_token": 5e-8, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.0833333333333, "input": 0.25, "internalReasoning": 1.5, "output": 1.5 }, "other": { "audio": 5e-7, "image": 2.5e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Lite", "Gemini-3.1-Flash-Lite", "Google: Gemini 3.1 Flash Lite" ], "families": [ "gemini", "gemini-flash-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-07", "lastUpdated": "2026-05-07", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-3.1-flash-lite", "modelKey": "gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3.1-flash-lite", "modelKey": "gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.1-flash-lite", "modelKey": "gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Google: Gemini 3.1 Flash Lite", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-3.1-flash-lite", "modelKey": "gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini-3.1-Flash-Lite", "metadata": { "lastUpdated": "2026-02-18", "openWeights": false, "releaseDate": "2026-02-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-3.1-flash-lite", "modelKey": "google/gemini-3.1-flash-lite", "displayName": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-flash-lite", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-flash-lite", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-lite", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-lite", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite", "displayName": "Google: Gemini 3.1 Flash Lite", "metadata": { "canonicalSlug": "google/gemini-3.1-flash-lite-20260507", "createdAt": "2026-05-07T15:47:08.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "minimal" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-flash-lite-preview", "provider": "google", "model": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "gemini", "google", "google-vertex", "kilo", "llmgateway", "merge-gateway", "openrouter", "orcarouter", "vercel", "vertex_ai-language-models", "vivgrid", "zenmux" ], "aliases": [ "abacus/gemini-3.1-flash-lite-preview", "gemini/gemini-3.1-flash-lite-preview", "google-vertex/gemini-3.1-flash-lite-preview", "google/gemini-3.1-flash-lite-preview", "kilo/google/gemini-3.1-flash-lite-preview", "llmgateway/gemini-3.1-flash-lite-preview", "merge-gateway/google/gemini-3.1-flash-lite-preview", "openrouter/google/gemini-3.1-flash-lite-preview", "orcarouter/google/gemini-3.1-flash-lite-preview", "vercel/google/gemini-3.1-flash-lite-preview", "vertex_ai-language-models/gemini-3.1-flash-lite-preview", "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-lite-preview", "vivgrid/gemini-3.1-flash-lite-preview", "zenmux/google/gemini-3.1-flash-lite-preview" ], "mergedProviderModelRecords": 14, "limits": { "contextTokens": 1050000, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "codeExecution": true, "embedding": false, "fileSearch": true, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true, "nativeStreaming": true, "serviceTier": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 1, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.5, "reasoningOutput": 1.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.083333, "input": 0.25, "output": 1.5, "reasoningOutput": 1.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 1, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-flash-lite-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_per_audio_token": 5e-8, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "extra": { "cache_read_input_token_cost_per_audio_token": 5e-8, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-lite-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_per_audio_token": 5e-8, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-lite-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "inputAudio": 0.5, "output": 1.5, "reasoningOutput": 1.5 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_per_audio_token": 5e-8, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.0833333333333, "input": 0.25, "internalReasoning": 1.5, "output": 1.5 }, "other": { "audio": 5e-7, "image": 2.5e-7, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Flash Lite Preview", "Google: Gemini 3.1 Flash Lite Preview" ], "families": [ "gemini", "gemini-flash", "gemini-flash-lite" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-01", "lastUpdated": "2026-03-01", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 14 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gemini-3.1-flash-lite-preview", "modelKey": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3.1-flash-lite-preview", "modelKey": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.1-flash-lite-preview", "modelKey": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Google: Gemini 3.1 Flash Lite Preview", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-3.1-flash-lite-preview", "modelKey": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gemini-3.1-flash-lite-preview", "modelKey": "gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-3.1-flash-lite-preview", "modelKey": "google/gemini-3.1-flash-lite-preview", "displayName": "Gemini 3.1 Flash Lite Preview", "metadata": { "lastUpdated": "2025-03-20", "openWeights": false, "releaseDate": "2025-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-flash-lite-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-flash-lite-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.1-flash-lite-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/gemini-3.1-flash-lite-preview", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-flash-lite-preview", "displayName": "Google: Gemini 3.1 Flash Lite Preview", "metadata": { "canonicalSlug": "google/gemini-3.1-flash-lite-preview-20260303", "createdAt": "2026-03-03T04:37:53.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "minimal" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-flash-live-preview", "provider": "google", "model": "gemini-3.1-flash-live-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-3.1-flash-live-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini-3.1-flash-live-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "inputAudio": 3, "inputImage": 1, "output": 4.5, "outputAudio": 12 }, "perVideoSecond": { "input": 0.000033333333333333335 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-flash-live-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "inputAudio": 3, "inputImage": 1, "output": 4.5, "outputAudio": 12 }, "perVideoSecond": { "input": 0.000033333333333333335 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-3.1-flash-live-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-flash-live-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "google/gemini-3.1-pro", "provider": "google", "model": "gemini-3.1-pro", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "sources": [ "models.dev" ], "providers": [ "opencode", "poe", "snowflake-cortex" ], "aliases": [ "opencode/gemini-3.1-pro", "poe/google/gemini-3.1-pro", "snowflake-cortex/gemini-3.1-pro" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "gemini-3.1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-3.1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro Preview", "Gemini-3.1-Pro" ], "families": [ "gemini-pro" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "lastUpdated": "2026-02-19", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gemini-3.1-pro", "modelKey": "gemini-3.1-pro", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-3.1-pro", "modelKey": "google/gemini-3.1-pro", "displayName": "Gemini-3.1-Pro", "metadata": { "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "gemini-3.1-pro", "modelKey": "gemini-3.1-pro", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } } ] }, { "id": "google/gemini-3.1-pro-preview", "provider": "google", "model": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "aihubmix", "auriko", "fastrouter", "gemini", "github-copilot", "google", "google-vertex", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "openrouter", "orcarouter", "perplexity-agent", "vercel", "vertex_ai", "vertex_ai-language-models", "vivgrid", "zenmux" ], "aliases": [ "abacus/gemini-3.1-pro-preview", "aihubmix/gemini-3.1-pro-preview", "auriko/gemini-3.1-pro-preview", "fastrouter/google/gemini-3.1-pro-preview", "gemini/gemini-3.1-pro-preview", "github-copilot/gemini-3.1-pro-preview", "google-vertex/gemini-3.1-pro-preview", "google/gemini-3.1-pro-preview", "kilo/google/gemini-3.1-pro-preview", "llmgateway/gemini-3.1-pro-preview", "merge-gateway/google/gemini-3.1-pro-preview", "nano-gpt/google/gemini-3.1-pro-preview", "openrouter/google/gemini-3.1-pro-preview", "orcarouter/google/gemini-3.1-pro-preview", "perplexity-agent/google/gemini-3.1-pro-preview", "vercel/google/gemini-3.1-pro-preview", "vertex_ai-language-models/gemini-3.1-pro-preview", "vertex_ai/gemini-3.1-pro-preview", "vivgrid/gemini-3.1-pro-preview", "zenmux/google/gemini-3.1-pro-preview" ], "mergedProviderModelRecords": 20, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "webSearch": true, "nativeStreaming": true, "serviceTier": true, "urlContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "auriko", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12, "reasoningOutput": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 4, "output": 18 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 4.5, "input": 2, "output": 12 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000018 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.1-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "perImage": { "output": 0.00012 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.1-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "perImage": { "output": 0.00012 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "internalReasoning": 12, "output": 12 }, "other": { "audio": 0.000002, "image": 0.000002, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro (Preview)", "Gemini 3.1 Pro Preview", "Google: Gemini 3.1 Pro Preview" ], "families": [ "gemini", "gemini-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "lastUpdated": "2026-02-19", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 20 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 256, "max": 32000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Google: Gemini 3.1 Pro Preview", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro (Preview)", "metadata": { "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2025-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gemini-3.1-pro-preview", "modelKey": "gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-3.1-pro-preview", "modelKey": "google/gemini-3.1-pro-preview", "displayName": "Gemini 3.1 Pro Preview", "metadata": { "knowledgeCutoff": "2026-02-19", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-pro-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/google/gemini-3.1-pro-preview", "mode": "chat", "metadata": { "source": "https://openrouter.ai/google/gemini-3.1-pro-preview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.1-pro-preview", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.1-pro-preview", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview", "displayName": "Google: Gemini 3.1 Pro Preview", "metadata": { "canonicalSlug": "google/gemini-3.1-pro-preview-20260219", "createdAt": "2026-02-19T14:00:27.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-pro-preview-customtools", "provider": "google", "model": "gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "gemini", "google", "google-vertex", "kilo", "merge-gateway", "nano-gpt", "openrouter", "orcarouter", "vertex_ai", "vertex_ai-language-models" ], "aliases": [ "aihubmix/gemini-3.1-pro-preview-customtools", "gemini/gemini-3.1-pro-preview-customtools", "google-vertex/gemini-3.1-pro-preview-customtools", "google/gemini-3.1-pro-preview-customtools", "kilo/google/gemini-3.1-pro-preview-customtools", "merge-gateway/google/gemini-3.1-pro-preview-customtools", "nano-gpt/google/gemini-3.1-pro-preview-customtools", "openrouter/google/gemini-3.1-pro-preview-customtools", "orcarouter/google/gemini-3.1-pro-preview-customtools", "vertex_ai-language-models/gemini-3.1-pro-preview-customtools", "vertex_ai/gemini-3.1-pro-preview-customtools" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65536, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "promptCaching": true, "rerank": false, "serviceTier": true, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12, "reasoningOutput": 12 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 4, "output": 18 }, "tiered": { "contextOver200K": { "input": 4, "output": 18, "cache_read": 0.4 }, "tiers": [ { "input": 4, "output": 18, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.1-pro-preview-customtools", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "perImage": { "output": 0.00012 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 }, "perImage": { "output": 0.00012 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview-customtools", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "internalReasoning": 12, "output": 12 }, "other": { "audio": 0.000002, "image": 0.000002, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro (Preview Custom Tools)", "Gemini 3.1 Pro Preview Custom Tools", "Google: Gemini 3.1 Pro Preview Custom Tools" ], "families": [ "gemini-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-19", "lastUpdated": "2026-02-19", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gemini-3.1-pro-preview-customtools", "modelKey": "gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3.1-pro-preview-customtools", "modelKey": "gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.1-pro-preview-customtools", "modelKey": "gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.1-pro-preview-customtools", "modelKey": "google/gemini-3.1-pro-preview-customtools", "displayName": "Google: Gemini 3.1 Pro Preview Custom Tools", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3.1-pro-preview-customtools", "modelKey": "google/gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.1-pro-preview-customtools", "modelKey": "google/gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro (Preview Custom Tools)", "metadata": { "lastUpdated": "2026-02-27", "openWeights": false, "releaseDate": "2026-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.1-pro-preview-customtools", "modelKey": "google/gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-3.1-pro-preview-customtools", "modelKey": "google/gemini-3.1-pro-preview-customtools", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "family": "gemini-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.1-pro-preview-customtools", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.1-pro-preview-customtools", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.1-pro-preview-customtools", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.1-pro-preview-customtools", "displayName": "Google: Gemini 3.1 Pro Preview Custom Tools", "metadata": { "canonicalSlug": "google/gemini-3.1-pro-preview-customtools-20260219", "createdAt": "2026-02-25T18:58:43.000Z", "links": { "details": "/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.1-pro-preview-high", "provider": "google", "model": "gemini-3.1-pro-preview-high", "displayName": "Gemini 3.1 Pro (Preview High)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemini-3.1-pro-preview-high" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.1-pro-preview-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro (Preview High)" ], "releaseDate": "2026-02-21", "lastUpdated": "2026-02-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.1-pro-preview-high", "modelKey": "google/gemini-3.1-pro-preview-high", "displayName": "Gemini 3.1 Pro (Preview High)", "metadata": { "lastUpdated": "2026-02-21", "openWeights": false, "releaseDate": "2026-02-21" } } ] }, { "id": "google/gemini-3.1-pro-preview-low", "provider": "google", "model": "gemini-3.1-pro-preview-low", "displayName": "Gemini 3.1 Pro (Preview Low)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemini-3.1-pro-preview-low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.1-pro-preview-low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } } ] }, "metadata": { "displayNames": [ "Gemini 3.1 Pro (Preview Low)" ], "releaseDate": "2026-02-21", "lastUpdated": "2026-02-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.1-pro-preview-low", "modelKey": "google/gemini-3.1-pro-preview-low", "displayName": "Gemini 3.1 Pro (Preview Low)", "metadata": { "lastUpdated": "2026-02-21", "openWeights": false, "releaseDate": "2026-02-21" } } ] }, { "id": "google/gemini-3.5-flash", "provider": "google", "model": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fastrouter", "gemini", "github-copilot", "google", "google-vertex", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "opencode", "openrouter", "poe", "vercel", "vertex_ai", "vertex_ai-language-models", "zenmux" ], "aliases": [ "fastrouter/google/gemini-3.5-flash", "gemini/gemini-3.5-flash", "github-copilot/gemini-3.5-flash", "google-vertex/gemini-3.5-flash", "google/gemini-3.5-flash", "kilo/google/gemini-3.5-flash", "llmgateway/gemini-3.5-flash", "merge-gateway/google/gemini-3.5-flash", "nano-gpt/google/gemini-3.5-flash", "nearai/google/gemini-3.5-flash", "opencode/gemini-3.5-flash", "openrouter/google/gemini-3.5-flash", "poe/google/gemini-3.5-flash", "vercel/google/gemini-3.5-flash", "vertex_ai-language-models/gemini-3.5-flash", "vertex_ai/gemini-3.5-flash", "zenmux/google/gemini-3.5-flash" ], "mergedProviderModelRecords": 17, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "promptCaching": true, "rerank": false, "serviceTier": true, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "google-vertex", "model": "gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "google", "model": "gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "cacheWrite": 0.08333, "input": 1.5, "output": 9, "reasoningOutput": 9 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "opencode", "model": "gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "cacheWrite": 0.083333, "input": 1.5, "output": 9, "reasoningOutput": 9 } }, { "source": "models.dev", "provider": "poe", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1515, "input": 1.5152, "output": 9.0909 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "zenmux", "model": "google/gemini-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 9 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-3.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1, "output": 9, "reasoningOutput": 9 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-3.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1, "output": 9, "reasoningOutput": 9 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "inputAudio": 1, "output": 9, "reasoningOutput": 9 }, "searchContextPerQuery": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemini-3.5-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "cacheWrite": 0.0833333333333, "input": 1.5, "internalReasoning": 9, "output": 9 }, "other": { "audio": 0.000003, "image": 0.0000015, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini 3.5 Flash", "Gemini-3.5-Flash", "Google: Gemini 3.5 Flash" ], "families": [ "gemini", "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-19", "lastUpdated": "2026-05-19", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gemini-3.5-flash", "modelKey": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] }, { "type": "budget_tokens", "min": 256, "max": 24000 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-3.5-flash", "modelKey": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-3.5-flash", "modelKey": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Google: Gemini 3.5 Flash", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-3.5-flash", "modelKey": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gemini-3.5-flash", "modelKey": "gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini-3.5-Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "google/gemini-3.5-flash", "modelKey": "google/gemini-3.5-flash", "displayName": "Gemini 3.5 Flash", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-3.5-flash", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-3.5-flash", "mode": "chat", "metadata": { "source": "https://ai.google.dev/pricing/gemini-3", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-3.5-flash", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemini-3.5-flash", "displayName": "Google: Gemini 3.5 Flash", "metadata": { "canonicalSlug": "google/gemini-3.5-flash-20260519", "createdAt": "2026-05-19T12:30:00.000Z", "knowledgeCutoff": "2025-01-01", "links": { "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" }, "reasoning": { "mandatory": true, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-3.5-flash-thinking", "provider": "google", "model": "gemini-3.5-flash-thinking", "displayName": "Gemini 3.5 Flash Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemini-3.5-flash-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-3.5-flash-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 9 } } ] }, "metadata": { "displayNames": [ "Gemini 3.5 Flash Thinking" ], "releaseDate": "2026-05-19", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-3.5-flash-thinking", "modelKey": "google/gemini-3.5-flash-thinking", "displayName": "Gemini 3.5 Flash Thinking", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-19" } } ] }, { "id": "google/gemini-deep-research", "provider": "google", "model": "gemini-deep-research", "displayName": "gemini-deep-research", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/gemini-deep-research" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 0, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "google/gemini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.6, "output": 9.6 } } ] }, "metadata": { "displayNames": [ "gemini-deep-research" ], "statuses": [ "deprecated" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemini-deep-research", "modelKey": "google/gemini-deep-research", "displayName": "gemini-deep-research", "status": "deprecated", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "google/gemini-embedding-001", "provider": "google", "model": "gemini-embedding-001", "displayName": "Gemini Embedding 001", "family": "gemini", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "google", "google-vertex", "vercel", "vercel_ai_gateway", "vertex_ai-embedding-models" ], "aliases": [ "gemini/gemini-embedding-001", "google-vertex/gemini-embedding-001", "google/gemini-embedding-001", "vercel/google/gemini-embedding-001", "vercel_ai_gateway/google/gemini-embedding-001", "vertex_ai-embedding-models/gemini-embedding-001" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 8192, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-embedding-001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0 } }, { "source": "models.dev", "provider": "google", "model": "gemini-embedding-001", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-embedding-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-embedding-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0 } }, { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemini Embedding 001" ], "families": [ "gemini", "gemini-embedding" ], "modes": [ "embedding" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-embedding-001", "modelKey": "gemini-embedding-001", "displayName": "Gemini Embedding 001", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-embedding-001", "modelKey": "gemini-embedding-001", "displayName": "Gemini Embedding 001", "family": "gemini", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-embedding-001", "modelKey": "google/gemini-embedding-001", "displayName": "Gemini Embedding 001", "family": "gemini-embedding", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-embedding-001", "mode": "embedding", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemini-embedding-001", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-001", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } } ] }, { "id": "google/gemini-embedding-2", "provider": "google", "model": "gemini-embedding-2", "displayName": "Gemini Embedding 2", "family": "gemini-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "vercel", "vertex_ai", "vertex_ai-embedding-models" ], "aliases": [ "gemini/gemini-embedding-2", "vercel/google/gemini-embedding-2", "vertex_ai-embedding-models/gemini-embedding-2", "vertex_ai/gemini-embedding-2" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "multimodal": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-embedding-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } }, { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-embedding-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } } ] }, "metadata": { "displayNames": [ "Gemini Embedding 2" ], "families": [ "gemini-embedding" ], "modes": [ "embedding" ], "releaseDate": "2026-03-10", "lastUpdated": "2026-03-23", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemini-embedding-2", "modelKey": "google/gemini-embedding-2", "displayName": "Gemini Embedding 2", "family": "gemini-embedding", "metadata": { "lastUpdated": "2026-03-23", "openWeights": false, "releaseDate": "2026-03-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-embedding-2", "mode": "embedding", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-2", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-embedding-2", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/gemini-embedding-2-preview", "provider": "google", "model": "gemini-embedding-2-preview", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai", "vertex_ai-embedding-models" ], "aliases": [ "gemini/gemini-embedding-2-preview", "vertex_ai-embedding-models/gemini-embedding-2-preview", "vertex_ai/gemini-embedding-2-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "multimodal": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-embedding-2-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } }, { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-2-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/gemini-embedding-2-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0 }, "perImage": { "input": 0.00012 }, "perAudioSecond": { "input": 0.00016 }, "perVideoSecond": { "input": 0.00079 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-embedding-2-preview", "mode": "embedding", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "gemini-embedding-2-preview", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/gemini-embedding-2-preview", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/gemini-exp-1114", "provider": "google", "model": "gemini-exp-1114", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-exp-1114" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 8192, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-exp-1114", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "extra": { "input_cost_per_token_above_128k_tokens": 0, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_128k_tokens": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-exp-1114", "mode": "chat", "metadata": { "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "source": "https://ai.google.dev/pricing" } } ] }, { "id": "google/gemini-exp-1206", "provider": "google", "model": "gemini-exp-1206", "displayName": "Gemini 2.0 Pro 1206", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "nano-gpt" ], "aliases": [ "gemini/gemini-exp-1206", "nano-gpt/gemini-exp-1206" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2097152, "inputTokens": 2097152, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65535, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemini-exp-1206", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.258, "output": 4.998 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-exp-1206", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-exp-1206", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "extra": { "input_cost_per_token_above_128k_tokens": 0, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_128k_tokens": 0 } } ] }, "metadata": { "displayNames": [ "Gemini 2.0 Pro 1206" ], "modes": [ "chat" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemini-exp-1206", "modelKey": "gemini-exp-1206", "displayName": "Gemini 2.0 Pro 1206", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-exp-1206", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-exp-1206", "mode": "chat", "metadata": { "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "source": "https://ai.google.dev/pricing" } } ] }, { "id": "google/gemini-flash-1.5", "provider": "google", "model": "gemini-flash-1.5", "displayName": "Gemini 1.5 Flash", "family": "gemini-flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemini-flash-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-flash-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0748, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemini 1.5 Flash" ], "families": [ "gemini-flash" ], "releaseDate": "2024-05-14", "lastUpdated": "2024-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-flash-1.5", "modelKey": "google/gemini-flash-1.5", "displayName": "Gemini 1.5 Flash", "family": "gemini-flash", "metadata": { "lastUpdated": "2024-05-14", "openWeights": false, "releaseDate": "2024-05-14" } } ] }, { "id": "google/gemini-flash-experimental", "provider": "google", "model": "gemini-flash-experimental", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-language-models" ], "aliases": [ "vertex_ai-language-models/gemini-flash-experimental" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 3072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-flash-experimental", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perCharacter": { "input": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-flash-experimental", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/gemini-flash-latest", "provider": "google", "model": "gemini-flash-latest", "displayName": "Gemini Flash Latest", "family": "gemini-flash", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "gemini", "google", "google-vertex", "kilo", "merge-gateway", "nano-gpt", "openrouter", "orcarouter" ], "aliases": [ "gemini/gemini-flash-latest", "google-vertex/gemini-flash-latest", "google/gemini-flash-latest", "kilo/~google/gemini-flash-latest", "merge-gateway/google/gemini-flash-latest", "nano-gpt/google/gemini-flash-latest", "openrouter/~google/gemini-flash-latest", "orcarouter/google/gemini-flash-latest" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "urlContext": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.383, "input": 0.3, "output": 2.5 } }, { "source": "models.dev", "provider": "google", "model": "gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "kilo", "model": "~google/gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.08333333333333334, "input": 0.5, "output": 3 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 1, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 9 } }, { "source": "models.dev", "provider": "openrouter", "model": "~google/gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "cacheWrite": 0.083333, "input": 1.5, "output": 9, "reasoningOutput": 9 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-flash-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.5, "inputAudio": 1, "output": 3 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-flash-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-flash-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "~google/gemini-flash-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "cacheWrite": 0.0833333333333, "input": 1.5, "internalReasoning": 9, "output": 9 }, "other": { "audio": 0.000003, "image": 0.0000015, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini Flash Latest", "Google Gemini Flash Latest", "Google: Gemini Flash Latest" ], "families": [ "gemini-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-flash-latest", "modelKey": "gemini-flash-latest", "displayName": "Gemini Flash Latest", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-flash-latest", "modelKey": "gemini-flash-latest", "displayName": "Gemini Flash Latest", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 0, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~google/gemini-flash-latest", "modelKey": "~google/gemini-flash-latest", "displayName": "Google: Gemini Flash Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-flash-latest", "modelKey": "google/gemini-flash-latest", "displayName": "Gemini Flash Latest", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-flash-latest", "modelKey": "google/gemini-flash-latest", "displayName": "Gemini Flash Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~google/gemini-flash-latest", "modelKey": "~google/gemini-flash-latest", "displayName": "Google Gemini Flash Latest", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-flash-latest", "modelKey": "google/gemini-flash-latest", "displayName": "Gemini Flash Latest", "family": "gemini-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-flash-latest", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-flash-latest", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~google/gemini-flash-latest", "displayName": "Google Gemini Flash Latest", "metadata": { "canonicalSlug": "~google/gemini-flash-latest", "createdAt": "2026-04-27T19:33:18.000Z", "knowledgeCutoff": "2025-01-01", "links": { "details": "/api/v1/models/~google/gemini-flash-latest/endpoints" }, "reasoning": { "mandatory": true, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Router", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-flash-lite-latest", "provider": "google", "model": "gemini-flash-lite-latest", "displayName": "Gemini Flash-Lite Latest", "family": "gemini-flash-lite", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "google", "google-vertex", "merge-gateway", "nano-gpt", "orcarouter" ], "aliases": [ "gemini/gemini-flash-lite-latest", "google-vertex/gemini-flash-lite-latest", "google/gemini-flash-lite-latest", "merge-gateway/google/gemini-flash-lite-latest", "nano-gpt/google/gemini-flash-lite-latest", "orcarouter/google/gemini-flash-lite-latest" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "gemini-flash-lite-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "google", "model": "gemini-flash-lite-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "google/gemini-flash-lite-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-flash-lite-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemini-flash-lite-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-flash-lite-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-flash-lite-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "inputAudio": 0.3, "output": 0.4, "reasoningOutput": 0.4 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "displayNames": [ "Gemini Flash Lite Latest", "Gemini Flash-Lite Latest" ], "families": [ "gemini-flash-lite" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "gemini-flash-lite-latest", "modelKey": "gemini-flash-lite-latest", "displayName": "Gemini Flash-Lite Latest", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemini-flash-lite-latest", "modelKey": "gemini-flash-lite-latest", "displayName": "Gemini Flash-Lite Latest", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 512, "max": 24576 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemini-flash-lite-latest", "modelKey": "google/gemini-flash-lite-latest", "displayName": "Gemini Flash-Lite Latest", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-flash-lite-latest", "modelKey": "google/gemini-flash-lite-latest", "displayName": "Gemini Flash Lite Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemini-flash-lite-latest", "modelKey": "google/gemini-flash-lite-latest", "displayName": "Gemini Flash-Lite Latest", "family": "gemini-flash-lite", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-flash-lite-latest", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-flash-lite-latest", "mode": "chat", "metadata": { "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "google/gemini-gemma-2-27b-it", "provider": "google", "model": "gemini-gemma-2-27b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-gemma-2-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-gemma-2-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.05 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-gemma-2-27b-it", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "google/gemini-gemma-2-9b-it", "provider": "google", "model": "gemini-gemma-2-9b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/gemini-gemma-2-9b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-gemma-2-9b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.05 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-gemma-2-9b-it", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "google/gemini-live-2.5-flash-preview-native-audio-09-2025", "provider": "google", "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", "mode": "realtime", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "vertex_ai-language-models/gemini-live-2.5-flash-preview-native-audio-09-2025" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65535, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 3, "output": 2, "outputAudio": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "inputAudio": 3, "output": 2, "outputAudio": 12 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10 } } ] }, "metadata": { "modes": [ "realtime" ], "supportedEndpoints": [ "/v1/realtime", "/vertex_ai/live" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "mode": "realtime", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", "mode": "realtime", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/vertex_ai/live" ] } } ] }, { "id": "google/gemini-pro-latest", "provider": "google", "model": "gemini-pro-latest", "displayName": "Google: Gemini Pro Latest", "family": "gemini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "gemini", "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "gemini/gemini-pro-latest", "kilo/~google/gemini-pro-latest", "llmgateway/gemini-pro-latest", "nano-gpt/google/gemini-pro-latest", "openrouter/~google/gemini-pro-latest" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "maxAudioLengthHours": 8.4, "maxAudioPerPrompt": 1, "maxImagesPerPrompt": 3000, "maxPdfSizeMB": 30, "maxTokens": 65535, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~google/gemini-pro-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gemini-pro-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemini-pro-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "models.dev", "provider": "openrouter", "model": "~google/gemini-pro-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "output": 12, "reasoningOutput": 12 } }, { "source": "litellm", "provider": "gemini", "model": "gemini-pro-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-pro-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015 } }, { "source": "openrouter", "provider": "openrouter", "model": "~google/gemini-pro-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.375, "input": 2, "internalReasoning": 12, "output": 12 }, "other": { "audio": 0.000002, "image": 0.000002, "webSearch": 0.014 } } ] }, "metadata": { "displayNames": [ "Gemini Pro Latest", "Google Gemini Pro Latest", "Google: Gemini Pro Latest" ], "families": [ "gemini", "gemini-pro" ], "modes": [ "chat" ], "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~google/gemini-pro-latest", "modelKey": "~google/gemini-pro-latest", "displayName": "Google: Gemini Pro Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemini-pro-latest", "modelKey": "gemini-pro-latest", "displayName": "Gemini Pro Latest", "family": "gemini", "metadata": { "lastUpdated": "2026-02-27", "openWeights": false, "releaseDate": "2026-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemini-pro-latest", "modelKey": "google/gemini-pro-latest", "displayName": "Gemini Pro Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~google/gemini-pro-latest", "modelKey": "~google/gemini-pro-latest", "displayName": "Google Gemini Pro Latest", "family": "gemini-pro", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini-pro-latest", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-pro-latest", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~google/gemini-pro-latest", "displayName": "Google Gemini Pro Latest", "metadata": { "canonicalSlug": "~google/gemini-pro-latest", "createdAt": "2026-04-27T19:34:11.000Z", "links": { "details": "/api/v1/models/~google/gemini-pro-latest/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Router", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/gemini-robotics-er-1.5-preview", "provider": "google", "model": "gemini-robotics-er-1.5-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-language-models" ], "aliases": [ "gemini/gemini-robotics-er-1.5-preview", "vertex_ai-language-models/gemini-robotics-er-1.5-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65535, "outputTokens": 65535, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "urlContext": true, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/gemini-robotics-er-1.5-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 }, "searchContextPerQuery": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "gemini-robotics-er-1.5-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "input": 0.3, "inputAudio": 1, "output": 2.5, "reasoningOutput": 2.5 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemini-robotics-er-1.5-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "gemini-robotics-er-1.5-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions" ] } } ] }, { "id": "google/gemma-2-27b-it", "provider": "google", "model": "gemma-2-27b-it", "displayName": "Google: Gemma 2 27B", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/google/gemma-2-27b-it", "openrouter/google/gemma-2-27b-it" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemma-2-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 0.65 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-2-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 0.65 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-2-27b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "Gemma 2 27B", "Google: Gemma 2 27B" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-06-24", "lastUpdated": "2024-06-24", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-2-27b-it", "modelKey": "google/gemma-2-27b-it", "displayName": "Google: Gemma 2 27B", "metadata": { "lastUpdated": "2024-06-24", "openWeights": true, "releaseDate": "2024-06-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-2-27b-it", "modelKey": "google/gemma-2-27b-it", "displayName": "Gemma 2 27B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2024-07-13", "openWeights": true, "releaseDate": "2024-07-13" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-2-27b-it", "displayName": "Google: Gemma 2 27B", "metadata": { "canonicalSlug": "google/gemma-2-27b-it", "createdAt": "2024-07-13T00:00:00.000Z", "huggingFaceId": "google/gemma-2-27b-it", "instructType": "gemma", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/google/gemma-2-27b-it/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 8192, "max_completion_tokens": 2048, "is_moderated": false } } } ] }, { "id": "google/gemma-2-2b-it", "provider": "google", "model": "gemma-2-2b-it", "displayName": "Gemma 2 2b It", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/google/gemma-2-2b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "google/gemma-2-2b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 2 2b It" ], "releaseDate": "2024-07-16", "lastUpdated": "2024-07-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "google/gemma-2-2b-it", "modelKey": "google/gemma-2-2b-it", "displayName": "Gemma 2 2b It", "metadata": { "lastUpdated": "2024-07-16", "openWeights": true, "releaseDate": "2024-07-16" } } ] }, { "id": "google/gemma-2-9b", "provider": "google", "model": "gemma-2-9b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/google/gemma-2-9b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemma-2-9b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/gemma-2-9b", "mode": "chat" } ] }, { "id": "google/gemma-3", "provider": "google", "model": "gemma-3", "displayName": "Google Gemma 3", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "inference" ], "aliases": [ "inference/google/gemma-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 125000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inference", "model": "google/gemma-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Google Gemma 3" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "google/gemma-3", "modelKey": "google/gemma-3", "displayName": "Google Gemma 3", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "google/gemma-3-12b-it", "provider": "google", "model": "gemma-3-12b-it", "displayName": "Gemma 3 12B IT", "family": "gemma", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "crusoe", "deepinfra", "kilo", "novita", "novita-ai", "openrouter" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/google/gemma-3-12b-it", "crusoe/google/gemma-3-12b-it", "deepinfra/google/gemma-3-12b-it", "kilo/google/gemma-3-12b-it", "novita-ai/google/gemma-3-12b-it", "novita/google/gemma-3-12b-it", "openrouter/google/gemma-3-12b-it" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/google/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.56 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.04, "output": 0.13 } }, { "source": "models.dev", "provider": "novita-ai", "model": "google/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.15 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/google/gemma-3-12b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-12b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/google/gemma-3-12b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-3-12b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Gemma 3 12B", "Gemma 3 12B IT", "Google: Gemma 3 12B" ], "families": [ "gemma" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-04-11", "lastUpdated": "2025-04-11", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/google/gemma-3-12b-it", "modelKey": "workers-ai/@cf/google/gemma-3-12b-it", "displayName": "Gemma 3 12B IT", "family": "gemma", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-3-12b-it", "modelKey": "google/gemma-3-12b-it", "displayName": "Google: Gemma 3 12B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "google/gemma-3-12b-it", "modelKey": "google/gemma-3-12b-it", "displayName": "Gemma 3 12B", "family": "gemma", "metadata": { "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-3-12b-it", "modelKey": "google/gemma-3-12b-it", "displayName": "Gemma 3 12B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/google/gemma-3-12b-it", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-12b-it", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/google/gemma-3-12b-it", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-3-12b-it", "displayName": "Google: Gemma 3 12B", "metadata": { "canonicalSlug": "google/gemma-3-12b-it", "createdAt": "2025-03-13T21:50:25.000Z", "huggingFaceId": "google/gemma-3-12b-it", "instructType": "gemma", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/google/gemma-3-12b-it/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "google/gemma-3-27b-it", "provider": "google", "model": "gemma-3-27b-it", "displayName": "Gemma-3-27b-it", "family": "gemma", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "deepinfra", "gemini", "kilo", "nebius", "novita", "novita-ai", "openrouter", "stackit" ], "aliases": [ "deepinfra/google/gemma-3-27b-it", "gemini/gemma-3-27b-it", "kilo/google/gemma-3-27b-it", "nebius/google/gemma-3-27b-it", "novita-ai/google/gemma-3-27b-it", "novita/google/gemma-3-27b-it", "openrouter/google/gemma-3-27b-it", "stackit/google/gemma-3-27b-it" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.03, "output": 0.11 } }, { "source": "models.dev", "provider": "nebius", "model": "google/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.125, "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "novita-ai", "model": "google/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.119, "output": 0.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.16 } }, { "source": "models.dev", "provider": "stackit", "model": "google/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49, "output": 0.71 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.16 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perImage": { "input": 0 }, "perAudioSecond": { "input": 0, "inputAbove128KTokens": 0 }, "perVideoSecond": { "input": 0, "inputAbove128KTokens": 0 }, "perCharacter": { "input": 0, "inputAbove128KTokens": 0, "output": 0, "outputAbove128KTokens": 0 }, "extra": { "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token_above_128k_tokens": 0, "output_cost_per_token_above_128k_tokens": 0 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/google/gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/google/gemma-3-27b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.119, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-3-27b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "Gemma 3 27B", "Gemma-3-27b-it", "Google: Gemma 3 27B" ], "families": [ "gemma" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-10", "releaseDate": "2025-03-12", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-3-27b-it", "modelKey": "google/gemma-3-27b-it", "displayName": "Google: Gemma 3 27B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "google/gemma-3-27b-it", "modelKey": "google/gemma-3-27b-it", "displayName": "Gemma-3-27b-it", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "google/gemma-3-27b-it", "modelKey": "google/gemma-3-27b-it", "displayName": "Gemma 3 27B", "family": "gemma", "metadata": { "lastUpdated": "2025-03-25", "openWeights": true, "releaseDate": "2025-03-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-3-27b-it", "modelKey": "google/gemma-3-27b-it", "displayName": "Gemma 3 27B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-03-12", "openWeights": true, "releaseDate": "2025-03-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "google/gemma-3-27b-it", "modelKey": "google/gemma-3-27b-it", "displayName": "Gemma 3 27B", "family": "gemma", "metadata": { "lastUpdated": "2025-05-17", "openWeights": true, "releaseDate": "2025-05-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-27b-it", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/gemma-3-27b-it", "mode": "chat", "metadata": { "source": "https://aistudio.google.com" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/google/gemma-3-27b-it", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/google/gemma-3-27b-it", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-3-27b-it", "displayName": "Google: Gemma 3 27B", "metadata": { "canonicalSlug": "google/gemma-3-27b-it", "createdAt": "2025-03-12T05:12:39.000Z", "huggingFaceId": "google/gemma-3-27b-it", "instructType": "gemma", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/google/gemma-3-27b-it/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "google/gemma-3-4b-it", "provider": "google", "model": "gemma-3-4b-it", "displayName": "Google: Gemma 3 4B", "family": "gemma", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "deepinfra", "kilo", "openrouter" ], "aliases": [ "deepinfra/google/gemma-3-4b-it", "kilo/google/gemma-3-4b-it", "openrouter/google/gemma-3-4b-it" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemma-3-4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.08 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-3-4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-4b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.08 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-3-4b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Gemma 3 4B", "Google: Gemma 3 4B" ], "families": [ "gemma" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-03-13", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-3-4b-it", "modelKey": "google/gemma-3-4b-it", "displayName": "Google: Gemma 3 4B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-3-4b-it", "modelKey": "google/gemma-3-4b-it", "displayName": "Gemma 3 4B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-03-13", "openWeights": true, "releaseDate": "2025-03-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/google/gemma-3-4b-it", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-3-4b-it", "displayName": "Google: Gemma 3 4B", "metadata": { "canonicalSlug": "google/gemma-3-4b-it", "createdAt": "2025-03-13T22:38:30.000Z", "huggingFaceId": "google/gemma-3-4b-it", "instructType": "gemma", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/google/gemma-3-4b-it/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Gemini", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "google/gemma-3n-e2b-it", "provider": "google", "model": "gemma-3n-e2b-it", "displayName": "Gemma 3n E2b It", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/google/gemma-3n-e2b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "google/gemma-3n-e2b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 3n E2b It" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-06-12", "lastUpdated": "2025-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "google/gemma-3n-e2b-it", "modelKey": "google/gemma-3n-e2b-it", "displayName": "Gemma 3n E2b It", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-06-12", "openWeights": true, "releaseDate": "2025-06-12" } } ] }, { "id": "google/gemma-3n-e4b-it", "provider": "google", "model": "gemma-3n-e4b-it", "displayName": "Google: Gemma 3n 4B", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nvidia", "openrouter", "togetherai" ], "aliases": [ "kilo/google/gemma-3n-e4b-it", "nvidia/google/gemma-3n-e4b-it", "openrouter/google/gemma-3n-e4b-it", "togetherai/google/gemma-3n-E4B-it" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/gemma-3n-e4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.04 } }, { "source": "models.dev", "provider": "nvidia", "model": "google/gemma-3n-e4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-3n-e4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.12 } }, { "source": "models.dev", "provider": "togetherai", "model": "google/gemma-3n-E4B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.12 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-3n-e4b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "Gemma 3N E4B Instruct", "Gemma 3n 4B", "Gemma 3n E4b It", "Google: Gemma 3n 4B" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-3n-e4b-it", "modelKey": "google/gemma-3n-e4b-it", "displayName": "Google: Gemma 3n 4B", "metadata": { "lastUpdated": "2025-05-20", "openWeights": true, "releaseDate": "2025-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "google/gemma-3n-e4b-it", "modelKey": "google/gemma-3n-e4b-it", "displayName": "Gemma 3n E4b It", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-06-03", "openWeights": true, "releaseDate": "2025-06-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-3n-e4b-it", "modelKey": "google/gemma-3n-e4b-it", "displayName": "Gemma 3n 4B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-05-20", "openWeights": true, "releaseDate": "2025-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "google/gemma-3n-E4B-it", "modelKey": "google/gemma-3n-E4B-it", "displayName": "Gemma 3N E4B Instruct", "family": "gemma", "metadata": { "lastUpdated": "2025-05-20", "openWeights": true, "releaseDate": "2025-05-20" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-3n-e4b-it", "displayName": "Google: Gemma 3n 4B", "metadata": { "canonicalSlug": "google/gemma-3n-e4b-it", "createdAt": "2025-05-20T21:33:44.000Z", "huggingFaceId": "google/gemma-3n-E4B-it", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/google/gemma-3n-e4b-it/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "google/gemma-4-26b-a4b-it", "provider": "google", "model": "gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "cloudflare-workers-ai", "deepinfra", "google", "kilo", "merge-gateway", "nano-gpt", "novita-ai", "openrouter", "orcarouter", "siliconflow", "vercel" ], "aliases": [ "cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it", "deepinfra/google/gemma-4-26B-A4B-it", "google/gemma-4-26b-a4b-it", "kilo/google/gemma-4-26b-a4b-it", "merge-gateway/google/gemma-4-26b-a4b-it", "nano-gpt/google/gemma-4-26b-a4b-it", "novita-ai/google/gemma-4-26b-a4b-it", "openrouter/google/gemma-4-26b-a4b-it", "orcarouter/google/gemma-4-26b-a4b-it", "siliconflow/google/gemma-4-26B-A4B-it", "vercel/google/gemma-4-26b-a4b-it" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "interleaved": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "deepinfra", "model": "google/gemma-4-26B-A4B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.34 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.33 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.33 } }, { "source": "models.dev", "provider": "siliconflow", "model": "google/gemma-4-26B-A4B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.4 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.33 } } ] }, "metadata": { "displayNames": [ "Gemma 4 26B A4B", "Gemma 4 26B A4B IT", "Google: Gemma 4 26B A4B" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/google/gemma-4-26b-a4b-it", "modelKey": "@cf/google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "google/gemma-4-26B-A4B-it", "modelKey": "google/gemma-4-26B-A4B-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemma-4-26b-a4b-it", "modelKey": "gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Google: Gemma 4 26B A4B", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "google/gemma-4-26B-A4B-it", "modelKey": "google/gemma-4-26B-A4B-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemma-4-26b-a4b-it", "modelKey": "google/gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it", "displayName": "Google: Gemma 4 26B A4B", "metadata": { "canonicalSlug": "google/gemma-4-26b-a4b-it-20260403", "createdAt": "2026-04-03T14:53:09.000Z", "huggingFaceId": "google/gemma-4-26B-A4B-it", "links": { "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Gemma", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "google/gemma-4-26b-a4b-it-maas", "provider": "google", "model": "gemma-4-26b-a4b-it-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-openai_models" ], "aliases": [ "vertex_ai-openai_models/vertex_ai/google/gemma-4-26b-a4b-it-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-openai_models", "model": "vertex_ai/google/gemma-4-26b-a4b-it-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "supportedRegions": [ "global" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-openai_models", "model": "vertex_ai/google/gemma-4-26b-a4b-it-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", "supportedRegions": [ "global" ] } } ] }, { "id": "google/gemma-4-26b-a4b-it:free", "provider": "google", "model": "gemma-4-26b-a4b-it:free", "displayName": "Gemma 4 26B A4B (free)", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/google/gemma-4-26b-a4b-it:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 4 26B A4B (free)", "Google: Gemma 4 26B A4B (free)" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-4-26b-a4b-it:free", "modelKey": "google/gemma-4-26b-a4b-it:free", "displayName": "Gemma 4 26B A4B (free)", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-4-26b-a4b-it:free", "displayName": "Google: Gemma 4 26B A4B (free)", "metadata": { "canonicalSlug": "google/gemma-4-26b-a4b-it-20260403", "createdAt": "2026-04-03T14:53:09.000Z", "huggingFaceId": "google/gemma-4-26B-A4B-it", "links": { "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Gemma", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "google/gemma-4-26b-a4b-it:thinking", "provider": "google", "model": "gemma-4-26b-a4b-it:thinking", "displayName": "Gemma 4 26B A4B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemma-4-26b-a4b-it:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemma-4-26b-a4b-it:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Gemma 4 26B A4B Thinking" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemma-4-26b-a4b-it:thinking", "modelKey": "google/gemma-4-26b-a4b-it:thinking", "displayName": "Gemma 4 26B A4B Thinking", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } } ] }, { "id": "google/gemma-4-31b", "provider": "google", "model": "gemma-4-31b", "displayName": "Gemma-4-31B", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/gemma-4-31b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "google/gemma-4-31b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma-4-31B" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/gemma-4-31b", "modelKey": "google/gemma-4-31b", "displayName": "Gemma-4-31B", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } } ] }, { "id": "google/gemma-4-31b-it", "provider": "google", "model": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "berget", "deepinfra", "fastrouter", "google", "kilo", "lilac", "merge-gateway", "nano-gpt", "nearai", "novita-ai", "nvidia", "openrouter", "orcarouter", "siliconflow", "togetherai", "vercel" ], "aliases": [ "berget/google/gemma-4-31B-it", "deepinfra/google/gemma-4-31B-it", "fastrouter/google/gemma-4-31b-it", "google/gemma-4-31b-it", "kilo/google/gemma-4-31b-it", "lilac/google/gemma-4-31b-it", "merge-gateway/google/gemma-4-31b-it", "nano-gpt/google/gemma-4-31b-it", "nearai/google/gemma-4-31B-it", "novita-ai/google/gemma-4-31b-it", "nvidia/google/gemma-4-31b-it", "openrouter/google/gemma-4-31b-it", "orcarouter/google/gemma-4-31b-it", "siliconflow/google/gemma-4-31B-it", "togetherai/google/gemma-4-31B-it", "vercel/google/gemma-4-31b-it" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "berget", "model": "google/gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.275, "output": 0.55 } }, { "source": "models.dev", "provider": "deepinfra", "model": "google/gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.38 } }, { "source": "models.dev", "provider": "fastrouter", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.38 } }, { "source": "models.dev", "provider": "kilo", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.4 } }, { "source": "models.dev", "provider": "lilac", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.35 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.35 } }, { "source": "models.dev", "provider": "nearai", "model": "google/gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.026, "input": 0.13, "output": 0.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09, "input": 0.12, "output": 0.35 } }, { "source": "models.dev", "provider": "orcarouter", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.38 } }, { "source": "models.dev", "provider": "siliconflow", "model": "google/gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "models.dev", "provider": "togetherai", "model": "google/gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.39, "output": 0.97 } }, { "source": "models.dev", "provider": "vercel", "model": "google/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-4-31b-it", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.09, "input": 0.12, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B", "Gemma 4 31B IT", "Gemma 4 31B Instruct", "Gemma-4-31B-IT", "Google: Gemma 4 31B" ], "families": [ "gemma" ], "knowledgeCutoff": "2025-12", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "google/gemma-4-31B-it", "modelKey": "google/gemma-4-31B-it", "displayName": "Gemma 4 31B Instruct", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "google/gemma-4-31B-it", "modelKey": "google/gemma-4-31B-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google", "providerName": "Google", "providerDoc": "https://ai.google.dev/gemini-api/docs/models", "model": "gemma-4-31b-it", "modelKey": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Google: Gemma 4 31B", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lilac", "providerName": "Lilac", "providerApi": "https://api.getlilac.com/v1", "providerDoc": "https://docs.getlilac.com/inference/models", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "google/gemma-4-31B-it", "modelKey": "google/gemma-4-31B-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma-4-31B-IT", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "google/gemma-4-31B-it", "modelKey": "google/gemma-4-31B-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "google/gemma-4-31B-it", "modelKey": "google/gemma-4-31B-it", "displayName": "Gemma 4 31B Instruct", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/gemma-4-31b-it", "modelKey": "google/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-4-31b-it", "displayName": "Google: Gemma 4 31B", "metadata": { "canonicalSlug": "google/gemma-4-31b-it-20260402", "createdAt": "2026-04-02T16:48:06.000Z", "huggingFaceId": "google/gemma-4-31B-it", "links": { "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Gemma", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "google/gemma-4-31b-it:free", "provider": "google", "model": "gemma-4-31b-it:free", "displayName": "Gemma 4 31B (free)", "family": "gemma", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/google/gemma-4-31b-it:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "google/gemma-4-31b-it:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/gemma-4-31b-it:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B (free)", "Google: Gemma 4 31B (free)" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "supportedParameters": [ "include_reasoning", "max_tokens", "min_p", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/gemma-4-31b-it:free", "modelKey": "google/gemma-4-31b-it:free", "displayName": "Gemma 4 31B (free)", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/gemma-4-31b-it:free", "displayName": "Google: Gemma 4 31B (free)", "metadata": { "canonicalSlug": "google/gemma-4-31b-it-20260402", "createdAt": "2026-04-02T16:48:06.000Z", "huggingFaceId": "google/gemma-4-31B-it", "links": { "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "min_p", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "tokenizer": "Gemma", "topProvider": { "context_length": 262144, "max_completion_tokens": 8192, "is_moderated": true } } } ] }, { "id": "google/gemma-4-31b-it:thinking", "provider": "google", "model": "gemma-4-31b-it:thinking", "displayName": "Gemma 4 31B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/google/gemma-4-31b-it:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "google/gemma-4-31b-it:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Thinking" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "google/gemma-4-31b-it:thinking", "modelKey": "google/gemma-4-31b-it:thinking", "displayName": "Gemma 4 31B Thinking", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } } ] }, { "id": "google/gemma-4-31b-turbo-tee", "provider": "google", "model": "gemma-4-31b-turbo-tee", "displayName": "gemma 4 31B turbo TEE", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/google/gemma-4-31B-turbo-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "google/gemma-4-31B-turbo-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.065, "input": 0.13, "output": 0.38 } } ] }, "metadata": { "displayNames": [ "gemma 4 31B turbo TEE" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "google/gemma-4-31B-turbo-TEE", "modelKey": "google/gemma-4-31B-turbo-TEE", "displayName": "gemma 4 31B turbo TEE", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "google/gemma-7b-it", "provider": "google", "model": "gemma-7b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/google/gemma-7b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/google/gemma-7b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/google/gemma-7b-it", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" } } ] }, { "id": "google/google-paligemma", "provider": "google", "model": "google-paligemma", "displayName": "paligemma", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/google/google-paligemma" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "google/google-paligemma", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "paligemma" ], "releaseDate": "2024-05-14", "lastUpdated": "2024-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "google/google-paligemma", "modelKey": "google/google-paligemma", "displayName": "paligemma", "metadata": { "lastUpdated": "2024-08-26", "openWeights": true, "releaseDate": "2024-05-14" } } ] }, { "id": "google/imagen-3", "provider": "google", "model": "imagen-3", "displayName": "Imagen-3", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/imagen-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen-3" ], "families": [ "imagen" ], "releaseDate": "2024-10-15", "lastUpdated": "2024-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/imagen-3", "modelKey": "google/imagen-3", "displayName": "Imagen-3", "family": "imagen", "metadata": { "lastUpdated": "2024-10-15", "openWeights": false, "releaseDate": "2024-10-15" } } ] }, { "id": "google/imagen-3-fast", "provider": "google", "model": "imagen-3-fast", "displayName": "Imagen-3-Fast", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/imagen-3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen-3-Fast" ], "families": [ "imagen" ], "releaseDate": "2024-10-17", "lastUpdated": "2024-10-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/imagen-3-fast", "modelKey": "google/imagen-3-fast", "displayName": "Imagen-3-Fast", "family": "imagen", "metadata": { "lastUpdated": "2024-10-17", "openWeights": false, "releaseDate": "2024-10-17" } } ] }, { "id": "google/imagen-3.0-capability-001", "provider": "google", "model": "imagen-3.0-capability-001", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "vertex_ai-image-models" ], "aliases": [ "vertex_ai-image-models/vertex_ai/imagen-3.0-capability-001" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-capability-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-capability-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" } } ] }, { "id": "google/imagen-3.0-fast-generate-001", "provider": "google", "model": "imagen-3.0-fast-generate-001", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-image-models" ], "aliases": [ "gemini/imagen-3.0-fast-generate-001", "vertex_ai-image-models/vertex_ai/imagen-3.0-fast-generate-001" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-3.0-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-3.0-fast-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-fast-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/imagen-3.0-generate-001", "provider": "google", "model": "imagen-3.0-generate-001", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-image-models" ], "aliases": [ "gemini/imagen-3.0-generate-001", "vertex_ai-image-models/vertex_ai/imagen-3.0-generate-001" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-3.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-3.0-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/imagen-3.0-generate-002", "provider": "google", "model": "imagen-3.0-generate-002", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-image-models" ], "aliases": [ "gemini/imagen-3.0-generate-002", "vertex_ai-image-models/vertex_ai/imagen-3.0-generate-002" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-3.0-generate-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-generate-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "deprecationDate": "2025-11-10", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-3.0-generate-002", "mode": "image_generation", "metadata": { "deprecationDate": "2025-11-10", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-3.0-generate-002", "mode": "image_generation", "metadata": { "deprecationDate": "2025-11-10", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/imagen-4", "provider": "google", "model": "imagen-4", "displayName": "Imagen-4", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/imagen-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen-4" ], "families": [ "imagen" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/imagen-4", "modelKey": "google/imagen-4", "displayName": "Imagen-4", "family": "imagen", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "google/imagen-4-fast", "provider": "google", "model": "imagen-4-fast", "displayName": "Imagen-4-Fast", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/imagen-4-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen-4-Fast" ], "families": [ "imagen" ], "releaseDate": "2025-06-25", "lastUpdated": "2025-06-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/imagen-4-fast", "modelKey": "google/imagen-4-fast", "displayName": "Imagen-4-Fast", "family": "imagen", "metadata": { "lastUpdated": "2025-06-25", "openWeights": false, "releaseDate": "2025-06-25" } } ] }, { "id": "google/imagen-4-ultra", "provider": "google", "model": "imagen-4-ultra", "displayName": "Imagen-4-Ultra", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/imagen-4-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen-4-Ultra" ], "families": [ "imagen" ], "releaseDate": "2025-05-24", "lastUpdated": "2025-05-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/imagen-4-ultra", "modelKey": "google/imagen-4-ultra", "displayName": "Imagen-4-Ultra", "family": "imagen", "metadata": { "lastUpdated": "2025-05-24", "openWeights": false, "releaseDate": "2025-05-24" } } ] }, { "id": "google/imagen-4.0-fast", "provider": "google", "model": "imagen-4.0-fast", "displayName": "Imagen 4 Fast", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/google/imagen-4.0-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen 4 Fast" ], "families": [ "imagen" ], "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/imagen-4.0-fast", "modelKey": "google/imagen-4.0-fast", "displayName": "Imagen 4 Fast", "family": "imagen", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "google/imagen-4.0-fast-generate-001", "provider": "google", "model": "imagen-4.0-fast-generate-001", "displayName": "Imagen 4 Fast", "family": "imagen", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "vercel", "vertex_ai-image-models" ], "aliases": [ "gemini/imagen-4.0-fast-generate-001", "vercel/google/imagen-4.0-fast-generate-001", "vertex_ai-image-models/vertex_ai/imagen-4.0-fast-generate-001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-4.0-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } } ] }, "metadata": { "displayNames": [ "Imagen 4 Fast" ], "families": [ "imagen" ], "modes": [ "image_generation" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/imagen-4.0-fast-generate-001", "modelKey": "google/imagen-4.0-fast-generate-001", "displayName": "Imagen 4 Fast", "family": "imagen", "metadata": { "lastUpdated": "2025-06", "openWeights": false, "releaseDate": "2025-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-4.0-fast-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-fast-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/imagen-4.0-generate-001", "provider": "google", "model": "imagen-4.0-generate-001", "displayName": "Imagen 4", "family": "imagen", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "vercel", "vertex_ai-image-models" ], "aliases": [ "gemini/imagen-4.0-generate-001", "vercel/google/imagen-4.0-generate-001", "vertex_ai-image-models/vertex_ai/imagen-4.0-generate-001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": false, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-4.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "displayNames": [ "Imagen 4" ], "families": [ "imagen" ], "modes": [ "image_generation" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/imagen-4.0-generate-001", "modelKey": "google/imagen-4.0-generate-001", "displayName": "Imagen 4", "family": "imagen", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-4.0-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/imagen-4.0-ultra", "provider": "google", "model": "imagen-4.0-ultra", "displayName": "Imagen 4 Ultra", "family": "imagen", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/google/imagen-4.0-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Imagen 4 Ultra" ], "families": [ "imagen" ], "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/imagen-4.0-ultra", "modelKey": "google/imagen-4.0-ultra", "displayName": "Imagen 4 Ultra", "family": "imagen", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "google/imagen-4.0-ultra-generate-001", "provider": "google", "model": "imagen-4.0-ultra-generate-001", "displayName": "Imagen 4 Ultra", "family": "imagen", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "aiml", "gemini", "vercel", "vertex_ai-image-models" ], "aliases": [ "aiml/google/imagen-4.0-ultra-generate-001", "gemini/imagen-4.0-ultra-generate-001", "vercel/google/imagen-4.0-ultra-generate-001", "vertex_ai-image-models/vertex_ai/imagen-4.0-ultra-generate-001" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": false, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/google/imagen-4.0-ultra-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.078 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/imagen-4.0-ultra-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } }, { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-ultra-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "displayNames": [ "Imagen 4 Ultra" ], "families": [ "imagen" ], "modes": [ "image_generation" ], "releaseDate": "2025-05-24", "lastUpdated": "2025-05-24", "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/imagen-4.0-ultra-generate-001", "modelKey": "google/imagen-4.0-ultra-generate-001", "displayName": "Imagen 4 Ultra", "family": "imagen", "metadata": { "lastUpdated": "2025-05-24", "openWeights": false, "releaseDate": "2025-05-24" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/google/imagen-4.0-ultra-generate-001", "mode": "image_generation", "metadata": { "metadata": { "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" }, "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/imagen-4.0-ultra-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagen-4.0-ultra-generate-001", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "google/learnlm-1.5-pro-experimental", "provider": "google", "model": "learnlm-1.5-pro-experimental", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/learnlm-1.5-pro-experimental" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32767, "inputTokens": 32767, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": true, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/learnlm-1.5-pro-experimental", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perImage": { "input": 0 }, "perAudioSecond": { "input": 0, "inputAbove128KTokens": 0 }, "perVideoSecond": { "input": 0, "inputAbove128KTokens": 0 }, "perCharacter": { "input": 0, "inputAbove128KTokens": 0, "output": 0, "outputAbove128KTokens": 0 }, "extra": { "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token_above_128k_tokens": 0, "output_cost_per_token_above_128k_tokens": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/learnlm-1.5-pro-experimental", "mode": "chat", "metadata": { "source": "https://aistudio.google.com" } } ] }, { "id": "google/lyria", "provider": "google", "model": "lyria", "displayName": "Lyria", "family": "lyria", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/lyria" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Lyria" ], "families": [ "lyria" ], "releaseDate": "2025-06-04", "lastUpdated": "2025-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/lyria", "modelKey": "google/lyria", "displayName": "Lyria", "family": "lyria", "metadata": { "lastUpdated": "2025-06-04", "openWeights": false, "releaseDate": "2025-06-04" } } ] }, { "id": "google/lyria-3-clip-preview", "provider": "google", "model": "lyria-3-clip-preview", "displayName": "Google: Lyria 3 Clip Preview", "family": "lyria", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "gemini", "kilo", "openrouter" ], "aliases": [ "gemini/lyria-3-clip-preview", "kilo/google/lyria-3-clip-preview", "openrouter/google/lyria-3-clip-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048576, "inputTokens": 131072, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "systemMessages": false, "transcription": false, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/lyria-3-clip-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/lyria-3-clip-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/lyria-3-clip-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perImage": { "output": 0.04 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/lyria-3-clip-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Google: Lyria 3 Clip Preview", "Lyria 3 Clip Preview" ], "families": [ "lyria" ], "modes": [ "chat" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-04-11", "supportedParameters": [ "max_tokens", "response_format", "seed", "temperature", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/lyria-3-clip-preview", "modelKey": "google/lyria-3-clip-preview", "displayName": "Google: Lyria 3 Clip Preview", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/lyria-3-clip-preview", "modelKey": "google/lyria-3-clip-preview", "displayName": "Lyria 3 Clip Preview", "family": "lyria", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/lyria-3-clip-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/lyria-3-clip-preview", "displayName": "Google: Lyria 3 Clip Preview", "metadata": { "canonicalSlug": "google/lyria-3-clip-preview-20260330", "createdAt": "2026-03-30T21:47:35.000Z", "links": { "details": "/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "seed", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/lyria-3-pro-preview", "provider": "google", "model": "lyria-3-pro-preview", "displayName": "Google: Lyria 3 Pro Preview", "family": "lyria", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "gemini", "kilo", "openrouter" ], "aliases": [ "gemini/lyria-3-pro-preview", "kilo/google/lyria-3-pro-preview", "openrouter/google/lyria-3-pro-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1048576, "inputTokens": 131072, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "systemMessages": false, "transcription": false, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "google/lyria-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "google/lyria-3-pro-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "gemini", "model": "gemini/lyria-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "google/lyria-3-pro-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Google: Lyria 3 Pro Preview", "Lyria 3 Pro Preview" ], "families": [ "lyria" ], "modes": [ "chat" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-04-11", "supportedParameters": [ "max_tokens", "response_format", "seed", "temperature", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "google/lyria-3-pro-preview", "modelKey": "google/lyria-3-pro-preview", "displayName": "Google: Lyria 3 Pro Preview", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "google/lyria-3-pro-preview", "modelKey": "google/lyria-3-pro-preview", "displayName": "Lyria 3 Pro Preview", "family": "lyria", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/lyria-3-pro-preview", "mode": "chat", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "google/lyria-3-pro-preview", "displayName": "Google: Lyria 3 Pro Preview", "metadata": { "canonicalSlug": "google/lyria-3-pro-preview-20260330", "createdAt": "2026-03-30T21:48:06.000Z", "links": { "details": "/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "seed", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048576, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "google/nano-banana", "provider": "google", "model": "nano-banana", "displayName": "Nano-Banana", "family": "nano-banana", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/nano-banana" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "google/nano-banana", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.021, "input": 0.21, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Nano-Banana" ], "families": [ "nano-banana" ], "releaseDate": "2025-08-21", "lastUpdated": "2025-08-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/nano-banana", "modelKey": "google/nano-banana", "displayName": "Nano-Banana", "family": "nano-banana", "metadata": { "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } } ] }, { "id": "google/nano-banana-pro", "provider": "google", "model": "nano-banana-pro", "displayName": "Nano-Banana-Pro", "family": "nano-banana", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "aiml", "poe" ], "aliases": [ "aiml/google/nano-banana-pro", "poe/google/nano-banana-pro" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "google/nano-banana-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 12 } }, { "source": "litellm", "provider": "aiml", "model": "aiml/google/nano-banana-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.195 } } ] }, "metadata": { "displayNames": [ "Nano-Banana-Pro" ], "families": [ "nano-banana" ], "modes": [ "image_generation" ], "releaseDate": "2025-11-19", "lastUpdated": "2025-11-19", "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/nano-banana-pro", "modelKey": "google/nano-banana-pro", "displayName": "Nano-Banana-Pro", "family": "nano-banana", "metadata": { "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/google/nano-banana-pro", "mode": "image_generation", "metadata": { "metadata": { "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" }, "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "google/text-embedding-005", "provider": "google", "model": "text-embedding-005", "displayName": "Text Embedding 005", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/google/text-embedding-005", "vercel_ai_gateway/google/text-embedding-005" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 0, "maxTokens": 0, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/text-embedding-005", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0 } } ] }, "metadata": { "displayNames": [ "Text Embedding 005" ], "families": [ "text-embedding" ], "modes": [ "embedding" ], "releaseDate": "2024-08-01", "lastUpdated": "2024-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/text-embedding-005", "modelKey": "google/text-embedding-005", "displayName": "Text Embedding 005", "family": "text-embedding", "metadata": { "lastUpdated": "2024-08", "openWeights": false, "releaseDate": "2024-08-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/text-embedding-005", "mode": "embedding" } ] }, { "id": "google/text-multilingual-embedding-002", "provider": "google", "model": "text-multilingual-embedding-002", "displayName": "Text Multilingual Embedding 002", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/google/text-multilingual-embedding-002", "vercel_ai_gateway/google/text-multilingual-embedding-002" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 0, "maxTokens": 0, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/text-multilingual-embedding-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0 } } ] }, "metadata": { "displayNames": [ "Text Multilingual Embedding 002" ], "families": [ "text-embedding" ], "modes": [ "embedding" ], "releaseDate": "2024-03-01", "lastUpdated": "2024-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/text-multilingual-embedding-002", "modelKey": "google/text-multilingual-embedding-002", "displayName": "Text Multilingual Embedding 002", "family": "text-embedding", "metadata": { "lastUpdated": "2024-03", "openWeights": false, "releaseDate": "2024-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/google/text-multilingual-embedding-002", "mode": "embedding" } ] }, { "id": "google/veo-2", "provider": "google", "model": "veo-2", "displayName": "Veo-2", "family": "veo", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/veo-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo-2" ], "families": [ "veo" ], "releaseDate": "2024-12-02", "lastUpdated": "2024-12-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/veo-2", "modelKey": "google/veo-2", "displayName": "Veo-2", "family": "veo", "metadata": { "lastUpdated": "2024-12-02", "openWeights": false, "releaseDate": "2024-12-02" } } ] }, { "id": "google/veo-2.0-generate-001", "provider": "google", "model": "veo-2.0-generate-001", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-video-models" ], "aliases": [ "gemini/veo-2.0-generate-001", "vertex_ai-video-models/vertex_ai/veo-2.0-generate-001" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-2.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.35 } }, { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-2.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.35 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-2.0-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-2.0-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } } ] }, { "id": "google/veo-3", "provider": "google", "model": "veo-3", "displayName": "Veo-3", "family": "veo", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/veo-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo-3" ], "families": [ "veo" ], "releaseDate": "2025-05-21", "lastUpdated": "2025-05-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/veo-3", "modelKey": "google/veo-3", "displayName": "Veo-3", "family": "veo", "metadata": { "lastUpdated": "2025-05-21", "openWeights": false, "releaseDate": "2025-05-21" } } ] }, { "id": "google/veo-3-fast", "provider": "google", "model": "veo-3-fast", "displayName": "Veo-3-Fast", "family": "veo", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/veo-3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo-3-Fast" ], "families": [ "veo" ], "releaseDate": "2025-10-13", "lastUpdated": "2025-10-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/veo-3-fast", "modelKey": "google/veo-3-fast", "displayName": "Veo-3-Fast", "family": "veo", "metadata": { "lastUpdated": "2025-10-13", "openWeights": false, "releaseDate": "2025-10-13" } } ] }, { "id": "google/veo-3.0-fast-generate-001", "provider": "google", "model": "veo-3.0-fast-generate-001", "displayName": "Veo 3.0 Fast Generate", "family": "veo", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vertex_ai-video-models" ], "aliases": [ "vercel/google/veo-3.0-fast-generate-001", "vertex_ai-video-models/vertex_ai/veo-3.0-fast-generate-001" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.0-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Veo 3.0 Fast Generate" ], "families": [ "veo" ], "modes": [ "video_generation" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/veo-3.0-fast-generate-001", "modelKey": "google/veo-3.0-fast-generate-001", "displayName": "Veo 3.0 Fast Generate", "family": "veo", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.0-fast-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } } ] }, { "id": "google/veo-3.0-generate-001", "provider": "google", "model": "veo-3.0-generate-001", "displayName": "Veo 3.0", "family": "veo", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vertex_ai-video-models" ], "aliases": [ "vercel/google/veo-3.0-generate-001", "vertex_ai-video-models/vertex_ai/veo-3.0-generate-001" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.0-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Veo 3.0" ], "families": [ "veo" ], "modes": [ "video_generation" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/veo-3.0-generate-001", "modelKey": "google/veo-3.0-generate-001", "displayName": "Veo 3.0", "family": "veo", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.0-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } } ] }, { "id": "google/veo-3.1", "provider": "google", "model": "veo-3.1", "displayName": "Veo-3.1", "family": "veo", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/veo-3.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo-3.1" ], "families": [ "veo" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/veo-3.1", "modelKey": "google/veo-3.1", "displayName": "Veo-3.1", "family": "veo", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } } ] }, { "id": "google/veo-3.1-fast", "provider": "google", "model": "veo-3.1-fast", "displayName": "Veo-3.1-Fast", "family": "veo", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/google/veo-3.1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 480, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo-3.1-Fast" ], "families": [ "veo" ], "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "google/veo-3.1-fast", "modelKey": "google/veo-3.1-fast", "displayName": "Veo-3.1-Fast", "family": "veo", "metadata": { "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } } ] }, { "id": "google/veo-3.1-fast-generate-001", "provider": "google", "model": "veo-3.1-fast-generate-001", "displayName": "Veo 3.1 Fast Generate", "family": "veo", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "vercel", "vertex_ai-video-models" ], "aliases": [ "gemini/veo-3.1-fast-generate-001", "vercel/google/veo-3.1-fast-generate-001", "vertex_ai-video-models/vertex_ai/veo-3.1-fast-generate-001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-3.1-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.15 } }, { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-fast-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Veo 3.1 Fast Generate" ], "families": [ "veo" ], "modes": [ "video_generation" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/veo-3.1-fast-generate-001", "modelKey": "google/veo-3.1-fast-generate-001", "displayName": "Veo 3.1 Fast Generate", "family": "veo", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-3.1-fast-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-fast-generate-001", "mode": "video_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" } } ] }, { "id": "google/veo-3.1-fast-generate-preview", "provider": "google", "model": "veo-3.1-fast-generate-preview", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-video-models" ], "aliases": [ "gemini/veo-3.1-fast-generate-preview", "vertex_ai-video-models/vertex_ai/veo-3.1-fast-generate-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-3.1-fast-generate-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.15 } }, { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-fast-generate-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.15 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-3.1-fast-generate-preview", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-fast-generate-preview", "mode": "video_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" } } ] }, { "id": "google/veo-3.1-generate-001", "provider": "google", "model": "veo-3.1-generate-001", "displayName": "Veo 3.1", "family": "veo", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "gemini", "vercel", "vertex_ai-video-models" ], "aliases": [ "gemini/veo-3.1-generate-001", "vercel/google/veo-3.1-generate-001", "vertex_ai-video-models/vertex_ai/veo-3.1-generate-001" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-3.1-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.4 } }, { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-generate-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Veo 3.1" ], "families": [ "veo" ], "modes": [ "video_generation" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "google/veo-3.1-generate-001", "modelKey": "google/veo-3.1-generate-001", "displayName": "Veo 3.1", "family": "veo", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-3.1-generate-001", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-generate-001", "mode": "video_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" } } ] }, { "id": "google/veo-3.1-generate-preview", "provider": "google", "model": "veo-3.1-generate-preview", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "gemini", "vertex_ai-video-models" ], "aliases": [ "gemini/veo-3.1-generate-preview", "vertex_ai-video-models/vertex_ai/veo-3.1-generate-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-3.1-generate-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.4 } }, { "source": "litellm", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-generate-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.4 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-3.1-generate-preview", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-video-models", "model": "vertex_ai/veo-3.1-generate-preview", "mode": "video_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" } } ] }, { "id": "google/veo-3.1-lite-generate-preview", "provider": "google", "model": "veo-3.1-lite-generate-preview", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "gemini" ], "aliases": [ "gemini/veo-3.1-lite-generate-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gemini", "model": "gemini/veo-3.1-lite-generate-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.05 }, "perVideoSecond": { "output1080p": 0.08 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gemini", "model": "gemini/veo-3.1-lite-generate-preview", "mode": "video_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/video" } } ] }, { "id": "google/veo3.1", "provider": "google", "model": "veo3.1", "displayName": "Veo 3.1", "family": "veo", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/google/veo3.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo 3.1" ], "families": [ "veo" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/veo3.1", "modelKey": "google/veo3.1", "displayName": "Veo 3.1", "family": "veo", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "google/veo3.1-fast", "provider": "google", "model": "veo3.1-fast", "displayName": "Veo 3.1 Fast", "family": "veo", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/google/veo3.1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo 3.1 Fast" ], "families": [ "veo" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/veo3.1-fast", "modelKey": "google/veo3.1-fast", "displayName": "Veo 3.1 Fast", "family": "veo", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "google/veo3.1-lite", "provider": "google", "model": "veo3.1-lite", "displayName": "Veo 3.1 Lite", "family": "veo", "sources": [ "models.dev" ], "providers": [ "fastrouter" ], "aliases": [ "fastrouter/google/veo3.1-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Veo 3.1 Lite" ], "families": [ "veo" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "google/veo3.1-lite", "modelKey": "google/veo3.1-lite", "displayName": "Veo 3.1 Lite", "family": "veo", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "gradient-ai/alibaba-qwen3-32b", "provider": "gradient-ai", "model": "alibaba-qwen3-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/alibaba-qwen3-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/alibaba-qwen3-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/alibaba-qwen3-32b", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/anthropic-claude-3-opus", "provider": "gradient-ai", "model": "anthropic-claude-3-opus", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/anthropic-claude-3-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3-opus", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3-opus", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/anthropic-claude-3.5-haiku", "provider": "gradient-ai", "model": "anthropic-claude-3.5-haiku", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/anthropic-claude-3.5-haiku" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.5-haiku", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.5-haiku", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/anthropic-claude-3.5-sonnet", "provider": "gradient-ai", "model": "anthropic-claude-3.5-sonnet", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/anthropic-claude-3.5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.5-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.5-sonnet", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/anthropic-claude-3.7-sonnet", "provider": "gradient-ai", "model": "anthropic-claude-3.7-sonnet", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/anthropic-claude-3.7-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.7-sonnet", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/anthropic-claude-3.7-sonnet", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/llama3-8b-instruct", "provider": "gradient-ai", "model": "llama3-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/llama3-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/llama3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/llama3-8b-instruct", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/llama3.3-70b-instruct", "provider": "gradient-ai", "model": "llama3.3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/llama3.3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/llama3.3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.65 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/llama3.3-70b-instruct", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/openai-gpt-4o", "provider": "gradient-ai", "model": "openai-gpt-4o", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/openai-gpt-4o" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/openai-gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/openai-gpt-4o", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/openai-gpt-4o-mini", "provider": "gradient-ai", "model": "openai-gpt-4o-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/openai-gpt-4o-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/openai-gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/openai-gpt-4o-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/openai-o3", "provider": "gradient-ai", "model": "openai-o3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/openai-o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/openai-o3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/openai-o3", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "gradient-ai/openai-o3-mini", "provider": "gradient-ai", "model": "openai-o3-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "gradient_ai" ], "aliases": [ "gradient_ai/openai-o3-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/openai-o3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 4.4 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/openai-o3-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "groq/compound", "provider": "groq", "model": "compound", "displayName": "Compound", "family": "groq", "sources": [ "models.dev" ], "providers": [ "groq" ], "aliases": [ "groq/compound" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Compound" ], "families": [ "groq" ], "releaseDate": "2025-09-04", "lastUpdated": "2025-09-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "groq/compound", "modelKey": "groq/compound", "displayName": "Compound", "family": "groq", "metadata": { "lastUpdated": "2025-09-04", "openWeights": false, "releaseDate": "2025-09-04" } } ] }, { "id": "groq/compound-mini", "provider": "groq", "model": "compound-mini", "displayName": "Compound Mini", "family": "groq", "sources": [ "models.dev" ], "providers": [ "groq" ], "aliases": [ "groq/compound-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Compound Mini" ], "families": [ "groq" ], "releaseDate": "2025-09-04", "lastUpdated": "2025-09-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "groq/compound-mini", "modelKey": "groq/compound-mini", "displayName": "Compound Mini", "family": "groq", "metadata": { "lastUpdated": "2025-09-04", "openWeights": false, "releaseDate": "2025-09-04" } } ] }, { "id": "groq/gemma-7b-it", "provider": "groq", "model": "gemma-7b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "groq" ], "aliases": [ "groq/gemma-7b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "groq", "model": "groq/gemma-7b-it", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/gemma-7b-it", "mode": "chat" } ] }, { "id": "groq/orpheus-arabic-saudi", "provider": "groq", "model": "orpheus-arabic-saudi", "displayName": "Canopy Labs Orpheus Arabic Saudi", "family": "canopylabs", "sources": [ "models.dev" ], "providers": [ "groq" ], "aliases": [ "groq/canopylabs/orpheus-arabic-saudi" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Canopy Labs Orpheus Arabic Saudi" ], "families": [ "canopylabs" ], "statuses": [ "beta" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "canopylabs/orpheus-arabic-saudi", "modelKey": "canopylabs/orpheus-arabic-saudi", "displayName": "Canopy Labs Orpheus Arabic Saudi", "family": "canopylabs", "status": "beta", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "groq/orpheus-v1-english", "provider": "groq", "model": "orpheus-v1-english", "displayName": "Canopy Labs Orpheus V1 English", "family": "canopylabs", "sources": [ "models.dev" ], "providers": [ "groq" ], "aliases": [ "groq/canopylabs/orpheus-v1-english" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Canopy Labs Orpheus V1 English" ], "families": [ "canopylabs" ], "statuses": [ "beta" ], "releaseDate": "2025-12-19", "lastUpdated": "2025-12-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "canopylabs/orpheus-v1-english", "modelKey": "canopylabs/orpheus-v1-english", "displayName": "Canopy Labs Orpheus V1 English", "family": "canopylabs", "status": "beta", "metadata": { "lastUpdated": "2025-12-19", "openWeights": false, "releaseDate": "2025-12-19" } } ] }, { "id": "groq/playai-tts", "provider": "groq", "model": "playai-tts", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "groq" ], "aliases": [ "groq/playai-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 10000, "inputTokens": 10000, "maxTokens": 10000, "outputTokens": 10000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "groq", "model": "groq/playai-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00005 } } ] }, "metadata": { "modes": [ "audio_speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/playai-tts", "mode": "audio_speech" } ] }, { "id": "helicone/ernie-4.5-21b-a3b-thinking", "provider": "helicone", "model": "ernie-4.5-21b-a3b-thinking", "displayName": "Baidu Ernie 4.5 21B A3B Thinking", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/ernie-4.5-21b-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "ernie-4.5-21b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Baidu Ernie 4.5 21B A3B Thinking" ], "families": [ "ernie" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-03-16", "lastUpdated": "2025-03-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "ernie-4.5-21b-a3b-thinking", "modelKey": "ernie-4.5-21b-a3b-thinking", "displayName": "Baidu Ernie 4.5 21B A3B Thinking", "family": "ernie", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-03-16", "openWeights": false, "releaseDate": "2025-03-16" } } ] }, { "id": "helicone/gemma-3-12b-it", "provider": "helicone", "model": "gemma-3-12b-it", "displayName": "Google Gemma 3 12B", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/gemma-3-12b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049999999999999996, "output": 0.09999999999999999 } } ] }, "metadata": { "displayNames": [ "Google Gemma 3 12B" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-12", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemma-3-12b-it", "modelKey": "gemma-3-12b-it", "displayName": "Google Gemma 3 12B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "helicone/gemma2-9b-it", "provider": "helicone", "model": "gemma2-9b-it", "displayName": "Google Gemma 2", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/gemma2-9b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "gemma2-9b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Google Gemma 2" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-06", "releaseDate": "2024-06-25", "lastUpdated": "2024-06-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gemma2-9b-it", "modelKey": "gemma2-9b-it", "displayName": "Google Gemma 2", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-25", "openWeights": false, "releaseDate": "2024-06-25" } } ] }, { "id": "helicone/hermes-2-pro-llama-3-8b", "provider": "helicone", "model": "hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/hermes-2-pro-llama-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "hermes-2-pro-llama-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Hermes 2 Pro Llama 3 8B" ], "families": [ "llama" ], "knowledgeCutoff": "2024-05", "releaseDate": "2024-05-27", "lastUpdated": "2024-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "hermes-2-pro-llama-3-8b", "modelKey": "hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "family": "llama", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-05-27", "openWeights": false, "releaseDate": "2024-05-27" } } ] }, { "id": "helicone/o1", "provider": "helicone", "model": "o1", "displayName": "OpenAI: o1", "family": "o", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "OpenAI: o1" ], "families": [ "o" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o1", "modelKey": "o1", "displayName": "OpenAI: o1", "family": "o", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "helicone/o3", "provider": "helicone", "model": "o3", "displayName": "OpenAI o3", "family": "o", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "OpenAI o3" ], "families": [ "o" ], "knowledgeCutoff": "2024-06", "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o3", "modelKey": "o3", "displayName": "OpenAI o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "helicone/sonar", "provider": "helicone", "model": "sonar", "displayName": "Perplexity Sonar", "family": "sonar", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/sonar" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 127000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "Perplexity Sonar" ], "families": [ "sonar" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-27", "lastUpdated": "2025-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "sonar", "modelKey": "sonar", "displayName": "Perplexity Sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27" } } ] }, { "id": "huggingface/mimo-v2-flash", "provider": "huggingface", "model": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "huggingface" ], "aliases": [ "huggingface/XiaomiMiMo/MiMo-V2-Flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "huggingface", "model": "XiaomiMiMo/MiMo-V2-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "XiaomiMiMo/MiMo-V2-Flash", "modelKey": "XiaomiMiMo/MiMo-V2-Flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "openWeights": true, "releaseDate": "2025-12-16" } } ] }, { "id": "hyperbolic/hermes-3-llama-3.1-70b", "provider": "hyperbolic", "model": "hermes-3-llama-3.1-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "hyperbolic" ], "aliases": [ "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B", "mode": "chat" } ] }, { "id": "inception/mercury-2", "provider": "inception", "model": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "inception" ], "aliases": [ "inception/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 50000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inception", "model": "mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } }, { "source": "litellm", "provider": "inception", "model": "inception/mercury-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Mercury 2" ], "families": [ "mercury" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inception", "providerName": "Inception", "providerApi": "https://api.inceptionlabs.ai/v1/", "providerDoc": "https://platform.inceptionlabs.ai/docs", "model": "mercury-2", "modelKey": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "inception", "model": "inception/mercury-2", "mode": "chat" } ] }, { "id": "inception/mercury-edit-2", "provider": "inception", "model": "mercury-edit-2", "displayName": "Mercury Edit 2", "sources": [ "models.dev" ], "providers": [ "inception" ], "aliases": [ "inception/mercury-edit-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inception", "model": "mercury-edit-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Mercury Edit 2" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-03-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inception", "providerName": "Inception", "providerApi": "https://api.inceptionlabs.ai/v1/", "providerDoc": "https://platform.inceptionlabs.ai/docs", "model": "mercury-edit-2", "modelKey": "mercury-edit-2", "displayName": "Mercury Edit 2", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } } ] }, { "id": "inference/osmosis-structure-0.6b", "provider": "inference", "model": "osmosis-structure-0.6b", "displayName": "Osmosis Structure 0.6B", "family": "osmosis", "sources": [ "models.dev" ], "providers": [ "inference" ], "aliases": [ "inference/osmosis/osmosis-structure-0.6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inference", "model": "osmosis/osmosis-structure-0.6b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Osmosis Structure 0.6B" ], "families": [ "osmosis" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "osmosis/osmosis-structure-0.6b", "modelKey": "osmosis/osmosis-structure-0.6b", "displayName": "Osmosis Structure 0.6B", "family": "osmosis", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "jiekou/ernie-4.5-300b-a47b-paddle", "provider": "jiekou", "model": "ernie-4.5-300b-a47b-paddle", "displayName": "ERNIE 4.5 300B A47B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "jiekou" ], "aliases": [ "jiekou/baidu/ernie-4.5-300b-a47b-paddle" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "baidu/ernie-4.5-300b-a47b-paddle", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 300B A47B" ], "families": [ "ernie" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "baidu/ernie-4.5-300b-a47b-paddle", "modelKey": "baidu/ernie-4.5-300b-a47b-paddle", "displayName": "ERNIE 4.5 300B A47B", "family": "ernie", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } } ] }, { "id": "jiekou/ernie-4.5-vl-424b-a47b", "provider": "jiekou", "model": "ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "jiekou" ], "aliases": [ "jiekou/baidu/ernie-4.5-vl-424b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.42, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 VL 424B A47B" ], "families": [ "ernie" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "baidu/ernie-4.5-vl-424b-a47b", "modelKey": "baidu/ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "family": "ernie", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } } ] }, { "id": "jiekou/mimo-v2-flash", "provider": "jiekou", "model": "mimo-v2-flash", "displayName": "XiaomiMiMo/MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "jiekou" ], "aliases": [ "jiekou/xiaomimimo/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "xiaomimimo/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "XiaomiMiMo/MiMo-V2-Flash" ], "families": [ "mimo" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "xiaomimimo/mimo-v2-flash", "modelKey": "xiaomimimo/mimo-v2-flash", "displayName": "XiaomiMiMo/MiMo-V2-Flash", "family": "mimo", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } } ] }, { "id": "jiekou/o3", "provider": "jiekou", "model": "o3", "displayName": "o3", "sources": [ "models.dev" ], "providers": [ "jiekou" ], "aliases": [ "jiekou/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 40 } } ] }, "metadata": { "displayNames": [ "o3" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "o3", "modelKey": "o3", "displayName": "o3", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } } ] }, { "id": "jina-ai/jina-reranker-v2-base-multilingual", "provider": "jina-ai", "model": "jina-reranker-v2-base-multilingual", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "jina_ai" ], "aliases": [ "jina_ai/jina-reranker-v2-base-multilingual" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1024, "inputTokens": 1024, "maxDocumentChunksPerQuery": 2048, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "jina_ai", "model": "jina-reranker-v2-base-multilingual", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.018, "output": 0.018 }, "extra": { "max_document_chunks_per_query": 2048 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "jina_ai", "model": "jina-reranker-v2-base-multilingual", "mode": "rerank" } ] }, { "id": "kilo/aion-1.0", "provider": "kilo", "model": "aion-1.0", "displayName": "AionLabs: Aion-1.0", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/aion-labs/aion-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "aion-labs/aion-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4, "output": 8 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-1.0" ], "releaseDate": "2025-02-05", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "aion-labs/aion-1.0", "modelKey": "aion-labs/aion-1.0", "displayName": "AionLabs: Aion-1.0", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-02-05" } } ] }, { "id": "kilo/aion-1.0-mini", "provider": "kilo", "model": "aion-1.0-mini", "displayName": "AionLabs: Aion-1.0-Mini", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/aion-labs/aion-1.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "aion-labs/aion-1.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-1.0-Mini" ], "releaseDate": "2025-02-05", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "aion-labs/aion-1.0-mini", "modelKey": "aion-labs/aion-1.0-mini", "displayName": "AionLabs: Aion-1.0-Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-02-05" } } ] }, { "id": "kilo/aion-2.0", "provider": "kilo", "model": "aion-2.0", "displayName": "AionLabs: Aion-2.0", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/aion-labs/aion-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "aion-labs/aion-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-2.0" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "aion-labs/aion-2.0", "modelKey": "aion-labs/aion-2.0", "displayName": "AionLabs: Aion-2.0", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-24" } } ] }, { "id": "kilo/aion-rp-llama-3.1-8b", "provider": "kilo", "model": "aion-rp-llama-3.1-8b", "displayName": "AionLabs: Aion-RP 1.0 (8B)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/aion-labs/aion-rp-llama-3.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "aion-labs/aion-rp-llama-3.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-RP 1.0 (8B)" ], "releaseDate": "2025-02-05", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "aion-labs/aion-rp-llama-3.1-8b", "modelKey": "aion-labs/aion-rp-llama-3.1-8b", "displayName": "AionLabs: Aion-RP 1.0 (8B)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-02-05" } } ] }, { "id": "kilo/auto", "provider": "kilo", "model": "auto", "displayName": "Auto Router", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/openrouter/auto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openrouter/auto", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Auto Router" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openrouter/auto", "modelKey": "openrouter/auto", "displayName": "Auto Router", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "kilo/balanced", "provider": "kilo", "model": "balanced", "displayName": "Kilo Auto Balanced", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/kilo-auto/balanced" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "kilo-auto/balanced", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } } ] }, "metadata": { "displayNames": [ "Kilo Auto Balanced" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "kilo-auto/balanced", "modelKey": "kilo-auto/balanced", "displayName": "Kilo Auto Balanced", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "kilo/bodybuilder", "provider": "kilo", "model": "bodybuilder", "displayName": "Body Builder (beta)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/openrouter/bodybuilder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openrouter/bodybuilder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Body Builder (beta)" ], "statuses": [ "beta" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openrouter/bodybuilder", "modelKey": "openrouter/bodybuilder", "displayName": "Body Builder (beta)", "status": "beta", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "kilo/cobuddy:free", "provider": "kilo", "model": "cobuddy:free", "displayName": "Baidu: CoBuddy (free)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/cobuddy:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/cobuddy:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Baidu: CoBuddy (free)" ], "releaseDate": "2026-05-06", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/cobuddy:free", "modelKey": "baidu/cobuddy:free", "displayName": "Baidu: CoBuddy (free)", "metadata": { "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-06" } } ] }, { "id": "kilo/coder-large", "provider": "kilo", "model": "coder-large", "displayName": "Arcee AI: Coder Large", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/coder-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/coder-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Coder Large" ], "releaseDate": "2025-05-06", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/coder-large", "modelKey": "arcee-ai/coder-large", "displayName": "Arcee AI: Coder Large", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-05-06" } } ] }, { "id": "kilo/cogito-v2.1-671b", "provider": "kilo", "model": "cogito-v2.1-671b", "displayName": "Deep Cogito: Cogito v2.1 671B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/deepcogito/cogito-v2.1-671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "deepcogito/cogito-v2.1-671b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Deep Cogito: Cogito v2.1 671B" ], "releaseDate": "2025-11-14", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "deepcogito/cogito-v2.1-671b", "modelKey": "deepcogito/cogito-v2.1-671b", "displayName": "Deep Cogito: Cogito v2.1 671B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-11-14" } } ] }, { "id": "kilo/cydonia-24b-v4.1", "provider": "kilo", "model": "cydonia-24b-v4.1", "displayName": "TheDrummer: Cydonia 24B V4.1", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/thedrummer/cydonia-24b-v4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "thedrummer/cydonia-24b-v4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "TheDrummer: Cydonia 24B V4.1" ], "releaseDate": "2025-09-27", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "thedrummer/cydonia-24b-v4.1", "modelKey": "thedrummer/cydonia-24b-v4.1", "displayName": "TheDrummer: Cydonia 24B V4.1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-27" } } ] }, { "id": "kilo/ernie-4.5-21b-a3b", "provider": "kilo", "model": "ernie-4.5-21b-a3b", "displayName": "Baidu: ERNIE 4.5 21B A3B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/ernie-4.5-21b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/ernie-4.5-21b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 21B A3B" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/ernie-4.5-21b-a3b", "modelKey": "baidu/ernie-4.5-21b-a3b", "displayName": "Baidu: ERNIE 4.5 21B A3B", "metadata": { "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "kilo/ernie-4.5-21b-a3b-thinking", "provider": "kilo", "model": "ernie-4.5-21b-a3b-thinking", "displayName": "Baidu: ERNIE 4.5 21B A3B Thinking", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/ernie-4.5-21b-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/ernie-4.5-21b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 21B A3B Thinking" ], "releaseDate": "2025-09-19", "lastUpdated": "2025-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/ernie-4.5-21b-a3b-thinking", "modelKey": "baidu/ernie-4.5-21b-a3b-thinking", "displayName": "Baidu: ERNIE 4.5 21B A3B Thinking", "metadata": { "lastUpdated": "2025-09-19", "openWeights": true, "releaseDate": "2025-09-19" } } ] }, { "id": "kilo/ernie-4.5-300b-a47b", "provider": "kilo", "model": "ernie-4.5-300b-a47b", "displayName": "Baidu: ERNIE 4.5 300B A47B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/ernie-4.5-300b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/ernie-4.5-300b-a47b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 300B A47B" ], "releaseDate": "2025-06-30", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/ernie-4.5-300b-a47b", "modelKey": "baidu/ernie-4.5-300b-a47b", "displayName": "Baidu: ERNIE 4.5 300B A47B", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "kilo/ernie-4.5-vl-28b-a3b", "provider": "kilo", "model": "ernie-4.5-vl-28b-a3b", "displayName": "Baidu: ERNIE 4.5 VL 28B A3B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/ernie-4.5-vl-28b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 30000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/ernie-4.5-vl-28b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.56 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 VL 28B A3B" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/ernie-4.5-vl-28b-a3b", "modelKey": "baidu/ernie-4.5-vl-28b-a3b", "displayName": "Baidu: ERNIE 4.5 VL 28B A3B", "metadata": { "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "kilo/ernie-4.5-vl-424b-a47b", "provider": "kilo", "model": "ernie-4.5-vl-424b-a47b", "displayName": "Baidu: ERNIE 4.5 VL 424B A47B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/ernie-4.5-vl-424b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.42, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 VL 424B A47B" ], "releaseDate": "2025-06-30", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/ernie-4.5-vl-424b-a47b", "modelKey": "baidu/ernie-4.5-vl-424b-a47b", "displayName": "Baidu: ERNIE 4.5 VL 424B A47B", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "kilo/free", "provider": "kilo", "model": "free", "displayName": "Kilo Auto Free", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/kilo-auto/free", "kilo/openrouter/free" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "kilo-auto/free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "openrouter/free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Free Models Router", "Kilo Auto Free" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "kilo-auto/free", "modelKey": "kilo-auto/free", "displayName": "Kilo Auto Free", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openrouter/free", "modelKey": "openrouter/free", "displayName": "Free Models Router", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-01" } } ] }, { "id": "kilo/frontier", "provider": "kilo", "model": "frontier", "displayName": "Kilo Auto Frontier", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/kilo-auto/frontier" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "kilo-auto/frontier", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "Kilo Auto Frontier" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "kilo-auto/frontier", "modelKey": "kilo-auto/frontier", "displayName": "Kilo Auto Frontier", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "kilo/granite-4.0-h-micro", "provider": "kilo", "model": "granite-4.0-h-micro", "displayName": "IBM: Granite 4.0 Micro", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/ibm-granite/granite-4.0-h-micro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "ibm-granite/granite-4.0-h-micro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.017, "output": 0.11 } } ] }, "metadata": { "displayNames": [ "IBM: Granite 4.0 Micro" ], "releaseDate": "2025-10-20", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "ibm-granite/granite-4.0-h-micro", "modelKey": "ibm-granite/granite-4.0-h-micro", "displayName": "IBM: Granite 4.0 Micro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-10-20" } } ] }, { "id": "kilo/granite-4.1-8b", "provider": "kilo", "model": "granite-4.1-8b", "displayName": "IBM: Granite 4.1 8B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/ibm-granite/granite-4.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "ibm-granite/granite-4.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "IBM: Granite 4.1 8B" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "ibm-granite/granite-4.1-8b", "modelKey": "ibm-granite/granite-4.1-8b", "displayName": "IBM: Granite 4.1 8B", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "kilo/hermes-2-pro-llama-3-8b", "provider": "kilo", "model": "hermes-2-pro-llama-3-8b", "displayName": "NousResearch: Hermes 2 Pro - Llama-3 8B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nousresearch/hermes-2-pro-llama-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nousresearch/hermes-2-pro-llama-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "NousResearch: Hermes 2 Pro - Llama-3 8B" ], "releaseDate": "2024-05-27", "lastUpdated": "2024-06-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nousresearch/hermes-2-pro-llama-3-8b", "modelKey": "nousresearch/hermes-2-pro-llama-3-8b", "displayName": "NousResearch: Hermes 2 Pro - Llama-3 8B", "metadata": { "lastUpdated": "2024-06-27", "openWeights": true, "releaseDate": "2024-05-27" } } ] }, { "id": "kilo/hermes-3-llama-3.1-405b", "provider": "kilo", "model": "hermes-3-llama-3.1-405b", "displayName": "Nous: Hermes 3 405B Instruct", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nousresearch/hermes-3-llama-3.1-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nousresearch/hermes-3-llama-3.1-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "Nous: Hermes 3 405B Instruct" ], "releaseDate": "2024-08-16", "lastUpdated": "2024-08-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nousresearch/hermes-3-llama-3.1-405b", "modelKey": "nousresearch/hermes-3-llama-3.1-405b", "displayName": "Nous: Hermes 3 405B Instruct", "metadata": { "lastUpdated": "2024-08-16", "openWeights": true, "releaseDate": "2024-08-16" } } ] }, { "id": "kilo/hermes-3-llama-3.1-70b", "provider": "kilo", "model": "hermes-3-llama-3.1-70b", "displayName": "Nous: Hermes 3 70B Instruct", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nousresearch/hermes-3-llama-3.1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nousresearch/hermes-3-llama-3.1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Nous: Hermes 3 70B Instruct" ], "releaseDate": "2024-08-18", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nousresearch/hermes-3-llama-3.1-70b", "modelKey": "nousresearch/hermes-3-llama-3.1-70b", "displayName": "Nous: Hermes 3 70B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-08-18" } } ] }, { "id": "kilo/hermes-4-405b", "provider": "kilo", "model": "hermes-4-405b", "displayName": "Nous: Hermes 4 405B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nousresearch/hermes-4-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 26215, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nousresearch/hermes-4-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Nous: Hermes 4 405B" ], "releaseDate": "2025-08-25", "lastUpdated": "2025-08-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nousresearch/hermes-4-405b", "modelKey": "nousresearch/hermes-4-405b", "displayName": "Nous: Hermes 4 405B", "metadata": { "lastUpdated": "2025-08-25", "openWeights": true, "releaseDate": "2025-08-25", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "kilo/hermes-4-70b", "provider": "kilo", "model": "hermes-4-70b", "displayName": "Nous: Hermes 4 70B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nousresearch/hermes-4-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nousresearch/hermes-4-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "input": 0.13, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Nous: Hermes 4 70B" ], "releaseDate": "2025-08-25", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nousresearch/hermes-4-70b", "modelKey": "nousresearch/hermes-4-70b", "displayName": "Nous: Hermes 4 70B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-08-25", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "kilo/hunyuan-a13b-instruct", "provider": "kilo", "model": "hunyuan-a13b-instruct", "displayName": "Tencent: Hunyuan A13B Instruct", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/tencent/hunyuan-a13b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "tencent/hunyuan-a13b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "Tencent: Hunyuan A13B Instruct" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "tencent/hunyuan-a13b-instruct", "modelKey": "tencent/hunyuan-a13b-instruct", "displayName": "Tencent: Hunyuan A13B Instruct", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-06-30" } } ] }, { "id": "kilo/hy3-preview", "provider": "kilo", "model": "hy3-preview", "displayName": "Tencent: Hy3 Preview", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/tencent/hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "tencent/hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.029, "input": 0.066, "output": 0.26 } } ] }, "metadata": { "displayNames": [ "Tencent: Hy3 Preview" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-05-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "tencent/hy3-preview", "modelKey": "tencent/hy3-preview", "displayName": "Tencent: Hy3 Preview", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "high" ] } ] } } ] }, { "id": "kilo/inflection-3-pi", "provider": "kilo", "model": "inflection-3-pi", "displayName": "Inflection: Inflection 3 Pi", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inflection/inflection-3-pi" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inflection/inflection-3-pi", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Inflection: Inflection 3 Pi" ], "releaseDate": "2024-10-11", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inflection/inflection-3-pi", "modelKey": "inflection/inflection-3-pi", "displayName": "Inflection: Inflection 3 Pi", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-10-11" } } ] }, { "id": "kilo/inflection-3-productivity", "provider": "kilo", "model": "inflection-3-productivity", "displayName": "Inflection: Inflection 3 Productivity", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inflection/inflection-3-productivity" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inflection/inflection-3-productivity", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Inflection: Inflection 3 Productivity" ], "releaseDate": "2024-10-11", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inflection/inflection-3-productivity", "modelKey": "inflection/inflection-3-productivity", "displayName": "Inflection: Inflection 3 Productivity", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-10-11" } } ] }, { "id": "kilo/intellect-3", "provider": "kilo", "model": "intellect-3", "displayName": "Prime Intellect: INTELLECT-3", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/prime-intellect/intellect-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "prime-intellect/intellect-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "Prime Intellect: INTELLECT-3" ], "releaseDate": "2025-11-26", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "prime-intellect/intellect-3", "modelKey": "prime-intellect/intellect-3", "displayName": "Prime Intellect: INTELLECT-3", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-11-26" } } ] }, { "id": "kilo/kat-coder-pro-v2", "provider": "kilo", "model": "kat-coder-pro-v2", "displayName": "Kwaipilot: KAT-Coder-Pro V2", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/kwaipilot/kat-coder-pro-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "kwaipilot/kat-coder-pro-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Kwaipilot: KAT-Coder-Pro V2" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "kwaipilot/kat-coder-pro-v2", "modelKey": "kwaipilot/kat-coder-pro-v2", "displayName": "Kwaipilot: KAT-Coder-Pro V2", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-27" } } ] }, { "id": "kilo/l3-euryale-70b", "provider": "kilo", "model": "l3-euryale-70b", "displayName": "Sao10k: Llama 3 Euryale 70B v2.1", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/sao10k/l3-euryale-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "sao10k/l3-euryale-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.48, "output": 1.48 } } ] }, "metadata": { "displayNames": [ "Sao10k: Llama 3 Euryale 70B v2.1" ], "releaseDate": "2024-06-18", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "sao10k/l3-euryale-70b", "modelKey": "sao10k/l3-euryale-70b", "displayName": "Sao10k: Llama 3 Euryale 70B v2.1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-06-18" } } ] }, { "id": "kilo/l3-lunaris-8b", "provider": "kilo", "model": "l3-lunaris-8b", "displayName": "Sao10K: Llama 3 8B Lunaris", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/sao10k/l3-lunaris-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "sao10k/l3-lunaris-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "Sao10K: Llama 3 8B Lunaris" ], "releaseDate": "2024-08-13", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "sao10k/l3-lunaris-8b", "modelKey": "sao10k/l3-lunaris-8b", "displayName": "Sao10K: Llama 3 8B Lunaris", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-08-13" } } ] }, { "id": "kilo/l3.1-70b-hanami-x1", "provider": "kilo", "model": "l3.1-70b-hanami-x1", "displayName": "Sao10K: Llama 3.1 70B Hanami x1", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/sao10k/l3.1-70b-hanami-x1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "sao10k/l3.1-70b-hanami-x1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "displayNames": [ "Sao10K: Llama 3.1 70B Hanami x1" ], "releaseDate": "2025-01-08", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "sao10k/l3.1-70b-hanami-x1", "modelKey": "sao10k/l3.1-70b-hanami-x1", "displayName": "Sao10K: Llama 3.1 70B Hanami x1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-01-08" } } ] }, { "id": "kilo/l3.1-euryale-70b", "provider": "kilo", "model": "l3.1-euryale-70b", "displayName": "Sao10K: Llama 3.1 Euryale 70B v2.2", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/sao10k/l3.1-euryale-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "sao10k/l3.1-euryale-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "Sao10K: Llama 3.1 Euryale 70B v2.2" ], "releaseDate": "2024-08-28", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "sao10k/l3.1-euryale-70b", "modelKey": "sao10k/l3.1-euryale-70b", "displayName": "Sao10K: Llama 3.1 Euryale 70B v2.2", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-08-28" } } ] }, { "id": "kilo/l3.3-euryale-70b", "provider": "kilo", "model": "l3.3-euryale-70b", "displayName": "Sao10K: Llama 3.3 Euryale 70B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/sao10k/l3.3-euryale-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "sao10k/l3.3-euryale-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Sao10K: Llama 3.3 Euryale 70B" ], "releaseDate": "2024-12-18", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "sao10k/l3.3-euryale-70b", "modelKey": "sao10k/l3.3-euryale-70b", "displayName": "Sao10K: Llama 3.3 Euryale 70B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-12-18" } } ] }, { "id": "kilo/laguna-m.1:free", "provider": "kilo", "model": "laguna-m.1:free", "displayName": "Poolside: Laguna M.1 (free)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/poolside/laguna-m.1:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "poolside/laguna-m.1:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Poolside: Laguna M.1 (free)" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "poolside/laguna-m.1:free", "modelKey": "poolside/laguna-m.1:free", "displayName": "Poolside: Laguna M.1 (free)", "metadata": { "lastUpdated": "2026-06-13", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "kilo/laguna-xs.2:free", "provider": "kilo", "model": "laguna-xs.2:free", "displayName": "Poolside: Laguna XS.2 (free)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/poolside/laguna-xs.2:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "poolside/laguna-xs.2:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Poolside: Laguna XS.2 (free)" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "poolside/laguna-xs.2:free", "modelKey": "poolside/laguna-xs.2:free", "displayName": "Poolside: Laguna XS.2 (free)", "metadata": { "lastUpdated": "2026-06-13", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "kilo/lfm-2-24b-a2b", "provider": "kilo", "model": "lfm-2-24b-a2b", "displayName": "LiquidAI: LFM2-24B-A2B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/liquid/lfm-2-24b-a2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "liquid/lfm-2-24b-a2b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "LiquidAI: LFM2-24B-A2B" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "liquid/lfm-2-24b-a2b", "modelKey": "liquid/lfm-2-24b-a2b", "displayName": "LiquidAI: LFM2-24B-A2B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-26" } } ] }, { "id": "kilo/ling-2.6-1t", "provider": "kilo", "model": "ling-2.6-1t", "displayName": "inclusionAI: Ling-2.6-1T", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inclusionai/ling-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inclusionai/ling-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "inclusionAI: Ling-2.6-1T" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-05-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inclusionai/ling-2.6-1t", "modelKey": "inclusionai/ling-2.6-1t", "displayName": "inclusionAI: Ling-2.6-1T", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "kilo/ling-2.6-flash", "provider": "kilo", "model": "ling-2.6-flash", "displayName": "inclusionAI: Ling-2.6 Flash", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inclusionai/ling-2.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inclusionai/ling-2.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.016, "input": 0.08, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "inclusionAI: Ling-2.6 Flash" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inclusionai/ling-2.6-flash", "modelKey": "inclusionai/ling-2.6-flash", "displayName": "inclusionAI: Ling-2.6 Flash", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-21" } } ] }, { "id": "kilo/maestro-reasoning", "provider": "kilo", "model": "maestro-reasoning", "displayName": "Arcee AI: Maestro Reasoning", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/maestro-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/maestro-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 3.3 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Maestro Reasoning" ], "releaseDate": "2025-05-06", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/maestro-reasoning", "modelKey": "arcee-ai/maestro-reasoning", "displayName": "Arcee AI: Maestro Reasoning", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-05-06" } } ] }, { "id": "kilo/magnum-v4-72b", "provider": "kilo", "model": "magnum-v4-72b", "displayName": "Magnum v4 72B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/anthracite-org/magnum-v4-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "anthracite-org/magnum-v4-72b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 5 } } ] }, "metadata": { "displayNames": [ "Magnum v4 72B" ], "releaseDate": "2024-10-22", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "anthracite-org/magnum-v4-72b", "modelKey": "anthracite-org/magnum-v4-72b", "displayName": "Magnum v4 72B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-10-22" } } ] }, { "id": "kilo/mercury-2", "provider": "kilo", "model": "mercury-2", "displayName": "Inception: Mercury 2", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inception/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inception/mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Inception: Mercury 2" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inception/mercury-2", "modelKey": "inception/mercury-2", "displayName": "Inception: Mercury 2", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "kilo/mimo-v2-flash", "provider": "kilo", "model": "mimo-v2-flash", "displayName": "Xiaomi: MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "xiaomi/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.045, "input": 0.09, "output": 0.29 } } ] }, "metadata": { "displayNames": [ "Xiaomi: MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "xiaomi/mimo-v2-flash", "modelKey": "xiaomi/mimo-v2-flash", "displayName": "Xiaomi: MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16" } } ] }, { "id": "kilo/mimo-v2-omni", "provider": "kilo", "model": "mimo-v2-omni", "displayName": "Xiaomi: MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/xiaomi/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "xiaomi/mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Xiaomi: MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "xiaomi/mimo-v2-omni", "modelKey": "xiaomi/mimo-v2-omni", "displayName": "Xiaomi: MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "kilo/mimo-v2-pro", "provider": "kilo", "model": "mimo-v2-pro", "displayName": "Xiaomi: MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/xiaomi/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "xiaomi/mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Xiaomi: MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "xiaomi/mimo-v2-pro", "modelKey": "xiaomi/mimo-v2-pro", "displayName": "Xiaomi: MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "kilo/mimo-v2.5", "provider": "kilo", "model": "mimo-v2.5", "displayName": "Xiaomi: MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 }, "tiered": { "contextOver200K": { "input": 0.8, "output": 4, "cache_read": 0.16 }, "tiers": [ { "input": 0.8, "output": 4, "cache_read": 0.16, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Xiaomi: MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "xiaomi/mimo-v2.5", "modelKey": "xiaomi/mimo-v2.5", "displayName": "Xiaomi: MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "kilo/mimo-v2.5-pro", "provider": "kilo", "model": "mimo-v2.5-pro", "displayName": "Xiaomi: MiMo V2.5 Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "Xiaomi: MiMo V2.5 Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "xiaomi/mimo-v2.5-pro", "modelKey": "xiaomi/mimo-v2.5-pro", "displayName": "Xiaomi: MiMo V2.5 Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "kilo/morph-v3-fast", "provider": "kilo", "model": "morph-v3-fast", "displayName": "Morph: Morph V3 Fast", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/morph/morph-v3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 81920, "outputTokens": 38000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "morph/morph-v3-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Morph: Morph V3 Fast" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "morph/morph-v3-fast", "modelKey": "morph/morph-v3-fast", "displayName": "Morph: Morph V3 Fast", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } } ] }, { "id": "kilo/morph-v3-large", "provider": "kilo", "model": "morph-v3-large", "displayName": "Morph: Morph V3 Large", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/morph/morph-v3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "morph/morph-v3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Morph: Morph V3 Large" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "morph/morph-v3-large", "modelKey": "morph/morph-v3-large", "displayName": "Morph: Morph V3 Large", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } } ] }, { "id": "kilo/mythomax-l2-13b", "provider": "kilo", "model": "mythomax-l2-13b", "displayName": "MythoMax 13B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/gryphe/mythomax-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "gryphe/mythomax-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.06 } } ] }, "metadata": { "displayNames": [ "MythoMax 13B" ], "releaseDate": "2024-04-25", "lastUpdated": "2024-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "gryphe/mythomax-l2-13b", "modelKey": "gryphe/mythomax-l2-13b", "displayName": "MythoMax 13B", "metadata": { "lastUpdated": "2024-04-25", "openWeights": true, "releaseDate": "2024-04-25" } } ] }, { "id": "kilo/nemotron-3-nano-30b-a3b", "provider": "kilo", "model": "nemotron-3-nano-30b-a3b", "displayName": "NVIDIA: Nemotron 3 Nano 30B A3B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nvidia/nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 52429, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Nano 30B A3B" ], "families": [ "nemotron" ], "releaseDate": "2024-12", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/nemotron-3-nano-30b-a3b", "modelKey": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "NVIDIA: Nemotron 3 Nano 30B A3B", "family": "nemotron", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2024-12" } } ] }, { "id": "kilo/nemotron-3-nano-omni-30b-a3b-reasoning:free", "provider": "kilo", "model": "nemotron-3-nano-omni-30b-a3b-reasoning:free", "displayName": "NVIDIA: Nemotron 3 Nano Omni (free)", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Nano Omni (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "modelKey": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "displayName": "NVIDIA: Nemotron 3 Nano Omni (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "kilo/nemotron-3-super-120b-a12b", "provider": "kilo", "model": "nemotron-3-super-120b-a12b", "displayName": "NVIDIA: Nemotron 3 Super", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.1, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Super" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "NVIDIA: Nemotron 3 Super", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "kilo/nemotron-3-super-120b-a12b:free", "provider": "kilo", "model": "nemotron-3-super-120b-a12b:free", "displayName": "NVIDIA: Nemotron 3 Super (free)", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nvidia/nemotron-3-super-120b-a12b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/nemotron-3-super-120b-a12b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Super (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-03-12", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/nemotron-3-super-120b-a12b:free", "modelKey": "nvidia/nemotron-3-super-120b-a12b:free", "displayName": "NVIDIA: Nemotron 3 Super (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-03-12" } } ] }, { "id": "kilo/nemotron-nano-9b-v2", "provider": "kilo", "model": "nemotron-nano-9b-v2", "displayName": "NVIDIA: Nemotron Nano 9B V2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/nvidia/nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 26215, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/nemotron-nano-9b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron Nano 9B V2" ], "families": [ "nemotron" ], "releaseDate": "2025-08-18", "lastUpdated": "2025-08-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/nemotron-nano-9b-v2", "modelKey": "nvidia/nemotron-nano-9b-v2", "displayName": "NVIDIA: Nemotron Nano 9B V2", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-18", "openWeights": true, "releaseDate": "2025-08-18" } } ] }, { "id": "kilo/olmo-3-32b-think", "provider": "kilo", "model": "olmo-3-32b-think", "displayName": "AllenAI: Olmo 3 32B Think", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/allenai/olmo-3-32b-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "allenai/olmo-3-32b-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "AllenAI: Olmo 3 32B Think" ], "releaseDate": "2025-11-22", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "allenai/olmo-3-32b-think", "modelKey": "allenai/olmo-3-32b-think", "displayName": "AllenAI: Olmo 3 32B Think", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-11-22" } } ] }, { "id": "kilo/owl-alpha", "provider": "kilo", "model": "owl-alpha", "displayName": "Owl Alpha", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/openrouter/owl-alpha" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openrouter/owl-alpha", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Owl Alpha" ], "statuses": [ "alpha" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openrouter/owl-alpha", "modelKey": "openrouter/owl-alpha", "displayName": "Owl Alpha", "status": "alpha", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "kilo/palmyra-x5", "provider": "kilo", "model": "palmyra-x5", "displayName": "Writer: Palmyra X5", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/writer/palmyra-x5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1040000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "writer/palmyra-x5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 6 } } ] }, "metadata": { "displayNames": [ "Writer: Palmyra X5" ], "releaseDate": "2025-04-28", "lastUpdated": "2025-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "writer/palmyra-x5", "modelKey": "writer/palmyra-x5", "displayName": "Writer: Palmyra X5", "metadata": { "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2025-04-28" } } ] }, { "id": "kilo/pareto-code", "provider": "kilo", "model": "pareto-code", "displayName": "Pareto Code Router", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/openrouter/pareto-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openrouter/pareto-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Pareto Code Router" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openrouter/pareto-code", "modelKey": "openrouter/pareto-code", "displayName": "Pareto Code Router", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-21" } } ] }, { "id": "kilo/perceptron-mk1", "provider": "kilo", "model": "perceptron-mk1", "displayName": "Perceptron: Perceptron Mk1", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/perceptron/perceptron-mk1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "perceptron/perceptron-mk1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Perceptron: Perceptron Mk1" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perceptron/perceptron-mk1", "modelKey": "perceptron/perceptron-mk1", "displayName": "Perceptron: Perceptron Mk1", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "kilo/phi-4", "provider": "kilo", "model": "phi-4", "displayName": "Microsoft: Phi 4", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/microsoft/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "microsoft/phi-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Microsoft: Phi 4" ], "releaseDate": "2024-12-11", "lastUpdated": "2024-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "microsoft/phi-4", "modelKey": "microsoft/phi-4", "displayName": "Microsoft: Phi 4", "metadata": { "lastUpdated": "2024-12-11", "openWeights": true, "releaseDate": "2024-12-11" } } ] }, { "id": "kilo/phi-4-mini-instruct", "provider": "kilo", "model": "phi-4-mini-instruct", "displayName": "Microsoft: Phi 4 Mini Instruct", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/microsoft/phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "microsoft/phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.08, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "Microsoft: Phi 4 Mini Instruct" ], "releaseDate": "2025-10-17", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "microsoft/phi-4-mini-instruct", "modelKey": "microsoft/phi-4-mini-instruct", "displayName": "Microsoft: Phi 4 Mini Instruct", "metadata": { "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-10-17" } } ] }, { "id": "kilo/qianfan-ocr-fast", "provider": "kilo", "model": "qianfan-ocr-fast", "displayName": "Baidu: Qianfan-OCR-Fast", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/baidu/qianfan-ocr-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 28672, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "baidu/qianfan-ocr-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.68, "output": 2.81 } } ] }, "metadata": { "displayNames": [ "Baidu: Qianfan-OCR-Fast" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-05-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "baidu/qianfan-ocr-fast", "modelKey": "baidu/qianfan-ocr-fast", "displayName": "Baidu: Qianfan-OCR-Fast", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-04-20" } } ] }, { "id": "kilo/reka-edge", "provider": "kilo", "model": "reka-edge", "displayName": "Reka Edge", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/rekaai/reka-edge" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "rekaai/reka-edge", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Reka Edge" ], "releaseDate": "2026-03-20", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "rekaai/reka-edge", "modelKey": "rekaai/reka-edge", "displayName": "Reka Edge", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-20" } } ] }, { "id": "kilo/reka-flash-3", "provider": "kilo", "model": "reka-flash-3", "displayName": "Reka Flash 3", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/rekaai/reka-flash-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "rekaai/reka-flash-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Reka Flash 3" ], "releaseDate": "2025-03-12", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "rekaai/reka-flash-3", "modelKey": "rekaai/reka-flash-3", "displayName": "Reka Flash 3", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2025-03-12" } } ] }, { "id": "kilo/relace-apply-3", "provider": "kilo", "model": "relace-apply-3", "displayName": "Relace: Relace Apply 3", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/relace/relace-apply-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "relace/relace-apply-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Relace: Relace Apply 3" ], "releaseDate": "2025-09-26", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "relace/relace-apply-3", "modelKey": "relace/relace-apply-3", "displayName": "Relace: Relace Apply 3", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-09-26" } } ] }, { "id": "kilo/relace-search", "provider": "kilo", "model": "relace-search", "displayName": "Relace: Relace Search", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/relace/relace-search" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "relace/relace-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Relace: Relace Search" ], "releaseDate": "2025-12-09", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "relace/relace-search", "modelKey": "relace/relace-search", "displayName": "Relace: Relace Search", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-12-09" } } ] }, { "id": "kilo/remm-slerp-l2-13b", "provider": "kilo", "model": "remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/undi95/remm-slerp-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 6144, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "undi95/remm-slerp-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "ReMM SLERP 13B" ], "releaseDate": "2023-07-22", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "undi95/remm-slerp-l2-13b", "modelKey": "undi95/remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2023-07-22" } } ] }, { "id": "kilo/ring-2.6-1t", "provider": "kilo", "model": "ring-2.6-1t", "displayName": "inclusionAI: Ring-2.6-1T", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/inclusionai/ring-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.075, "output": 0.625 } } ] }, "metadata": { "displayNames": [ "inclusionAI: Ring-2.6-1T" ], "releaseDate": "2026-05-08", "lastUpdated": "2026-05-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "inclusionai/ring-2.6-1t", "modelKey": "inclusionai/ring-2.6-1t", "displayName": "inclusionAI: Ring-2.6-1T", "metadata": { "lastUpdated": "2026-05-16", "openWeights": false, "releaseDate": "2026-05-08" } } ] }, { "id": "kilo/rnj-1-instruct", "provider": "kilo", "model": "rnj-1-instruct", "displayName": "EssentialAI: Rnj 1 Instruct", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/essentialai/rnj-1-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 6554, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "essentialai/rnj-1-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "EssentialAI: Rnj 1 Instruct" ], "releaseDate": "2025-12-05", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "essentialai/rnj-1-instruct", "modelKey": "essentialai/rnj-1-instruct", "displayName": "EssentialAI: Rnj 1 Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-05" } } ] }, { "id": "kilo/rocinante-12b", "provider": "kilo", "model": "rocinante-12b", "displayName": "TheDrummer: Rocinante 12B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/thedrummer/rocinante-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "thedrummer/rocinante-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.43 } } ] }, "metadata": { "displayNames": [ "TheDrummer: Rocinante 12B" ], "releaseDate": "2024-09-30", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "thedrummer/rocinante-12b", "modelKey": "thedrummer/rocinante-12b", "displayName": "TheDrummer: Rocinante 12B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-09-30" } } ] }, { "id": "kilo/router", "provider": "kilo", "model": "router", "displayName": "Switchpoint Router", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/switchpoint/router" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "switchpoint/router", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 3.4 } } ] }, "metadata": { "displayNames": [ "Switchpoint Router" ], "releaseDate": "2025-07-12", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "switchpoint/router", "modelKey": "switchpoint/router", "displayName": "Switchpoint Router", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-07-12" } } ] }, { "id": "kilo/seed-1.6", "provider": "kilo", "model": "seed-1.6", "displayName": "ByteDance Seed: Seed 1.6", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/bytedance-seed/seed-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "bytedance-seed/seed-1.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed 1.6" ], "releaseDate": "2025-09", "lastUpdated": "2025-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "bytedance-seed/seed-1.6", "modelKey": "bytedance-seed/seed-1.6", "displayName": "ByteDance Seed: Seed 1.6", "metadata": { "lastUpdated": "2025-09", "openWeights": false, "releaseDate": "2025-09" } } ] }, { "id": "kilo/seed-1.6-flash", "provider": "kilo", "model": "seed-1.6-flash", "displayName": "ByteDance Seed: Seed 1.6 Flash", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/bytedance-seed/seed-1.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "bytedance-seed/seed-1.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed 1.6 Flash" ], "releaseDate": "2025-12-23", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "bytedance-seed/seed-1.6-flash", "modelKey": "bytedance-seed/seed-1.6-flash", "displayName": "ByteDance Seed: Seed 1.6 Flash", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-23" } } ] }, { "id": "kilo/seed-2.0-lite", "provider": "kilo", "model": "seed-2.0-lite", "displayName": "ByteDance Seed: Seed-2.0-Lite", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/bytedance-seed/seed-2.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "bytedance-seed/seed-2.0-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed-2.0-Lite" ], "releaseDate": "2026-03-10", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "bytedance-seed/seed-2.0-lite", "modelKey": "bytedance-seed/seed-2.0-lite", "displayName": "ByteDance Seed: Seed-2.0-Lite", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-03-10" } } ] }, { "id": "kilo/seed-2.0-mini", "provider": "kilo", "model": "seed-2.0-mini", "displayName": "ByteDance Seed: Seed-2.0-Mini", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/bytedance-seed/seed-2.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "bytedance-seed/seed-2.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed-2.0-Mini" ], "releaseDate": "2026-02-27", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "bytedance-seed/seed-2.0-mini", "modelKey": "bytedance-seed/seed-2.0-mini", "displayName": "ByteDance Seed: Seed-2.0-Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-27" } } ] }, { "id": "kilo/skyfall-36b-v2", "provider": "kilo", "model": "skyfall-36b-v2", "displayName": "TheDrummer: Skyfall 36B V2", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/thedrummer/skyfall-36b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "thedrummer/skyfall-36b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "TheDrummer: Skyfall 36B V2" ], "releaseDate": "2025-03-11", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "thedrummer/skyfall-36b-v2", "modelKey": "thedrummer/skyfall-36b-v2", "displayName": "TheDrummer: Skyfall 36B V2", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-11" } } ] }, { "id": "kilo/small", "provider": "kilo", "model": "small", "displayName": "Kilo Auto Small", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/kilo-auto/small" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "kilo-auto/small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Kilo Auto Small" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "kilo-auto/small", "modelKey": "kilo-auto/small", "displayName": "Kilo Auto Small", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "kilo/solar-pro-3", "provider": "kilo", "model": "solar-pro-3", "displayName": "Upstage: Solar Pro 3", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/upstage/solar-pro-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "upstage/solar-pro-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Upstage: Solar Pro 3" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "upstage/solar-pro-3", "modelKey": "upstage/solar-pro-3", "displayName": "Upstage: Solar Pro 3", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-01-27" } } ] }, { "id": "kilo/spotlight", "provider": "kilo", "model": "spotlight", "displayName": "Arcee AI: Spotlight", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/spotlight" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65537, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/spotlight", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Spotlight" ], "releaseDate": "2025-05-06", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/spotlight", "modelKey": "arcee-ai/spotlight", "displayName": "Arcee AI: Spotlight", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-05-06" } } ] }, { "id": "kilo/step-3.5-flash", "provider": "kilo", "model": "step-3.5-flash", "displayName": "StepFun: Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "stepfun/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "StepFun: Step 3.5 Flash" ], "releaseDate": "2026-01-29", "lastUpdated": "2026-01-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "stepfun/step-3.5-flash", "modelKey": "stepfun/step-3.5-flash", "displayName": "StepFun: Step 3.5 Flash", "metadata": { "lastUpdated": "2026-01-29", "openWeights": true, "releaseDate": "2026-01-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "kilo/trinity-large-thinking", "provider": "kilo", "model": "trinity-large-thinking", "displayName": "Arcee AI: Trinity Large Thinking", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Trinity Large Thinking" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/trinity-large-thinking", "modelKey": "arcee-ai/trinity-large-thinking", "displayName": "Arcee AI: Trinity Large Thinking", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-01" } } ] }, { "id": "kilo/trinity-mini", "provider": "kilo", "model": "trinity-mini", "displayName": "Arcee AI: Trinity Mini", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/trinity-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/trinity-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Trinity Mini" ], "releaseDate": "2025-12", "lastUpdated": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/trinity-mini", "modelKey": "arcee-ai/trinity-mini", "displayName": "Arcee AI: Trinity Mini", "metadata": { "lastUpdated": "2026-01-28", "openWeights": true, "releaseDate": "2025-12" } } ] }, { "id": "kilo/ui-tars-1.5-7b", "provider": "kilo", "model": "ui-tars-1.5-7b", "displayName": "ByteDance: UI-TARS 7B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/bytedance/ui-tars-1.5-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "bytedance/ui-tars-1.5-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "ByteDance: UI-TARS 7B" ], "releaseDate": "2025-07-23", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "bytedance/ui-tars-1.5-7b", "modelKey": "bytedance/ui-tars-1.5-7b", "displayName": "ByteDance: UI-TARS 7B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-07-23" } } ] }, { "id": "kilo/unslopnemo-12b", "provider": "kilo", "model": "unslopnemo-12b", "displayName": "TheDrummer: UnslopNemo 12B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/thedrummer/unslopnemo-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "thedrummer/unslopnemo-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "TheDrummer: UnslopNemo 12B" ], "releaseDate": "2024-11-09", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "thedrummer/unslopnemo-12b", "modelKey": "thedrummer/unslopnemo-12b", "displayName": "TheDrummer: UnslopNemo 12B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-11-09" } } ] }, { "id": "kilo/virtuoso-large", "provider": "kilo", "model": "virtuoso-large", "displayName": "Arcee AI: Virtuoso Large", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/arcee-ai/virtuoso-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "arcee-ai/virtuoso-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Virtuoso Large" ], "releaseDate": "2025-05-06", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "arcee-ai/virtuoso-large", "modelKey": "arcee-ai/virtuoso-large", "displayName": "Arcee AI: Virtuoso Large", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-05-06" } } ] }, { "id": "kilo/weaver", "provider": "kilo", "model": "weaver", "displayName": "Mancer: Weaver (alpha)", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/mancer/weaver" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mancer/weaver", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 1 } } ] }, "metadata": { "displayNames": [ "Mancer: Weaver (alpha)" ], "releaseDate": "2023-08-02", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mancer/weaver", "modelKey": "mancer/weaver", "displayName": "Mancer: Weaver (alpha)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2023-08-02" } } ] }, { "id": "kilo/wizardlm-2-8x22b", "provider": "kilo", "model": "wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/microsoft/wizardlm-2-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65535, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "microsoft/wizardlm-2-8x22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.62, "output": 0.62 } } ] }, "metadata": { "displayNames": [ "WizardLM-2 8x22B" ], "releaseDate": "2024-04-24", "lastUpdated": "2024-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "microsoft/wizardlm-2-8x22b", "modelKey": "microsoft/wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "metadata": { "lastUpdated": "2024-04-24", "openWeights": true, "releaseDate": "2024-04-24" } } ] }, { "id": "kimi-for-coding/k2p5", "provider": "kimi-for-coding", "model": "k2p5", "displayName": "Kimi K2.5", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "kimi-for-coding" ], "aliases": [ "kimi-for-coding/k2p5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kimi-for-coding", "model": "k2p5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5" ], "families": [ "kimi-thinking" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kimi-for-coding", "providerName": "Kimi For Coding", "providerApi": "https://api.kimi.com/coding/v1", "providerDoc": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html", "model": "k2p5", "modelKey": "k2p5", "displayName": "Kimi K2.5", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "kimi-for-coding/k2p6", "provider": "kimi-for-coding", "model": "k2p6", "displayName": "Kimi K2.6", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "kimi-for-coding" ], "aliases": [ "kimi-for-coding/k2p6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kimi-for-coding", "model": "k2p6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6" ], "families": [ "kimi-thinking" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04", "lastUpdated": "2026-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kimi-for-coding", "providerName": "Kimi For Coding", "providerApi": "https://api.kimi.com/coding/v1", "providerDoc": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html", "model": "k2p6", "modelKey": "k2p6", "displayName": "Kimi K2.6", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04", "openWeights": true, "releaseDate": "2026-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "kimi-for-coding/k2p7", "provider": "kimi-for-coding", "model": "k2p7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "kimi-for-coding" ], "aliases": [ "kimi-for-coding/k2p7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kimi-for-coding", "model": "k2p7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kimi-for-coding", "providerName": "Kimi For Coding", "providerApi": "https://api.kimi.com/coding/v1", "providerDoc": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html", "model": "k2p7", "modelKey": "k2p7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "lambda-ai/hermes3-405b", "provider": "lambda-ai", "model": "hermes3-405b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/hermes3-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/hermes3-405b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/hermes3-405b", "mode": "chat" } ] }, { "id": "lambda-ai/hermes3-70b", "provider": "lambda-ai", "model": "hermes3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/hermes3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/hermes3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/hermes3-70b", "mode": "chat" } ] }, { "id": "lambda-ai/hermes3-8b", "provider": "lambda-ai", "model": "hermes3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/hermes3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/hermes3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0.04 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/hermes3-8b", "mode": "chat" } ] }, { "id": "lambda-ai/lfm-40b", "provider": "lambda-ai", "model": "lfm-40b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/lfm-40b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/lfm-40b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/lfm-40b", "mode": "chat" } ] }, { "id": "lambda-ai/lfm-7b", "provider": "lambda-ai", "model": "lfm-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/lfm-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/lfm-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0.04 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/lfm-7b", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.1-405b-instruct-fp8", "provider": "lambda-ai", "model": "llama3.1-405b-instruct-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.1-405b-instruct-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-405b-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-405b-instruct-fp8", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.1-70b-instruct-fp8", "provider": "lambda-ai", "model": "llama3.1-70b-instruct-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.1-70b-instruct-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-70b-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-70b-instruct-fp8", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.1-8b-instruct", "provider": "lambda-ai", "model": "llama3.1-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.1-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.025, "output": 0.04 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-8b-instruct", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.1-nemotron-70b-instruct-fp8", "provider": "lambda-ai", "model": "llama3.1-nemotron-70b-instruct-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.1-nemotron-70b-instruct-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-nemotron-70b-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.1-nemotron-70b-instruct-fp8", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.2-11b-vision-instruct", "provider": "lambda-ai", "model": "llama3.2-11b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.2-11b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.2-11b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.015, "output": 0.025 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.2-11b-vision-instruct", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.2-3b-instruct", "provider": "lambda-ai", "model": "llama3.2-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.2-3b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.2-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.015, "output": 0.025 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.2-3b-instruct", "mode": "chat" } ] }, { "id": "lambda-ai/llama3.3-70b-instruct-fp8", "provider": "lambda-ai", "model": "llama3.3-70b-instruct-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lambda_ai" ], "aliases": [ "lambda_ai/llama3.3-70b-instruct-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama3.3-70b-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama3.3-70b-instruct-fp8", "mode": "chat" } ] }, { "id": "lemonade/gemma-3-4b-it-gguf", "provider": "lemonade", "model": "gemma-3-4b-it-gguf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lemonade" ], "aliases": [ "lemonade/Gemma-3-4b-it-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lemonade", "model": "lemonade/Gemma-3-4b-it-GGUF", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lemonade", "model": "lemonade/Gemma-3-4b-it-GGUF", "mode": "chat" } ] }, { "id": "linkup/search", "provider": "linkup", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "linkup" ], "aliases": [ "linkup/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "linkup", "model": "linkup/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.00587 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "linkup", "model": "linkup/search", "mode": "search" } ] }, { "id": "linkup/search-deep", "provider": "linkup", "model": "search-deep", "mode": "search", "sources": [ "litellm" ], "providers": [ "linkup" ], "aliases": [ "linkup/search-deep" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "linkup", "model": "linkup/search-deep", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.05867 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "linkup", "model": "linkup/search-deep", "mode": "search" } ] }, { "id": "llamagate/dolphin3-8b", "provider": "llamagate", "model": "dolphin3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/dolphin3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/dolphin3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/dolphin3-8b", "mode": "chat" } ] }, { "id": "llamagate/gemma3-4b", "provider": "llamagate", "model": "gemma3-4b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/gemma3-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/gemma3-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.08 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/gemma3-4b", "mode": "chat" } ] }, { "id": "llamagate/llava-7b", "provider": "llamagate", "model": "llava-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/llava-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/llava-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/llava-7b", "mode": "chat" } ] }, { "id": "llamagate/nomic-embed-text", "provider": "llamagate", "model": "nomic-embed-text", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/nomic-embed-text" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/nomic-embed-text", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/nomic-embed-text", "mode": "embedding" } ] }, { "id": "llamagate/openthinker-7b", "provider": "llamagate", "model": "openthinker-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/openthinker-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/openthinker-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/openthinker-7b", "mode": "chat" } ] }, { "id": "llmgateway/auto", "provider": "llmgateway", "model": "auto", "displayName": "Auto Route", "family": "auto", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/auto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "auto", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Auto Route" ], "families": [ "auto" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "auto", "modelKey": "auto", "displayName": "Auto Route", "family": "auto", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "llmgateway/custom", "provider": "llmgateway", "model": "custom", "displayName": "Custom Model", "family": "auto", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/custom" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "custom", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Custom Model" ], "families": [ "auto" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "custom", "modelKey": "custom", "displayName": "Custom Model", "family": "auto", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "llmgateway/gemma-2-27b-it-together", "provider": "llmgateway", "model": "gemma-2-27b-it-together", "displayName": "Gemma 2 27B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/gemma-2-27b-it-together" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "gemma-2-27b-it-together", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.08 } } ] }, "metadata": { "displayNames": [ "Gemma 2 27B IT" ], "families": [ "gemma" ], "releaseDate": "2024-06-27", "lastUpdated": "2024-06-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemma-2-27b-it-together", "modelKey": "gemma-2-27b-it-together", "displayName": "Gemma 2 27B IT", "family": "gemma", "metadata": { "lastUpdated": "2024-06-27", "openWeights": true, "releaseDate": "2024-06-27" } } ] }, { "id": "llmgateway/gemma-3-1b-it", "provider": "llmgateway", "model": "gemma-3-1b-it", "displayName": "Gemma 3 1B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/gemma-3-1b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "gemma-3-1b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Gemma 3 1B IT" ], "families": [ "gemma" ], "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemma-3-1b-it", "modelKey": "gemma-3-1b-it", "displayName": "Gemma 3 1B IT", "family": "gemma", "metadata": { "lastUpdated": "2025-03-12", "openWeights": true, "releaseDate": "2025-03-12" } } ] }, { "id": "llmgateway/gemma-3-27b", "provider": "llmgateway", "model": "gemma-3-27b", "displayName": "Gemma 3 27B", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/gemma-3-27b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "gemma-3-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.27 } } ] }, "metadata": { "displayNames": [ "Gemma 3 27B" ], "families": [ "gemma" ], "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gemma-3-27b", "modelKey": "gemma-3-27b", "displayName": "Gemma 3 27B", "family": "gemma", "metadata": { "lastUpdated": "2025-03-12", "openWeights": true, "releaseDate": "2025-03-12" } } ] }, { "id": "llmgateway/hermes-2-pro-llama-3-8b", "provider": "llmgateway", "model": "hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "family": "hermes", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/hermes-2-pro-llama-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "hermes-2-pro-llama-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Hermes 2 Pro Llama 3 8B" ], "families": [ "hermes" ], "releaseDate": "2024-05-27", "lastUpdated": "2024-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "hermes-2-pro-llama-3-8b", "modelKey": "hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "family": "hermes", "metadata": { "lastUpdated": "2024-05-27", "openWeights": true, "releaseDate": "2024-05-27" } } ] }, { "id": "llmgateway/mimo-v2-flash", "provider": "llmgateway", "model": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mimo-v2-flash", "modelKey": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "llmgateway/mimo-v2-omni", "provider": "llmgateway", "model": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "llmgateway/mimo-v2-pro", "provider": "llmgateway", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "llmgateway/mimo-v2.5", "provider": "llmgateway", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 }, "tiered": { "contextOver200K": { "input": 0.8, "output": 4, "cache_read": 0.16 }, "tiers": [ { "input": 0.8, "output": 4, "cache_read": 0.16, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "llmgateway/mimo-v2.5-pro", "provider": "llmgateway", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "llmgateway/nemotron-3-ultra-550b", "provider": "llmgateway", "model": "nemotron-3-ultra-550b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/nemotron-3-ultra-550b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "nemotron-3-ultra-550b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Ultra 550B A55B" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "nemotron-3-ultra-550b", "modelKey": "nemotron-3-ultra-550b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "llmgateway/o1", "provider": "llmgateway", "model": "o1", "displayName": "o1", "family": "o", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "o1" ], "families": [ "o" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "o1", "modelKey": "o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05" } } ] }, { "id": "llmgateway/o3", "provider": "llmgateway", "model": "o3", "displayName": "o3", "family": "o", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/o3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "o3" ], "families": [ "o" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "o3", "modelKey": "o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } } ] }, { "id": "llmgateway/seed-1-6-250615", "provider": "llmgateway", "model": "seed-1-6-250615", "displayName": "Seed 1.6 (250615)", "family": "seed", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/seed-1-6-250615" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "seed-1-6-250615", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "Seed 1.6 (250615)" ], "families": [ "seed" ], "releaseDate": "2025-06-25", "lastUpdated": "2025-06-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "seed-1-6-250615", "modelKey": "seed-1-6-250615", "displayName": "Seed 1.6 (250615)", "family": "seed", "metadata": { "lastUpdated": "2025-06-25", "openWeights": true, "releaseDate": "2025-06-25" } } ] }, { "id": "llmgateway/seed-1-6-250915", "provider": "llmgateway", "model": "seed-1-6-250915", "displayName": "Seed 1.6 (250915)", "family": "seed", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/seed-1-6-250915" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "seed-1-6-250915", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "Seed 1.6 (250915)" ], "families": [ "seed" ], "releaseDate": "2025-09-15", "lastUpdated": "2025-09-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "seed-1-6-250915", "modelKey": "seed-1-6-250915", "displayName": "Seed 1.6 (250915)", "family": "seed", "metadata": { "lastUpdated": "2025-09-15", "openWeights": true, "releaseDate": "2025-09-15" } } ] }, { "id": "llmgateway/seed-1-6-flash-250715", "provider": "llmgateway", "model": "seed-1-6-flash-250715", "displayName": "Seed 1.6 Flash (250715)", "family": "seed", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/seed-1-6-flash-250715" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "seed-1-6-flash-250715", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.07, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Seed 1.6 Flash (250715)" ], "families": [ "seed" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "seed-1-6-flash-250715", "modelKey": "seed-1-6-flash-250715", "displayName": "Seed 1.6 Flash (250715)", "family": "seed", "metadata": { "lastUpdated": "2025-07-26", "openWeights": true, "releaseDate": "2025-07-26" } } ] }, { "id": "llmgateway/seed-1-8-251228", "provider": "llmgateway", "model": "seed-1-8-251228", "displayName": "Seed 1.8 (251228)", "family": "seed", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/seed-1-8-251228" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "seed-1-8-251228", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "Seed 1.8 (251228)" ], "families": [ "seed" ], "releaseDate": "2025-12-18", "lastUpdated": "2025-12-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "seed-1-8-251228", "modelKey": "seed-1-8-251228", "displayName": "Seed 1.8 (251228)", "family": "seed", "metadata": { "lastUpdated": "2025-12-18", "openWeights": true, "releaseDate": "2025-12-18" } } ] }, { "id": "llmgateway/sonar", "provider": "llmgateway", "model": "sonar", "displayName": "Sonar", "family": "sonar", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/sonar" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "Sonar" ], "families": [ "sonar" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2024-01-01", "lastUpdated": "2025-09-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "sonar", "modelKey": "sonar", "displayName": "Sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "llmtr/gemma-4", "provider": "llmtr", "model": "gemma-4", "displayName": "Gemma 4", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/gemma-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "gemma-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Gemma 4" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "gemma-4", "modelKey": "gemma-4", "displayName": "Gemma 4", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "llmtr/magibu-11b-v8", "provider": "llmtr", "model": "magibu-11b-v8", "displayName": "Magibu 11B v8", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/magibu-11b-v8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "magibu-11b-v8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Magibu 11B v8" ], "releaseDate": "2026-06-05", "lastUpdated": "2026-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "magibu-11b-v8", "modelKey": "magibu-11b-v8", "displayName": "Magibu 11B v8", "metadata": { "lastUpdated": "2026-06-05", "openWeights": false, "releaseDate": "2026-06-05" } } ] }, { "id": "llmtr/medgemma-4b", "provider": "llmtr", "model": "medgemma-4b", "displayName": "MedGemma 4B", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/medgemma-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "medgemma-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 5 } } ] }, "metadata": { "displayNames": [ "MedGemma 4B" ], "releaseDate": "2026-04-26", "lastUpdated": "2026-04-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "medgemma-4b", "modelKey": "medgemma-4b", "displayName": "MedGemma 4B", "metadata": { "lastUpdated": "2026-04-26", "openWeights": true, "releaseDate": "2026-04-26" } } ] }, { "id": "llmtr/sincap", "provider": "llmtr", "model": "sincap", "displayName": "Sincap", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/sincap" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "sincap", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Sincap" ], "releaseDate": "2026-05-05", "lastUpdated": "2026-05-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "sincap", "modelKey": "sincap", "displayName": "Sincap", "metadata": { "lastUpdated": "2026-05-05", "openWeights": false, "releaseDate": "2026-05-05" } } ] }, { "id": "llmtr/trendyol-7b", "provider": "llmtr", "model": "trendyol-7b", "displayName": "Trendyol 7B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "llmtr" ], "aliases": [ "llmtr/trendyol-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmtr", "model": "trendyol-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Trendyol 7B" ], "families": [ "qwen" ], "releaseDate": "2026-06-06", "lastUpdated": "2026-06-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmtr", "providerName": "LLMTR", "providerApi": "https://llmtr.com/v1", "providerDoc": "https://llmtr.com/docs", "model": "trendyol-7b", "modelKey": "trendyol-7b", "displayName": "Trendyol 7B", "family": "qwen", "metadata": { "lastUpdated": "2026-06-06", "openWeights": true, "releaseDate": "2026-06-06" } } ] }, { "id": "lucidquery/lucidnova-rf1-100b", "provider": "lucidquery", "model": "lucidnova-rf1-100b", "displayName": "LucidNova RF1 100B", "family": "nova", "sources": [ "models.dev" ], "providers": [ "lucidquery" ], "aliases": [ "lucidquery/lucidnova-rf1-100b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lucidquery", "model": "lucidnova-rf1-100b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "displayNames": [ "LucidNova RF1 100B" ], "families": [ "nova" ], "knowledgeCutoff": "2025-09-16", "releaseDate": "2024-12-28", "lastUpdated": "2025-09-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lucidquery", "providerName": "LucidQuery", "providerApi": "https://api.lucidquery.com/v1", "providerDoc": "https://lucidquery.com/docs", "model": "lucidnova-rf1-100b", "modelKey": "lucidnova-rf1-100b", "displayName": "LucidNova RF1 100B", "family": "nova", "metadata": { "knowledgeCutoff": "2025-09-16", "lastUpdated": "2025-09-10", "openWeights": false, "releaseDate": "2024-12-28" } } ] }, { "id": "lucidquery/lucidquery-agi-01-frontier", "provider": "lucidquery", "model": "lucidquery-agi-01-frontier", "displayName": "AGI-01 Frontier", "family": "agi", "sources": [ "models.dev" ], "providers": [ "lucidquery" ], "aliases": [ "lucidquery/lucidquery-agi-01-frontier" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "outputTokens": 120000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lucidquery", "model": "lucidquery-agi-01-frontier", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.5, "output": 22 } } ] }, "metadata": { "displayNames": [ "AGI-01 Frontier" ], "families": [ "agi" ], "knowledgeCutoff": "2026-06-05", "releaseDate": "2026-06-16", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lucidquery", "providerName": "LucidQuery", "providerApi": "https://api.lucidquery.com/v1", "providerDoc": "https://lucidquery.com/docs", "model": "lucidquery-agi-01-frontier", "modelKey": "lucidquery-agi-01-frontier", "displayName": "AGI-01 Frontier", "family": "agi", "metadata": { "knowledgeCutoff": "2026-06-05", "lastUpdated": "2026-06-16", "openWeights": false, "releaseDate": "2026-06-16" } } ] }, { "id": "lucidquery/lucidquery-agi-01-swift", "provider": "lucidquery", "model": "lucidquery-agi-01-swift", "displayName": "AGI-01 Swift", "family": "agi", "sources": [ "models.dev" ], "providers": [ "lucidquery" ], "aliases": [ "lucidquery/lucidquery-agi-01-swift" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "outputTokens": 120000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lucidquery", "model": "lucidquery-agi-01-swift", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 15 } } ] }, "metadata": { "displayNames": [ "AGI-01 Swift" ], "families": [ "agi" ], "knowledgeCutoff": "2026-06-05", "releaseDate": "2026-06-16", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lucidquery", "providerName": "LucidQuery", "providerApi": "https://api.lucidquery.com/v1", "providerDoc": "https://lucidquery.com/docs", "model": "lucidquery-agi-01-swift", "modelKey": "lucidquery-agi-01-swift", "displayName": "AGI-01 Swift", "family": "agi", "metadata": { "knowledgeCutoff": "2026-06-05", "lastUpdated": "2026-06-16", "openWeights": false, "releaseDate": "2026-06-16" } } ] }, { "id": "lucidquery/lucidquery-nexus-coder", "provider": "lucidquery", "model": "lucidquery-nexus-coder", "displayName": "LucidQuery Nexus Coder", "family": "lucid", "sources": [ "models.dev" ], "providers": [ "lucidquery" ], "aliases": [ "lucidquery/lucidquery-nexus-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 250000, "outputTokens": 60000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "lucidquery", "model": "lucidquery-nexus-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "displayNames": [ "LucidQuery Nexus Coder" ], "families": [ "lucid" ], "knowledgeCutoff": "2025-08-01", "releaseDate": "2025-09-01", "lastUpdated": "2025-09-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lucidquery", "providerName": "LucidQuery", "providerApi": "https://api.lucidquery.com/v1", "providerDoc": "https://lucidquery.com/docs", "model": "lucidquery-nexus-coder", "modelKey": "lucidquery-nexus-coder", "displayName": "LucidQuery Nexus Coder", "family": "lucid", "metadata": { "knowledgeCutoff": "2025-08-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2025-09-01" } } ] }, { "id": "meganova/mimo-v2-flash", "provider": "meganova", "model": "mimo-v2-flash", "displayName": "MiMo V2 Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "meganova" ], "aliases": [ "meganova/XiaomiMiMo/MiMo-V2-Flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "meganova", "model": "XiaomiMiMo/MiMo-V2-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "XiaomiMiMo/MiMo-V2-Flash", "modelKey": "XiaomiMiMo/MiMo-V2-Flash", "displayName": "MiMo V2 Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2025-12-17", "openWeights": true, "releaseDate": "2025-12-17" } } ] }, { "id": "meta-llama/cerebras-llama-4-maverick-17b-128e-instruct", "provider": "meta-llama", "model": "cerebras-llama-4-maverick-17b-128e-instruct", "displayName": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llama" ], "aliases": [ "llama/cerebras-llama-4-maverick-17b-128e-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llama", "model": "cerebras-llama-4-maverick-17b-128e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cerebras-Llama-4-Maverick-17B-128E-Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "cerebras-llama-4-maverick-17b-128e-instruct", "modelKey": "cerebras-llama-4-maverick-17b-128e-instruct", "displayName": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "meta-llama/cerebras-llama-4-scout-17b-16e-instruct", "provider": "meta-llama", "model": "cerebras-llama-4-scout-17b-16e-instruct", "displayName": "Cerebras-Llama-4-Scout-17B-16E-Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llama" ], "aliases": [ "llama/cerebras-llama-4-scout-17b-16e-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llama", "model": "cerebras-llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Cerebras-Llama-4-Scout-17B-16E-Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "cerebras-llama-4-scout-17b-16e-instruct", "modelKey": "cerebras-llama-4-scout-17b-16e-instruct", "displayName": "Cerebras-Llama-4-Scout-17B-16E-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "meta-llama/codellama", "provider": "meta-llama", "model": "codellama", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/codellama" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/codellama", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/codellama", "mode": "completion" } ] }, { "id": "meta-llama/codellama-34b-instruct", "provider": "meta-llama", "model": "codellama-34b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/togethercomputer/CodeLlama-34b-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/togethercomputer/CodeLlama-34b-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/togethercomputer/CodeLlama-34b-Instruct", "mode": "chat" } ] }, { "id": "meta-llama/codellama-34b-instruct-hf", "provider": "meta-llama", "model": "codellama-34b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/codellama/CodeLlama-34b-Instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/codellama/CodeLlama-34b-Instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/codellama/CodeLlama-34b-Instruct-hf", "mode": "chat" } ] }, { "id": "meta-llama/codellama-70b-instruct-hf", "provider": "meta-llama", "model": "codellama-70b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/codellama/CodeLlama-70b-Instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/codellama/CodeLlama-70b-Instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/codellama/CodeLlama-70b-Instruct-hf", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" } } ] }, { "id": "meta-llama/codellama-7b", "provider": "meta-llama", "model": "codellama-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/codellama-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/codellama-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.12 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/codellama-7b", "mode": "chat" } ] }, { "id": "meta-llama/codellama-7b-instruct-awq", "provider": "meta-llama", "model": "codellama-7b-instruct-awq", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cloudflare" ], "aliases": [ "cloudflare/@hf/thebloke/codellama-7b-instruct-awq" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cloudflare", "model": "cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.923, "output": 1.923 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cloudflare", "model": "cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "mode": "chat" } ] }, { "id": "meta-llama/codellama-7b-instruct-solidity", "provider": "meta-llama", "model": "codellama-7b-instruct-solidity", "displayName": "AlfredPros: CodeLLaMa 7B Instruct Solidity", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/alfredpros/codellama-7b-instruct-solidity" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "alfredpros/codellama-7b-instruct-solidity", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "AlfredPros: CodeLLaMa 7B Instruct Solidity" ], "releaseDate": "2025-04-14", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "alfredpros/codellama-7b-instruct-solidity", "modelKey": "alfredpros/codellama-7b-instruct-solidity", "displayName": "AlfredPros: CodeLLaMa 7B Instruct Solidity", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-04-14" } } ] }, { "id": "meta-llama/esm2-650m", "provider": "meta-llama", "model": "esm2-650m", "displayName": "esm2-650m", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/meta/esm2-650m" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "meta/esm2-650m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "esm2-650m" ], "releaseDate": "2024-08-29", "lastUpdated": "2025-03-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/esm2-650m", "modelKey": "meta/esm2-650m", "displayName": "esm2-650m", "metadata": { "lastUpdated": "2025-03-10", "openWeights": true, "releaseDate": "2024-08-29" } } ] }, { "id": "meta-llama/esmfold", "provider": "meta-llama", "model": "esmfold", "displayName": "esmfold", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/meta/esmfold" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "meta/esmfold", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "esmfold" ], "releaseDate": "2024-03-15", "lastUpdated": "2025-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/esmfold", "modelKey": "meta/esmfold", "displayName": "esmfold", "metadata": { "lastUpdated": "2025-06-12", "openWeights": true, "releaseDate": "2024-03-15" } } ] }, { "id": "meta-llama/groq-llama-4-maverick-17b-128e-instruct", "provider": "meta-llama", "model": "groq-llama-4-maverick-17b-128e-instruct", "displayName": "Groq-Llama-4-Maverick-17B-128E-Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llama" ], "aliases": [ "llama/groq-llama-4-maverick-17b-128e-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llama", "model": "groq-llama-4-maverick-17b-128e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Groq-Llama-4-Maverick-17B-128E-Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "groq-llama-4-maverick-17b-128e-instruct", "modelKey": "groq-llama-4-maverick-17b-128e-instruct", "displayName": "Groq-Llama-4-Maverick-17B-128E-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "meta-llama/llama-2-13b", "provider": "meta-llama", "model": "llama-2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-13b", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-13b-chat", "provider": "meta-llama", "model": "llama-2-13b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-13b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-13b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-13b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-13b-chat-hf", "provider": "meta-llama", "model": "llama-2-13b-chat-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/meta-llama/Llama-2-13b-chat-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-13b-chat-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-13b-chat-hf", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-70b", "provider": "meta-llama", "model": "llama-2-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-70b", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-70b-chat", "provider": "meta-llama", "model": "llama-2-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 2.75 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-70b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-70b-chat-hf", "provider": "meta-llama", "model": "llama-2-70b-chat-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/meta-llama/Llama-2-70b-chat-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-70b-chat-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-70b-chat-hf", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-7b", "provider": "meta-llama", "model": "llama-2-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-7b", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-7b-chat", "provider": "meta-llama", "model": "llama-2-7b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/meta/llama-2-7b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-2-7b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-2-7b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-7b-chat-fp16", "provider": "meta-llama", "model": "llama-2-7b-chat-fp16", "displayName": "Llama 2 7B Chat FP16", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare", "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-2-7b-chat-fp16", "cloudflare/@cf/meta/llama-2-7b-chat-fp16" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 3072, "maxTokens": 3072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-2-7b-chat-fp16", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.56, "output": 6.67 } }, { "source": "litellm", "provider": "cloudflare", "model": "cloudflare/@cf/meta/llama-2-7b-chat-fp16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.923, "output": 1.923 } } ] }, "metadata": { "displayNames": [ "Llama 2 7B Chat FP16" ], "families": [ "llama" ], "modes": [ "chat" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-2-7b-chat-fp16", "modelKey": "workers-ai/@cf/meta/llama-2-7b-chat-fp16", "displayName": "Llama 2 7B Chat FP16", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cloudflare", "model": "cloudflare/@cf/meta/llama-2-7b-chat-fp16", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-7b-chat-hf", "provider": "meta-llama", "model": "llama-2-7b-chat-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "anyscale" ], "aliases": [ "anyscale/meta-llama/Llama-2-7b-chat-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-7b-chat-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/meta-llama/Llama-2-7b-chat-hf", "mode": "chat" } ] }, { "id": "meta-llama/llama-2-7b-chat-int8", "provider": "meta-llama", "model": "llama-2-7b-chat-int8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "cloudflare" ], "aliases": [ "cloudflare/@cf/meta/llama-2-7b-chat-int8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "cloudflare", "model": "cloudflare/@cf/meta/llama-2-7b-chat-int8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.923, "output": 1.923 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cloudflare", "model": "cloudflare/@cf/meta/llama-2-7b-chat-int8", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-1-nemotron-safety-guard-8b-v3", "provider": "meta-llama", "model": "llama-3-1-nemotron-safety-guard-8b-v3", "displayName": "llama-3.1-nemotron-safety-guard-8b-v3", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/llama-3_1-nemotron-safety-guard-8b-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "llama-3.1-nemotron-safety-guard-8b-v3" ], "families": [ "nemotron" ], "releaseDate": "2025-10-28", "lastUpdated": "2025-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3", "modelKey": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3", "displayName": "llama-3.1-nemotron-safety-guard-8b-v3", "family": "nemotron", "metadata": { "lastUpdated": "2025-10-28", "openWeights": true, "releaseDate": "2025-10-28" } } ] }, { "id": "meta-llama/llama-3-1-nemotron-ultra-253b-v1", "provider": "meta-llama", "model": "llama-3-1-nemotron-ultra-253b-v1", "displayName": "Llama-3.1-Nemotron-Ultra-253B-v1", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 120000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.75, "input": 0.6, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Llama-3.1-Nemotron-Ultra-253B-v1" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-15", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "modelKey": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "displayName": "Llama-3.1-Nemotron-Ultra-253B-v1", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-01-15" } } ] }, { "id": "meta-llama/llama-3-2-11b-vision-instruct", "provider": "meta-llama", "model": "llama-3-2-11b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-3-2-11b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-11b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.35 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-11b-vision-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-2-1b-instruct", "provider": "meta-llama", "model": "llama-3-2-1b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-3-2-1b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-1b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-1b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-2-3b-instruct", "provider": "meta-llama", "model": "llama-3-2-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-3-2-3b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-3b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-2-90b-vision-instruct", "provider": "meta-llama", "model": "llama-3-2-90b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-3-2-90b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-90b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-2-90b-vision-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-2-nemoretriever-300m-embed-v1", "provider": "meta-llama", "model": "llama-3-2-nemoretriever-300m-embed-v1", "displayName": "llama-3_2-nemoretriever-300m-embed-v1", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/llama-3_2-nemoretriever-300m-embed-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/llama-3_2-nemoretriever-300m-embed-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "llama-3_2-nemoretriever-300m-embed-v1" ], "releaseDate": "2025-07-24", "lastUpdated": "2025-07-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/llama-3_2-nemoretriever-300m-embed-v1", "modelKey": "nvidia/llama-3_2-nemoretriever-300m-embed-v1", "displayName": "llama-3_2-nemoretriever-300m-embed-v1", "metadata": { "lastUpdated": "2025-07-24", "openWeights": true, "releaseDate": "2025-07-24" } } ] }, { "id": "meta-llama/llama-3-2-nv-rerankqa-1b-v2", "provider": "meta-llama", "model": "llama-3-2-nv-rerankqa-1b-v2", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "nvidia_nim" ], "aliases": [ "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nvidia_nim", "model": "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nvidia_nim", "model": "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2", "mode": "rerank" } ] }, { "id": "meta-llama/llama-3-3-70b-instruct", "provider": "meta-llama", "model": "llama-3-3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-3-3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.71, "output": 0.71 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-3-3-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-3-nemotron-super-49b-v1-5", "provider": "meta-llama", "model": "llama-3-3-nemotron-super-49b-v1-5", "displayName": "Nvidia Nemotron Super 49B v1.5", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron Super 49B v1.5" ], "families": [ "nemotron" ], "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "modelKey": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "displayName": "Nvidia Nemotron Super 49B v1.5", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } } ] }, { "id": "meta-llama/llama-3-70b", "provider": "meta-llama", "model": "llama-3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate", "vercel_ai_gateway" ], "aliases": [ "replicate/meta/llama-3-70b", "vercel_ai_gateway/meta/llama-3-70b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 2.75 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.59, "output": 0.79 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-3-70b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3-70b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-70b-instruct", "provider": "meta-llama", "model": "llama-3-70b-instruct", "displayName": "Meta: Llama 3 70B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "kilo", "llmgateway", "novita", "novita-ai", "openrouter", "replicate" ], "aliases": [ "kilo/meta-llama/llama-3-70b-instruct", "llmgateway/llama-3-70b-instruct", "novita-ai/meta-llama/llama-3-70b-instruct", "novita/meta-llama/llama-3-70b-instruct", "openrouter/meta-llama/llama-3-70b-instruct", "replicate/meta/llama-3-70b-instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.51, "output": 0.74 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.51, "output": 0.74 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.51, "output": 0.74 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.51, "output": 0.74 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/meta-llama/llama-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.59, "output": 0.79 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 2.75 } } ] }, "metadata": { "displayNames": [ "Llama 3 70B Instruct", "Llama3 70B Instruct", "Meta: Llama 3 70B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3-70b-instruct", "modelKey": "meta-llama/llama-3-70b-instruct", "displayName": "Meta: Llama 3 70B Instruct", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3-70b-instruct", "modelKey": "llama-3-70b-instruct", "displayName": "Llama 3 70B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-3-70b-instruct", "modelKey": "meta-llama/llama-3-70b-instruct", "displayName": "Llama3 70B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-04-25", "openWeights": true, "releaseDate": "2024-04-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-3-70b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/meta-llama/llama-3-70b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-3-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-8b", "provider": "meta-llama", "model": "llama-3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate", "vercel_ai_gateway" ], "aliases": [ "replicate/meta/llama-3-8b", "vercel_ai_gateway/meta/llama-3-8b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-3-8b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3-8b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3-8b-instruct", "provider": "meta-llama", "model": "llama-3-8b-instruct", "displayName": "Llama 3 8B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "kilo", "llmgateway", "novita", "novita-ai", "openrouter", "replicate" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct", "kilo/meta-llama/llama-3-8b-instruct", "llmgateway/llama-3-8b-instruct", "novita-ai/meta-llama/llama-3-8b-instruct", "novita/meta-llama/llama-3-8b-instruct", "openrouter/meta-llama/llama-3-8b-instruct", "replicate/meta/llama-3-8b-instruct" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.83 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.04 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/meta/llama-3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3-8b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Llama 3 8B Instruct", "Meta: Llama 3 8B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3-8b-instruct", "modelKey": "workers-ai/@cf/meta/llama-3-8b-instruct", "displayName": "Llama 3 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3-8b-instruct", "modelKey": "meta-llama/llama-3-8b-instruct", "displayName": "Meta: Llama 3 8B Instruct", "metadata": { "lastUpdated": "2025-04-03", "openWeights": true, "releaseDate": "2024-04-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3-8b-instruct", "modelKey": "llama-3-8b-instruct", "displayName": "Llama 3 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": true, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-3-8b-instruct", "modelKey": "meta-llama/llama-3-8b-instruct", "displayName": "Llama 3 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-04-25", "openWeights": true, "releaseDate": "2024-04-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3-8b-instruct", "modelKey": "meta-llama/llama-3-8b-instruct", "displayName": "Llama 3 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-3-8b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/meta/llama-3-8b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3-8b-instruct", "displayName": "Meta: Llama 3 8B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3-8b-instruct", "createdAt": "2024-04-18T00:00:00.000Z", "huggingFaceId": "meta-llama/Meta-Llama-3-8B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3-8b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 8192, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3-8b-instruct-awq", "provider": "meta-llama", "model": "llama-3-8b-instruct-awq", "displayName": "Llama 3 8B Instruct AWQ", "family": "llama", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct-awq" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3-8b-instruct-awq", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.27 } } ] }, "metadata": { "displayNames": [ "Llama 3 8B Instruct AWQ" ], "families": [ "llama" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3-8b-instruct-awq", "modelKey": "workers-ai/@cf/meta/llama-3-8b-instruct-awq", "displayName": "Llama 3 8B Instruct AWQ", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "meta-llama/llama-3.05-nemotron-tenyxchat-storybreaker-70b", "provider": "meta-llama", "model": "llama-3.05-nemotron-tenyxchat-storybreaker-70b", "displayName": "Nemotron Tenyxchat Storybreaker 70b", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Nemotron Tenyxchat Storybreaker 70b" ], "families": [ "nemotron" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B", "modelKey": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B", "displayName": "Nemotron Tenyxchat Storybreaker 70b", "family": "nemotron", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "meta-llama/llama-3.05-nt-storybreaker-ministral-70b", "provider": "meta-llama", "model": "llama-3.05-nt-storybreaker-ministral-70b", "displayName": "Llama 3.05 Storybreaker Ministral 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.05 Storybreaker Ministral 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B", "modelKey": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B", "displayName": "Llama 3.05 Storybreaker Ministral 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "meta-llama/llama-3.1-405b-instruct", "provider": "meta-llama", "model": "llama-3.1-405b-instruct", "displayName": "Llama 3.1 405B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "cortecs", "synthetic" ], "aliases": [ "cortecs/llama-3.1-405b-instruct", "synthetic/hf:meta-llama/Llama-3.1-405B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "llama-3.1-405b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-3.1-405B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 405B Instruct", "Llama-3.1-405B-Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "llama-3.1-405b-instruct", "modelKey": "llama-3.1-405b-instruct", "displayName": "Llama 3.1 405B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-3.1-405B-Instruct", "modelKey": "hf:meta-llama/Llama-3.1-405B-Instruct", "displayName": "Llama-3.1-405B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "meta-llama/llama-3.1-405b-instruct-maas", "provider": "meta-llama", "model": "llama-3.1-405b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-405b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-405b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 16 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-405b-instruct-maas", "mode": "chat", "metadata": { "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" } } ] }, { "id": "meta-llama/llama-3.1-70b", "provider": "meta-llama", "model": "llama-3.1-70b", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/meta/llama-3.1-70b", "vercel_ai_gateway/meta/llama-3.1-70b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.1-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.1-70b", "modelKey": "meta/llama-3.1-70b", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.1-70b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.1-70b-instruct", "provider": "meta-llama", "model": "llama-3.1-70b-instruct", "displayName": "Meta: Llama 3.1 70B Instruct", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "llmgateway", "nvidia", "openrouter", "synthetic", "wandb" ], "aliases": [ "kilo/meta-llama/llama-3.1-70b-instruct", "llmgateway/llama-3.1-70b-instruct", "nvidia/meta/llama-3.1-70b-instruct", "openrouter/meta-llama/llama-3.1-70b-instruct", "synthetic/hf:meta-llama/Llama-3.1-70B-Instruct", "wandb/meta-llama/Llama-3.1-70B-Instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-3.1-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "models.dev", "provider": "wandb", "model": "meta-llama/Llama-3.1-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.1-70b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B", "Llama 3.1 70B Instruct", "Llama 3.1 70b Instruct", "Llama-3.1-70B-Instruct", "Meta: Llama 3.1 70B Instruct" ], "families": [ "llama" ], "statuses": [ "beta" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-07-16", "lastUpdated": "2024-07-23", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.1-70b-instruct", "modelKey": "meta-llama/llama-3.1-70b-instruct", "displayName": "Meta: Llama 3.1 70B Instruct", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.1-70b-instruct", "modelKey": "llama-3.1-70b-instruct", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "status": "beta", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.1-70b-instruct", "modelKey": "meta/llama-3.1-70b-instruct", "displayName": "Llama 3.1 70b Instruct", "metadata": { "lastUpdated": "2024-07-16", "openWeights": true, "releaseDate": "2024-07-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.1-70b-instruct", "modelKey": "meta-llama/llama-3.1-70b-instruct", "displayName": "Llama 3.1 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-3.1-70B-Instruct", "modelKey": "hf:meta-llama/Llama-3.1-70B-Instruct", "displayName": "Llama-3.1-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "meta-llama/Llama-3.1-70B-Instruct", "modelKey": "meta-llama/Llama-3.1-70B-Instruct", "displayName": "Llama 3.1 70B", "family": "llama", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.1-70b-instruct", "displayName": "Meta: Llama 3.1 70B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.1-70b-instruct", "createdAt": "2024-07-23T00:00:00.000Z", "huggingFaceId": "meta-llama/Meta-Llama-3.1-70B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.1-70b-instruct-maas", "provider": "meta-llama", "model": "llama-3.1-70b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-70b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-70b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-70b-instruct-maas", "mode": "chat", "metadata": { "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" } } ] }, { "id": "meta-llama/llama-3.1-8b", "provider": "meta-llama", "model": "llama-3.1-8b", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llamagate", "vercel", "vercel_ai_gateway" ], "aliases": [ "llamagate/llama-3.1-8b", "vercel/meta/llama-3.1-8b", "vercel_ai_gateway/meta/llama-3.1-8b" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.22 } }, { "source": "litellm", "provider": "llamagate", "model": "llamagate/llama-3.1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.05 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.1-8b", "modelKey": "meta/llama-3.1-8b", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/llama-3.1-8b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.1-8b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.1-8b-cs", "provider": "meta-llama", "model": "llama-3.1-8b-cs", "displayName": "Llama-3.1-8B-CS", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/cerebras/llama-3.1-8b-cs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "cerebras/llama-3.1-8b-cs", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Llama-3.1-8B-CS" ], "releaseDate": "2025-05-13", "lastUpdated": "2025-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "cerebras/llama-3.1-8b-cs", "modelKey": "cerebras/llama-3.1-8b-cs", "displayName": "Llama-3.1-8B-CS", "metadata": { "lastUpdated": "2025-05-13", "openWeights": false, "releaseDate": "2025-05-13" } } ] }, { "id": "meta-llama/llama-3.1-8b-instant", "provider": "meta-llama", "model": "llama-3.1-8b-instant", "displayName": "Llama 3.1 8B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "groq", "helicone" ], "aliases": [ "groq/llama-3.1-8b-instant", "helicone/llama-3.1-8b-instant" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "groq", "model": "llama-3.1-8b-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.08 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-3.1-8b-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049999999999999996, "output": 0.08 } }, { "source": "litellm", "provider": "groq", "model": "groq/llama-3.1-8b-instant", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B", "Meta Llama 3.1 8B Instant" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "llama-3.1-8b-instant", "modelKey": "llama-3.1-8b-instant", "displayName": "Llama 3.1 8B", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-3.1-8b-instant", "modelKey": "llama-3.1-8b-instant", "displayName": "Meta Llama 3.1 8B Instant", "family": "llama", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/llama-3.1-8b-instant", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.1-8b-instruct", "provider": "meta-llama", "model": "llama-3.1-8b-instruct", "displayName": "Llama-3.1-8B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "friendli", "helicone", "inference", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "nscale", "nvidia", "openrouter", "ovhcloud", "regolo-ai", "synthetic", "wandb" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct", "friendli/meta-llama/Llama-3.1-8B-Instruct", "helicone/llama-3.1-8b-instruct", "inference/meta/llama-3.1-8b-instruct", "kilo/meta-llama/llama-3.1-8b-instruct", "llmgateway/llama-3.1-8b-instruct", "nano-gpt/meta-llama/llama-3.1-8b-instruct", "novita-ai/meta-llama/llama-3.1-8b-instruct", "novita/meta-llama/llama-3.1-8b-instruct", "nscale/meta-llama/Llama-3.1-8B-Instruct", "nvidia/meta/llama-3.1-8b-instruct", "openrouter/meta-llama/llama-3.1-8b-instruct", "ovhcloud/Llama-3.1-8B-Instruct", "ovhcloud/llama-3.1-8b-instruct", "regolo-ai/llama-3.1-8b-instruct", "synthetic/hf:meta-llama/Llama-3.1-8B-Instruct", "wandb/meta-llama/Llama-3.1-8B-Instruct" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "parallelFunctionCalling": false, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.8299999999999998 } }, { "source": "models.dev", "provider": "friendli", "model": "meta-llama/Llama-3.1-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.049999999999999996 } }, { "source": "models.dev", "provider": "inference", "model": "meta/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.025, "output": 0.025 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.05 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.22 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0544, "output": 0.0544 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.05 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.03 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.11 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-3.1-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "models.dev", "provider": "wandb", "model": "meta-llama/Llama-3.1-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.22 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.05 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/meta-llama/Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.03 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/meta-llama/Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 22000, "output": 22000 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.1-8b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct", "Llama 3.1 8b Instruct", "Llama-3.1-8B-Instruct", "Meta Llama 3.1 8B Instruct", "Meta-Llama-3.1-8B-Instruct", "Meta: Llama 3.1 8B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct", "modelKey": "workers-ai/@cf/meta/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "meta-llama/Llama-3.1-8B-Instruct", "modelKey": "meta-llama/Llama-3.1-8B-Instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2024-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-3.1-8b-instruct", "modelKey": "llama-3.1-8b-instruct", "displayName": "Meta Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "meta/llama-3.1-8b-instruct", "modelKey": "meta/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.1-8b-instruct", "modelKey": "meta-llama/llama-3.1-8b-instruct", "displayName": "Meta: Llama 3.1 8B Instruct", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.1-8b-instruct", "modelKey": "llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "status": "beta", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meta-llama/llama-3.1-8b-instruct", "modelKey": "meta-llama/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8b Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-3.1-8b-instruct", "modelKey": "meta-llama/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-07-24", "openWeights": true, "releaseDate": "2024-07-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.1-8b-instruct", "modelKey": "meta/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.1-8b-instruct", "modelKey": "meta-llama/llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "llama-3.1-8b-instruct", "modelKey": "llama-3.1-8b-instruct", "displayName": "Llama-3.1-8B-Instruct", "metadata": { "lastUpdated": "2025-06-11", "openWeights": true, "releaseDate": "2025-06-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "llama-3.1-8b-instruct", "modelKey": "llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-07", "openWeights": false, "releaseDate": "2025-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-3.1-8B-Instruct", "modelKey": "hf:meta-llama/Llama-3.1-8B-Instruct", "displayName": "Llama-3.1-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "meta-llama/Llama-3.1-8B-Instruct", "modelKey": "meta-llama/Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-3.1-8b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/meta-llama/Llama-3.1-8B-Instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Llama-3.1-8B-Instruct", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/meta-llama/Llama-3.1-8B-Instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.1-8b-instruct", "displayName": "Meta: Llama 3.1 8B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.1-8b-instruct", "createdAt": "2024-07-23T00:00:00.000Z", "huggingFaceId": "meta-llama/Meta-Llama-3.1-8B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.1-8b-instruct-awq", "provider": "meta-llama", "model": "llama-3.1-8b-instruct-awq", "displayName": "Llama 3.1 8B Instruct AWQ", "family": "llama", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-awq" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.27 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct AWQ" ], "families": [ "llama" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", "modelKey": "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", "displayName": "Llama 3.1 8B Instruct AWQ", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "meta-llama/llama-3.1-8b-instruct-fp8", "provider": "meta-llama", "model": "llama-3.1-8b-instruct-fp8", "displayName": "Llama 3.1 8B Instruct FP8", "family": "llama", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", "cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.29 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-3.1-8b-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.152, "output": 0.287 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct FP8", "Llama 3.1 8B Instruct fp8" ], "families": [ "llama" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", "modelKey": "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", "displayName": "Llama 3.1 8B Instruct FP8", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-3.1-8b-instruct-fp8", "modelKey": "@cf/meta/llama-3.1-8b-instruct-fp8", "displayName": "Llama 3.1 8B Instruct fp8", "family": "llama", "metadata": { "lastUpdated": "2024-07-25", "openWeights": true, "releaseDate": "2024-07-25" } } ] }, { "id": "meta-llama/llama-3.1-8b-instruct-maas", "provider": "meta-llama", "model": "llama-3.1-8b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-8b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-8b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.1-8b-instruct-maas", "mode": "chat", "metadata": { "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" } } ] }, { "id": "meta-llama/llama-3.1-8b-instruct-turbo", "provider": "meta-llama", "model": "llama-3.1-8b-instruct-turbo", "displayName": "Meta Llama 3.1 8B Instruct Turbo", "family": "llama", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/llama-3.1-8b-instruct-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "llama-3.1-8b-instruct-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Meta Llama 3.1 8B Instruct Turbo" ], "families": [ "llama" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-3.1-8b-instruct-turbo", "modelKey": "llama-3.1-8b-instruct-turbo", "displayName": "Meta Llama 3.1 8B Instruct Turbo", "family": "llama", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "meta-llama/llama-3.1-nemotron-70b-instruct", "provider": "meta-llama", "model": "llama-3.1-nemotron-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra" ], "aliases": [ "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.1-nemotron-70b-instruct-hf", "provider": "meta-llama", "model": "llama-3.1-nemotron-70b-instruct-hf", "displayName": "Nvidia Nemotron 70b", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.357, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron 70b" ], "families": [ "nemotron" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "modelKey": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "displayName": "Nvidia Nemotron 70b", "family": "nemotron", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "meta-llama/llama-3.1-nemotron-safety-guard-8b-v3", "provider": "meta-llama", "model": "llama-3.1-nemotron-safety-guard-8b-v3", "displayName": "Llama 3.1 Nemotron Safety Guard", "family": "llama", "sources": [ "models.dev" ], "providers": [ "vultr" ], "aliases": [ "vultr/nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vultr", "model": "nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 Nemotron Safety Guard" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-10-28", "lastUpdated": "2025-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3", "modelKey": "nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3", "displayName": "Llama 3.1 Nemotron Safety Guard", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-10-28", "openWeights": true, "releaseDate": "2025-10-28" } } ] }, { "id": "meta-llama/llama-3.1-nemotron-ultra-253b", "provider": "meta-llama", "model": "llama-3.1-nemotron-ultra-253b", "displayName": "Llama 3.1 Nemotron Ultra 253B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/llama-3.1-nemotron-ultra-253b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.1-nemotron-ultra-253b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 Nemotron Ultra 253B" ], "families": [ "llama" ], "releaseDate": "2025-04-07", "lastUpdated": "2025-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.1-nemotron-ultra-253b", "modelKey": "llama-3.1-nemotron-ultra-253b", "displayName": "Llama 3.1 Nemotron Ultra 253B", "family": "llama", "metadata": { "lastUpdated": "2025-04-07", "openWeights": true, "releaseDate": "2025-04-07" } } ] }, { "id": "meta-llama/llama-3.1-nemotron-ultra-253b-v1", "provider": "meta-llama", "model": "llama-3.1-nemotron-ultra-253b-v1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nebius" ], "aliases": [ "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nebius", "model": "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "meta-llama/llama-3.2-11b", "provider": "meta-llama", "model": "llama-3.2-11b", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/meta/llama-3.2-11b", "vercel_ai_gateway/meta/llama-3.2-11b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.2-11b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.16 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-11b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.16, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 11B Vision Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.2-11b", "modelKey": "meta/llama-3.2-11b", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": false, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-11b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.2-11b-instruct", "provider": "meta-llama", "model": "llama-3.2-11b-instruct", "displayName": "Llama 3.2 11B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/llama-3.2-11b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.2-11b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.33 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 11B Instruct" ], "families": [ "llama" ], "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.2-11b-instruct", "modelKey": "llama-3.2-11b-instruct", "displayName": "Llama 3.2 11B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } } ] }, { "id": "meta-llama/llama-3.2-11b-vision-instruct", "provider": "meta-llama", "model": "llama-3.2-11b-vision-instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "github-models", "inference", "kilo", "nvidia", "openrouter" ], "aliases": [ "azure-cognitive-services/llama-3.2-11b-vision-instruct", "azure/llama-3.2-11b-vision-instruct", "azure_ai/Llama-3.2-11B-Vision-Instruct", "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "cloudflare-workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct", "github-models/meta/llama-3.2-11b-vision-instruct", "inference/meta/llama-3.2-11b-vision-instruct", "kilo/meta-llama/llama-3.2-11b-vision-instruct", "nvidia/meta/llama-3.2-11b-vision-instruct", "openrouter/meta-llama/llama-3.2-11b-vision-instruct" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.37, "output": 0.37 } }, { "source": "models.dev", "provider": "azure", "model": "llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.37, "output": 0.37 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049, "output": 0.68 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0485, "output": 0.676 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "inference", "model": "meta/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.055, "output": 0.055 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049, "output": 0.049 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.2-11b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.345, "output": 0.345 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Llama-3.2-11B-Vision-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.37, "output": 0.37 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.049, "output": 0.049 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.2-11b-vision-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.345, "output": 0.345 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 11B Vision Instruct", "Llama 3.2 11b Vision Instruct", "Llama-3.2-11B-Vision-Instruct", "Meta: Llama 3.2 11B Vision Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.2-11b-vision-instruct", "modelKey": "llama-3.2-11b-vision-instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.2-11b-vision-instruct", "modelKey": "llama-3.2-11b-vision-instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "modelKey": "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-3.2-11b-vision-instruct", "modelKey": "@cf/meta/llama-3.2-11b-vision-instruct", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/llama-3.2-11b-vision-instruct", "modelKey": "meta/llama-3.2-11b-vision-instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "meta/llama-3.2-11b-vision-instruct", "modelKey": "meta/llama-3.2-11b-vision-instruct", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.2-11b-vision-instruct", "modelKey": "meta-llama/llama-3.2-11b-vision-instruct", "displayName": "Meta: Llama 3.2 11B Vision Instruct", "metadata": { "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.2-11b-vision-instruct", "modelKey": "meta/llama-3.2-11b-vision-instruct", "displayName": "Llama 3.2 11b Vision Instruct", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-18", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.2-11b-vision-instruct", "modelKey": "meta-llama/llama-3.2-11b-vision-instruct", "displayName": "Llama 3.2 11B Vision Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Llama-3.2-11B-Vision-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.2-11b-vision-instruct", "displayName": "Meta: Llama 3.2 11B Vision Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.2-11b-vision-instruct", "createdAt": "2024-09-25T00:00:00.000Z", "huggingFaceId": "meta-llama/Llama-3.2-11B-Vision-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.2-11b-vision-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.2-1b", "provider": "meta-llama", "model": "llama-3.2-1b", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/meta/llama-3.2-1b", "vercel_ai_gateway/meta/llama-3.2-1b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.2-1b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-1b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 1B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-09-18", "lastUpdated": "2024-09-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.2-1b", "modelKey": "meta/llama-3.2-1b", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-18", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-1b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.2-1b-instruct", "provider": "meta-llama", "model": "llama-3.2-1b-instruct", "displayName": "Llama 3.2 1B Instruct", "family": "unsloth", "sources": [ "models.dev", "openrouter" ], "providers": [ "chutes", "cloudflare-ai-gateway", "cloudflare-workers-ai", "inference", "kilo", "nvidia", "openrouter" ], "aliases": [ "chutes/unsloth/Llama-3.2-1B-Instruct", "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct", "cloudflare-workers-ai/@cf/meta/llama-3.2-1b-instruct", "inference/meta/llama-3.2-1b-instruct", "kilo/meta-llama/llama-3.2-1b-instruct", "nvidia/meta/llama-3.2-1b-instruct", "openrouter/meta-llama/llama-3.2-1b-instruct" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "outputTokens": 60000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/Llama-3.2-1B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.01, "output": 0.0109 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.027, "output": 0.2 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.027, "output": 0.201 } }, { "source": "models.dev", "provider": "inference", "model": "meta/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.01 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.027, "output": 0.2 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.2-1b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.027, "output": 0.201 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.2-1b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.027, "output": 0.201 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 1B Instruct", "Llama 3.2 1b Instruct", "Meta: Llama 3.2 1B Instruct" ], "families": [ "llama", "unsloth" ], "knowledgeCutoff": "2023-12", "releaseDate": "2026-01-27", "lastUpdated": "2026-04-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/Llama-3.2-1B-Instruct", "modelKey": "unsloth/Llama-3.2-1B-Instruct", "displayName": "Llama 3.2 1B Instruct", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.2-1b-instruct", "modelKey": "workers-ai/@cf/meta/llama-3.2-1b-instruct", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-3.2-1b-instruct", "modelKey": "@cf/meta/llama-3.2-1b-instruct", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "meta/llama-3.2-1b-instruct", "modelKey": "meta/llama-3.2-1b-instruct", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.2-1b-instruct", "modelKey": "meta-llama/llama-3.2-1b-instruct", "displayName": "Meta: Llama 3.2 1B Instruct", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.2-1b-instruct", "modelKey": "meta/llama-3.2-1b-instruct", "displayName": "Llama 3.2 1b Instruct", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-18", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.2-1b-instruct", "modelKey": "meta-llama/llama-3.2-1b-instruct", "displayName": "Llama 3.2 1B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.2-1b-instruct", "displayName": "Meta: Llama 3.2 1B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.2-1b-instruct", "createdAt": "2024-09-25T00:00:00.000Z", "huggingFaceId": "meta-llama/Llama-3.2-1B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 60000, "max_completion_tokens": 60000, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.2-3b", "provider": "meta-llama", "model": "llama-3.2-3b", "displayName": "Llama 3.2 3B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llamagate", "venice", "vercel", "vercel_ai_gateway" ], "aliases": [ "llamagate/llama-3.2-3b", "venice/llama-3.2-3b", "vercel/meta/llama-3.2-3b", "vercel_ai_gateway/meta/llama-3.2-3b" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "llama-3.2-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.2-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "llamagate", "model": "llamagate/llama-3.2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.08 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 3B", "Llama 3.2 3B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-10-03", "lastUpdated": "2026-06-11", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "llama-3.2-3b", "modelKey": "llama-3.2-3b", "displayName": "Llama 3.2 3B", "family": "llama", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2024-10-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.2-3b", "modelKey": "meta/llama-3.2-3b", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-18", "openWeights": false, "releaseDate": "2024-09-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/llama-3.2-3b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-3b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.2-3b-instruct", "provider": "meta-llama", "model": "llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "unsloth", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "chutes", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "hyperbolic", "inference", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "nvidia", "openrouter" ], "aliases": [ "chutes/unsloth/Llama-3.2-3B-Instruct", "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct", "cloudflare-workers-ai/@cf/meta/llama-3.2-3b-instruct", "deepinfra/meta-llama/Llama-3.2-3B-Instruct", "hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "inference/meta/llama-3.2-3b-instruct", "kilo/meta-llama/llama-3.2-3b-instruct", "llmgateway/llama-3.2-3b-instruct", "nano-gpt/meta-llama/llama-3.2-3b-instruct", "novita-ai/meta-llama/llama-3.2-3b-instruct", "novita/meta-llama/llama-3.2-3b-instruct", "nvidia/meta/llama-3.2-3b-instruct", "openrouter/meta-llama/llama-3.2-3b-instruct" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": false, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/Llama-3.2-3B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.01, "output": 0.0136 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.051, "output": 0.34 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0509, "output": 0.335 } }, { "source": "models.dev", "provider": "inference", "model": "meta/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.02 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.051, "output": 0.34 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.05 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0306, "output": 0.0493 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.05 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0509, "output": 0.335 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.2-3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.02 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.05 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.0509, "output": 0.335 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 3B Instruct", "Llama 3.2 3b Instruct", "Meta: Llama 3.2 3B Instruct" ], "families": [ "llama", "unsloth" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-02-12", "lastUpdated": "2026-04-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/Llama-3.2-3B-Instruct", "modelKey": "unsloth/Llama-3.2-3B-Instruct", "displayName": "Llama 3.2 3B Instruct", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.2-3b-instruct", "modelKey": "workers-ai/@cf/meta/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-3.2-3b-instruct", "modelKey": "@cf/meta/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "meta/llama-3.2-3b-instruct", "modelKey": "meta/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.2-3b-instruct", "modelKey": "meta-llama/llama-3.2-3b-instruct", "displayName": "Meta: Llama 3.2 3B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.2-3b-instruct", "modelKey": "llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-18", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meta-llama/llama-3.2-3b-instruct", "modelKey": "meta-llama/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3b Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-25", "openWeights": false, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-3.2-3b-instruct", "modelKey": "meta-llama/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-18", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.2-3b-instruct", "modelKey": "meta/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-09-18", "openWeights": true, "releaseDate": "2024-09-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.2-3b-instruct", "modelKey": "meta-llama/llama-3.2-3b-instruct", "displayName": "Llama 3.2 3B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.2-3B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-3.2-3b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct", "displayName": "Meta: Llama 3.2 3B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.2-3b-instruct", "createdAt": "2024-09-25T00:00:00.000Z", "huggingFaceId": "meta-llama/Llama-3.2-3B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 80000, "max_completion_tokens": 80000, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.2-3b-instruct-turbo", "provider": "meta-llama", "model": "llama-3.2-3b-instruct-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.2-3b-instruct:free", "provider": "meta-llama", "model": "llama-3.2-3b-instruct:free", "displayName": "Llama 3.2 3B Instruct (free)", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/meta-llama/llama-3.2-3b-instruct:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 3B Instruct (free)", "Meta: Llama 3.2 3B Instruct (free)" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.2-3b-instruct:free", "modelKey": "meta-llama/llama-3.2-3b-instruct:free", "displayName": "Llama 3.2 3B Instruct (free)", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.2-3b-instruct:free", "displayName": "Meta: Llama 3.2 3B Instruct (free)", "metadata": { "canonicalSlug": "meta-llama/llama-3.2-3b-instruct", "createdAt": "2024-09-25T00:00:00.000Z", "huggingFaceId": "meta-llama/Llama-3.2-3B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.2-90b", "provider": "meta-llama", "model": "llama-3.2-90b", "displayName": "Llama 3.2 90B Vision Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/meta/llama-3.2-90b", "vercel_ai_gateway/meta/llama-3.2-90b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.2-90b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-90b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 90B Vision Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.2-90b", "modelKey": "meta/llama-3.2-90b", "displayName": "Llama 3.2 90B Vision Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": false, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.2-90b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.2-90b-vision-instruct", "provider": "meta-llama", "model": "llama-3.2-90b-vision-instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "io-net", "nvidia" ], "aliases": [ "azure-cognitive-services/llama-3.2-90b-vision-instruct", "azure/llama-3.2-90b-vision-instruct", "azure_ai/Llama-3.2-90B-Vision-Instruct", "github-models/meta/llama-3.2-90b-vision-instruct", "io-net/meta-llama/Llama-3.2-90B-Vision-Instruct", "nvidia/meta/llama-3.2-90b-vision-instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "llama-3.2-90b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.04, "output": 2.04 } }, { "source": "models.dev", "provider": "azure", "model": "llama-3.2-90b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.04, "output": 2.04 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/llama-3.2-90b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "io-net", "model": "meta-llama/Llama-3.2-90B-Vision-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "cacheWrite": 0.7, "input": 0.35, "output": 0.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.2-90b-vision-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Llama-3.2-90B-Vision-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.04, "output": 2.04 } } ] }, "metadata": { "displayNames": [ "Llama 3.2 90B Vision Instruct", "Llama-3.2-90B-Vision-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-09-25", "lastUpdated": "2024-09-25", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.2-90b-vision-instruct", "modelKey": "llama-3.2-90b-vision-instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.2-90b-vision-instruct", "modelKey": "llama-3.2-90b-vision-instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/llama-3.2-90b-vision-instruct", "modelKey": "meta/llama-3.2-90b-vision-instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "meta-llama/Llama-3.2-90B-Vision-Instruct", "modelKey": "meta-llama/Llama-3.2-90B-Vision-Instruct", "displayName": "Llama 3.2 90B Vision Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.2-90b-vision-instruct", "modelKey": "meta/llama-3.2-90b-vision-instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Llama-3.2-90B-Vision-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview" } } ] }, { "id": "meta-llama/llama-3.2-90b-vision-instruct-maas", "provider": "meta-llama", "model": "llama-3.2-90b-vision-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-3.2-90b-vision-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas", "mode": "chat", "metadata": { "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" } } ] }, { "id": "meta-llama/llama-3.2-nv-rerankqa-1b-v2", "provider": "meta-llama", "model": "llama-3.2-nv-rerankqa-1b-v2", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "nvidia_nim" ], "aliases": [ "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nvidia_nim", "model": "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nvidia_nim", "model": "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2", "mode": "rerank" } ] }, { "id": "meta-llama/llama-3.3-70b", "provider": "meta-llama", "model": "llama-3.3-70b", "displayName": "Llama 3.3 70B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cerebras", "venice", "vercel", "vercel_ai_gateway" ], "aliases": [ "cerebras/llama-3.3-70b", "venice/llama-3.3-70b", "vercel/meta/llama-3.3-70b", "vercel_ai_gateway/meta/llama-3.3-70b" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "llama-3.3-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 2.8 } }, { "source": "models.dev", "provider": "vercel", "model": "meta/llama-3.3-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "cerebras", "model": "cerebras/llama-3.3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.85, "output": 1.2 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B", "Llama-3.3-70B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-04-06", "lastUpdated": "2026-06-11", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "llama-3.3-70b", "modelKey": "llama-3.3-70b", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-04-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-3.3-70b", "modelKey": "meta/llama-3.3-70b", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/llama-3.3-70b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-3.3-70b", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.3-70b-cs", "provider": "meta-llama", "model": "llama-3.3-70b-cs", "displayName": "llama-3.3-70b-cs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/cerebras/llama-3.3-70b-cs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "llama-3.3-70b-cs" ], "statuses": [ "deprecated" ], "releaseDate": "2025-05-13", "lastUpdated": "2025-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "cerebras/llama-3.3-70b-cs", "modelKey": "cerebras/llama-3.3-70b-cs", "displayName": "llama-3.3-70b-cs", "status": "deprecated", "metadata": { "lastUpdated": "2025-05-13", "openWeights": false, "releaseDate": "2025-05-13" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct", "provider": "meta-llama", "model": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "berget", "cloudferro-sherlock", "cortecs", "crusoe", "deepinfra", "friendli", "github-models", "helicone", "hyperbolic", "io-net", "kilo", "llama", "llmgateway", "meganova", "meta_llama", "nano-gpt", "nebius", "novita", "novita-ai", "nscale", "nvidia", "openrouter", "regolo-ai", "scaleway", "synthetic", "wandb" ], "aliases": [ "azure-cognitive-services/llama-3.3-70b-instruct", "azure/llama-3.3-70b-instruct", "azure_ai/Llama-3.3-70B-Instruct", "berget/meta-llama/Llama-3.3-70B-Instruct", "cloudferro-sherlock/meta-llama/Llama-3.3-70B-Instruct", "cortecs/llama-3.3-70b-instruct", "crusoe/meta-llama/Llama-3.3-70B-Instruct", "deepinfra/meta-llama/Llama-3.3-70B-Instruct", "friendli/meta-llama/Llama-3.3-70B-Instruct", "github-models/meta/llama-3.3-70b-instruct", "helicone/llama-3.3-70b-instruct", "hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "io-net/meta-llama/Llama-3.3-70B-Instruct", "kilo/meta-llama/llama-3.3-70b-instruct", "llama/llama-3.3-70b-instruct", "llmgateway/llama-3.3-70b-instruct", "meganova/meta-llama/Llama-3.3-70B-Instruct", "meta_llama/Llama-3.3-70B-Instruct", "nano-gpt/meta-llama/llama-3.3-70b-instruct", "nebius/meta-llama/Llama-3.3-70B-Instruct", "novita-ai/meta-llama/llama-3.3-70b-instruct", "novita/meta-llama/llama-3.3-70b-instruct", "nscale/meta-llama/Llama-3.3-70B-Instruct", "nvidia/meta/llama-3.3-70b-instruct", "openrouter/meta-llama/llama-3.3-70b-instruct", "regolo-ai/llama-3.3-70b-instruct", "scaleway/llama-3.3-70b-instruct", "synthetic/hf:meta-llama/Llama-3.3-70B-Instruct", "wandb/meta-llama/Llama-3.3-70B-Instruct" ], "mergedProviderModelRecords": 29, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.71, "output": 0.71 } }, { "source": "models.dev", "provider": "azure", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.71, "output": 0.71 } }, { "source": "models.dev", "provider": "berget", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.99, "output": 0.99 } }, { "source": "models.dev", "provider": "cloudferro-sherlock", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.92, "output": 2.92 } }, { "source": "models.dev", "provider": "cortecs", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.089, "output": 0.275 } }, { "source": "models.dev", "provider": "friendli", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 0.6 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.39 } }, { "source": "models.dev", "provider": "io-net", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.065, "cacheWrite": 0.26, "input": 0.13, "output": 0.38 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.32 } }, { "source": "models.dev", "provider": "llama", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "meganova", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.23 } }, { "source": "models.dev", "provider": "nebius", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.013, "cacheWrite": 0.16, "input": 0.13, "output": 0.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.135, "output": 0.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.32 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.7 } }, { "source": "models.dev", "provider": "scaleway", "model": "llama-3.3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "models.dev", "provider": "wandb", "model": "meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.71, "output": 0.71 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.71, "output": 0.71 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.23, "output": 0.4 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "meta_llama", "model": "meta_llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "nebius", "model": "nebius/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.135, "output": 0.4 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/meta-llama/Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 71000, "output": 71000 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.32 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct", "Llama 3.3 70b Instruct", "Llama-3.3-70B-Instruct", "Meta Llama 3.3 70B Instruct", "Meta: Llama 3.3 70B Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 29 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-04-27", "openWeights": true, "releaseDate": "2025-04-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudferro-sherlock", "providerName": "CloudFerro Sherlock", "providerApi": "https://api-sherlock.cloudferro.com/openai/v1/", "providerDoc": "https://docs.sherlock.cloudferro.com/", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-10-09", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2024-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/llama-3.3-70b-instruct", "modelKey": "meta/llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Meta Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-3.3-70b-instruct", "modelKey": "meta-llama/llama-3.3-70b-instruct", "displayName": "Meta: Llama 3.3 70B Instruct", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2024-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meta-llama/llama-3.3-70b-instruct", "modelKey": "meta-llama/llama-3.3-70b-instruct", "displayName": "Llama 3.3 70b Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-3.3-70b-instruct", "modelKey": "meta-llama/llama-3.3-70b-instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-07", "openWeights": true, "releaseDate": "2024-12-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-3.3-70b-instruct", "modelKey": "meta/llama-3.3-70b-instruct", "displayName": "Llama 3.3 70b Instruct", "metadata": { "lastUpdated": "2024-11-26", "openWeights": true, "releaseDate": "2024-11-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.3-70b-instruct", "modelKey": "meta-llama/llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-28", "openWeights": false, "releaseDate": "2025-04-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "llama-3.3-70b-instruct", "modelKey": "llama-3.3-70b-instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-3.3-70B-Instruct", "modelKey": "hf:meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "meta-llama/Llama-3.3-70B-Instruct", "modelKey": "meta-llama/Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Llama-3.3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "meta_llama", "model": "meta_llama/Llama-3.3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://llama.developer.meta.com/docs/models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-3.3-70b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/meta-llama/Llama-3.3-70B-Instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct", "displayName": "Meta: Llama 3.3 70B Instruct", "metadata": { "canonicalSlug": "meta-llama/llama-3.3-70b-instruct", "createdAt": "2024-12-06T17:28:57.000Z", "huggingFaceId": "meta-llama/Llama-3.3-70B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-abliterated", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-abliterated", "displayName": "Llama 3.3 70B Instruct abliterated", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/huihui-ai/Llama-3.3-70B-Instruct-abliterated" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "huihui-ai/Llama-3.3-70B-Instruct-abliterated", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct abliterated" ], "families": [ "llama" ], "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "huihui-ai/Llama-3.3-70B-Instruct-abliterated", "modelKey": "huihui-ai/Llama-3.3-70B-Instruct-abliterated", "displayName": "Llama 3.3 70B Instruct abliterated", "family": "llama", "metadata": { "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-fp8", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-fp8", "displayName": "Llama 3.3 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "evroc", "inceptron" ], "aliases": [ "evroc/nvidia/Llama-3.3-70B-Instruct-FP8", "inceptron/nvidia/llama-3.3-70b-instruct-fp8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "nvidia/Llama-3.3-70B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.18, "output": 1.18 } }, { "source": "models.dev", "provider": "inceptron", "model": "nvidia/llama-3.3-70b-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0.12, "output": 0.38 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B", "Llama 3.3 70B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "nvidia/Llama-3.3-70B-Instruct-FP8", "modelKey": "nvidia/Llama-3.3-70B-Instruct-FP8", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2024-12-01", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inceptron", "providerName": "Inceptron", "providerApi": "https://api.inceptron.io/v1", "providerDoc": "https://docs.inceptron.io", "model": "nvidia/llama-3.3-70b-instruct-fp8", "modelKey": "nvidia/llama-3.3-70b-instruct-fp8", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-fp8-dynamic", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-fp8-dynamic", "displayName": "Llama 3.3 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "stackit" ], "aliases": [ "stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49, "output": 0.71 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B" ], "families": [ "llama" ], "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", "modelKey": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2024-12-05", "openWeights": true, "releaseDate": "2024-12-05" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-fp8-fast", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-fp8-fast", "displayName": "Llama 3.3 70B Instruct FP8 Fast", "family": "llama", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", "cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 24000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 2.25 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.293, "output": 2.253 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct FP8 Fast", "Llama 3.3 70B Instruct fp8 Fast" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", "modelKey": "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", "displayName": "Llama 3.3 70B Instruct FP8 Fast", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast", "modelKey": "@cf/meta/llama-3.3-70b-instruct-fp8-fast", "displayName": "Llama 3.3 70B Instruct fp8 Fast", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-maas", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-maas", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "google-vertex" ], "aliases": [ "google-vertex/meta/llama-3.3-70b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "meta/llama-3.3-70b-instruct-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "meta/llama-3.3-70b-instruct-maas", "modelKey": "meta/llama-3.3-70b-instruct-maas", "displayName": "Llama 3.3 70B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-turbo", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-turbo", "displayName": "Llama 3.3 70B Turbo", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "deepinfra", "together_ai", "togetherai" ], "aliases": [ "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", "togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "temperature": true, "parallelFunctionCalling": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "deepinfra", "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.32 } }, { "source": "models.dev", "provider": "togetherai", "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.88, "output": 0.88 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.39 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.88, "output": 0.88 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B", "Llama 3.3 70B Turbo" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "modelKey": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "displayName": "Llama 3.3 70B Turbo", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "modelKey": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.3-70b-instruct-turbo-free", "provider": "meta-llama", "model": "llama-3.3-70b-instruct-turbo-free", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.3-70b-instruct:free", "provider": "meta-llama", "model": "llama-3.3-70b-instruct:free", "displayName": "Llama 3.3 70B Instruct (free)", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/meta-llama/llama-3.3-70b-instruct:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Instruct (free)", "Meta: Llama 3.3 70B Instruct (free)" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-3.3-70b-instruct:free", "modelKey": "meta-llama/llama-3.3-70b-instruct:free", "displayName": "Llama 3.3 70B Instruct (free)", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct:free", "displayName": "Meta: Llama 3.3 70B Instruct (free)", "metadata": { "canonicalSlug": "meta-llama/llama-3.3-70b-instruct", "createdAt": "2024-12-06T17:28:57.000Z", "huggingFaceId": "meta-llama/Llama-3.3-70B-Instruct", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 65536, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-3.3-70b-versatile", "provider": "meta-llama", "model": "llama-3.3-70b-versatile", "displayName": "Llama 3.3 70B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "groq", "helicone" ], "aliases": [ "abacus/llama-3.3-70b-versatile", "groq/llama-3.3-70b-versatile", "helicone/llama-3.3-70b-versatile" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "llama-3.3-70b-versatile", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.79 } }, { "source": "models.dev", "provider": "groq", "model": "llama-3.3-70b-versatile", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.79 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-3.3-70b-versatile", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 0.7899999999999999 } }, { "source": "litellm", "provider": "groq", "model": "groq/llama-3.3-70b-versatile", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.59, "output": 0.79 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B", "Llama 3.3 70B Versatile", "Meta Llama 3.3 70B Versatile" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "llama-3.3-70b-versatile", "modelKey": "llama-3.3-70b-versatile", "displayName": "Llama 3.3 70B Versatile", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "llama-3.3-70b-versatile", "modelKey": "llama-3.3-70b-versatile", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-3.3-70b-versatile", "modelKey": "llama-3.3-70b-versatile", "displayName": "Meta Llama 3.3 70B Versatile", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/llama-3.3-70b-versatile", "mode": "chat" } ] }, { "id": "meta-llama/llama-3.3-8b-instruct", "provider": "meta-llama", "model": "llama-3.3-8b-instruct", "displayName": "Llama-3.3-8B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llama", "meta_llama" ], "aliases": [ "llama/llama-3.3-8b-instruct", "meta_llama/Llama-3.3-8B-Instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4028, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llama", "model": "llama-3.3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "meta_llama", "model": "meta_llama/Llama-3.3-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Llama-3.3-8B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "llama-3.3-8b-instruct", "modelKey": "llama-3.3-8b-instruct", "displayName": "Llama-3.3-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "meta_llama", "model": "meta_llama/Llama-3.3-8B-Instruct", "mode": "chat", "metadata": { "source": "https://llama.developer.meta.com/docs/models" } } ] }, { "id": "meta-llama/llama-3.3-nemotron-super-49b-v1", "provider": "meta-llama", "model": "llama-3.3-nemotron-super-49b-v1", "displayName": "Nvidia Nemotron Super 49B", "family": "nemotron", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "nano-gpt", "nebius" ], "aliases": [ "nano-gpt/nvidia/Llama-3.3-Nemotron-Super-49B-v1", "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/Llama-3.3-Nemotron-Super-49B-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron Super 49B" ], "families": [ "nemotron" ], "modes": [ "chat" ], "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/Llama-3.3-Nemotron-Super-49B-v1", "modelKey": "nvidia/Llama-3.3-Nemotron-Super-49B-v1", "displayName": "Nvidia Nemotron Super 49B", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "meta-llama/llama-3.3-nemotron-super-49b-v1.5", "provider": "meta-llama", "model": "llama-3.3-nemotron-super-49b-v1.5", "displayName": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", "family": "nemotron", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "deepinfra", "kilo", "openrouter" ], "aliases": [ "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "kilo/nvidia/llama-3.3-nemotron-super-49b-v1.5", "openrouter/nvidia/llama-3.3-nemotron-super-49b-v1.5" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 Nemotron Super 49B v1.5", "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5" ], "families": [ "nemotron" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-03-31", "releaseDate": "2025-03-16", "lastUpdated": "2025-03-16", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "modelKey": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "displayName": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", "family": "nemotron", "metadata": { "lastUpdated": "2025-03-16", "openWeights": false, "releaseDate": "2025-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "modelKey": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "displayName": "Llama 3.3 Nemotron Super 49B v1.5", "family": "nemotron", "metadata": { "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "displayName": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", "metadata": { "canonicalSlug": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "createdAt": "2025-10-10T13:03:15.000Z", "huggingFaceId": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "knowledgeCutoff": "2024-03-31", "links": { "details": "/api/v1/models/nvidia/llama-3.3-nemotron-super-49b-v1.5/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-4-maverick", "provider": "meta-llama", "model": "llama-4-maverick", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cortecs", "digitalocean", "helicone", "kilo", "nano-gpt", "openrouter", "vercel", "vercel_ai_gateway" ], "aliases": [ "cortecs/llama-4-maverick", "digitalocean/llama-4-maverick", "helicone/llama-4-maverick", "kilo/meta-llama/llama-4-maverick", "nano-gpt/meta-llama/llama-4-maverick", "openrouter/meta-llama/llama-4-maverick", "vercel/meta/llama-4-maverick", "vercel_ai_gateway/meta/llama-4-maverick" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.151, "input": 0.124, "output": 0.603 } }, { "source": "models.dev", "provider": "digitalocean", "model": "llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.87 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "meta-llama/llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18000000000000002, "output": 0.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "vercel", "model": "meta/llama-4-maverick", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-4-maverick", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-4-maverick", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick", "Llama 4 Maverick 17B 128E Instruct", "Llama 4 Maverick 17B Instruct", "Llama-4-Maverick-17B-128E-Instruct-FP8", "Meta Llama 4 Maverick 17B 128E", "Meta: Llama 4 Maverick" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "llama-4-maverick", "modelKey": "llama-4-maverick", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "llama-4-maverick", "modelKey": "llama-4-maverick", "displayName": "Llama 4 Maverick 17B 128E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-4-maverick", "modelKey": "llama-4-maverick", "displayName": "Meta Llama 4 Maverick 17B 128E", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-4-maverick", "modelKey": "meta-llama/llama-4-maverick", "displayName": "Meta: Llama 4 Maverick", "metadata": { "lastUpdated": "2025-12-24", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meta-llama/llama-4-maverick", "modelKey": "meta-llama/llama-4-maverick", "displayName": "Llama 4 Maverick", "family": "llama", "metadata": { "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-4-maverick", "modelKey": "meta-llama/llama-4-maverick", "displayName": "Llama 4 Maverick", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-4-maverick", "modelKey": "meta/llama-4-maverick", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-4-maverick", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-4-maverick", "displayName": "Meta: Llama 4 Maverick", "metadata": { "canonicalSlug": "meta-llama/llama-4-maverick-17b-128e-instruct", "createdAt": "2025-04-05T19:37:02.000Z", "huggingFaceId": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama4", "topProvider": { "context_length": 1048576, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-4-maverick-17b", "provider": "meta-llama", "model": "llama-4-maverick-17b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-4-maverick-17b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-4-maverick-17b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-4-maverick-17b", "mode": "chat" } ] }, { "id": "meta-llama/llama-4-maverick-17b-128e-instruct", "provider": "meta-llama", "model": "llama-4-maverick-17b-128e-instruct", "displayName": "Llama 4 Maverick 17b 128e Instruct", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "groq", "nvidia", "sambanova" ], "aliases": [ "groq/meta-llama/llama-4-maverick-17b-128e-instruct", "nvidia/meta/llama-4-maverick-17b-128e-instruct", "sambanova/Llama-4-Maverick-17B-128E-Instruct" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-4-maverick-17b-128e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "groq", "model": "groq/meta-llama/llama-4-maverick-17b-128e-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/Llama-4-Maverick-17B-128E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.63, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17b 128e Instruct" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-02", "releaseDate": "2025-04-01", "lastUpdated": "2025-04-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-4-maverick-17b-128e-instruct", "modelKey": "meta/llama-4-maverick-17b-128e-instruct", "displayName": "Llama 4 Maverick 17b 128e Instruct", "metadata": { "knowledgeCutoff": "2024-02", "lastUpdated": "2025-04-01", "openWeights": true, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/meta-llama/llama-4-maverick-17b-128e-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Llama-4-Maverick-17B-128E-Instruct", "mode": "chat", "metadata": { "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "provider": "meta-llama", "model": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama 4 Maverick 17B FP8", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "azure_ai", "deepinfra", "github-models", "io-net", "lambda_ai", "llama", "meta_llama", "novita", "novita-ai", "synthetic", "together_ai" ], "aliases": [ "abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8", "azure/llama-4-maverick-17b-128e-instruct-fp8", "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "github-models/meta/llama-4-maverick-17b-128e-instruct-fp8", "io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "llama/llama-4-maverick-17b-128e-instruct-fp8", "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "novita-ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "synthetic/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" ], "mergedProviderModelRecords": 14, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 1048576, "outputTokens": 1048576, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": true, "temperature": true, "vision": true, "parallelFunctionCalling": true, "systemMessages": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.59 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "azure", "model": "llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "deepinfra", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "io-net", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.3, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "llama", "model": "llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.85 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.41, "output": 0.35 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "litellm", "provider": "meta_llama", "model": "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 0.85 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.27, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17B 128E Instruct", "Llama 4 Maverick 17B 128E Instruct FP8", "Llama 4 Maverick 17B FP8", "Llama 4 Maverick Instruct", "Llama-4-Maverick-17B-128E-Instruct-FP8" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 14 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "modelKey": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama 4 Maverick 17B 128E Instruct FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-4-maverick-17b-128e-instruct-fp8", "modelKey": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama 4 Maverick 17B 128E Instruct FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-4-maverick-17b-128e-instruct-fp8", "modelKey": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama 4 Maverick 17B 128E Instruct FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "modelKey": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama 4 Maverick 17B FP8", "family": "llama", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/llama-4-maverick-17b-128e-instruct-fp8", "modelKey": "meta/llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama 4 Maverick 17B 128E Instruct FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-31", "openWeights": true, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "modelKey": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama 4 Maverick 17B 128E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-15", "openWeights": true, "releaseDate": "2025-01-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "llama-4-maverick-17b-128e-instruct-fp8", "modelKey": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "modelKey": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "displayName": "Llama 4 Maverick Instruct", "metadata": { "lastUpdated": "2025-04-06", "openWeights": true, "releaseDate": "2025-04-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "modelKey": "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "meta_llama", "model": "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "metadata": { "source": "https://llama.developer.meta.com/docs/models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat" } ] }, { "id": "meta-llama/llama-4-maverick-17b-128e-instruct-maas", "provider": "meta-llama", "model": "llama-4-maverick-17b-128e-instruct-maas", "displayName": "Llama 4 Maverick 17B 128E Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-llama_models" ], "aliases": [ "google-vertex/meta/llama-4-maverick-17b-128e-instruct-maas", "vertex_ai-llama_models/vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "meta/llama-4-maverick-17b-128e-instruct-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.15 } }, { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17B 128E Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-29", "lastUpdated": "2025-04-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "meta/llama-4-maverick-17b-128e-instruct-maas", "modelKey": "meta/llama-4-maverick-17b-128e-instruct-maas", "displayName": "Llama 4 Maverick 17B 128E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-29", "openWeights": true, "releaseDate": "2025-04-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama-4-maverick-17b-16e-instruct-maas", "provider": "meta-llama", "model": "llama-4-maverick-17b-16e-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama-4-maverick-17b-instruct", "provider": "meta-llama", "model": "llama-4-maverick-17b-instruct", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/llama-4-maverick-17b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "llama-4-maverick-17b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.97 } } ] }, "metadata": { "displayNames": [ "Llama 4 Maverick 17B Instruct" ], "families": [ "llama" ], "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-4-maverick-17b-instruct", "modelKey": "llama-4-maverick-17b-instruct", "displayName": "Llama 4 Maverick 17B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "meta-llama/llama-4-scout", "provider": "meta-llama", "model": "llama-4-scout", "displayName": "Meta Llama 4 Scout 17B 16E", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "helicone", "kilo", "llmgateway", "nano-gpt", "openrouter", "vercel", "vercel_ai_gateway" ], "aliases": [ "helicone/llama-4-scout", "kilo/meta-llama/llama-4-scout", "llmgateway/llama-4-scout", "nano-gpt/meta-llama/llama-4-scout", "openrouter/meta-llama/llama-4-scout", "vercel/meta/llama-4-scout", "vercel_ai_gateway/meta/llama-4-scout" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 10000000, "inputTokens": 328000, "maxTokens": 8192, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.3 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.59 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "meta-llama/llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.085, "output": 0.46 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "vercel", "model": "meta/llama-4-scout", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-4-scout", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-4-scout", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Llama 4 Scout", "Llama-4-Scout-17B-16E-Instruct-FP8", "Meta Llama 4 Scout 17B 16E", "Meta: Llama 4 Scout" ], "families": [ "llama" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-4-scout", "modelKey": "llama-4-scout", "displayName": "Meta Llama 4 Scout 17B 16E", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-4-scout", "modelKey": "meta-llama/llama-4-scout", "displayName": "Meta: Llama 4 Scout", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-4-scout", "modelKey": "llama-4-scout", "displayName": "Llama 4 Scout", "family": "llama", "status": "beta", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meta-llama/llama-4-scout", "modelKey": "meta-llama/llama-4-scout", "displayName": "Llama 4 Scout", "family": "llama", "metadata": { "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-4-scout", "modelKey": "meta-llama/llama-4-scout", "displayName": "Llama 4 Scout", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meta/llama-4-scout", "modelKey": "meta/llama-4-scout", "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/meta/llama-4-scout", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-4-scout", "displayName": "Meta: Llama 4 Scout", "metadata": { "canonicalSlug": "meta-llama/llama-4-scout-17b-16e-instruct", "createdAt": "2025-04-05T19:31:59.000Z", "huggingFaceId": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Llama4", "topProvider": { "context_length": 327680, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-4-scout-17b-128e-instruct-maas", "provider": "meta-llama", "model": "llama-4-scout-17b-128e-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 10000000, "inputTokens": 10000000, "maxTokens": 10000000, "outputTokens": 10000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama-4-scout-17b-16e-instruct", "provider": "meta-llama", "model": "llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "github-models", "groq", "lambda_ai", "novita", "novita-ai", "nscale", "sambanova", "synthetic", "together_ai", "wandb" ], "aliases": [ "azure-cognitive-services/llama-4-scout-17b-16e-instruct", "azure/llama-4-scout-17b-16e-instruct", "azure_ai/Llama-4-Scout-17B-16E-Instruct", "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "github-models/meta/llama-4-scout-17b-16e-instruct", "groq/meta-llama/llama-4-scout-17b-16e-instruct", "lambda_ai/llama-4-scout-17b-16e-instruct", "novita-ai/meta-llama/llama-4-scout-17b-16e-instruct", "novita/meta-llama/llama-4-scout-17b-16e-instruct", "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct", "sambanova/Llama-4-Scout-17B-16E-Instruct", "synthetic/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct", "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 10000000, "inputTokens": 10000000, "maxTokens": 327680, "outputTokens": 327680, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": true, "structuredOutput": true, "temperature": true, "responseSchema": true, "vision": true, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.78 } }, { "source": "models.dev", "provider": "azure", "model": "llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.78 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.85 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.85 } }, { "source": "models.dev", "provider": "deepinfra", "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "groq", "model": "meta-llama/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.34 } }, { "source": "models.dev", "provider": "novita-ai", "model": "meta-llama/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.59 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "wandb", "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.66 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.78 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.3 } }, { "source": "litellm", "provider": "groq", "model": "groq/meta-llama/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.11, "output": 0.34 } }, { "source": "litellm", "provider": "lambda_ai", "model": "lambda_ai/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/meta-llama/llama-4-scout-17b-16e-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.59 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.29 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.7 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.59 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 17000, "output": 66000 } } ] }, "metadata": { "displayNames": [ "Llama 4 Scout 17B", "Llama 4 Scout 17B 16E", "Llama 4 Scout 17B 16E Instruct", "Llama 4 Scout Instruct", "Llama-4-Scout-17B-16E-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-4-scout-17b-16e-instruct", "modelKey": "llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "llama-4-scout-17b-16e-instruct", "modelKey": "llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "modelKey": "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-4-scout-17b-16e-instruct", "modelKey": "@cf/meta/llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "modelKey": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama 4 Scout 17B", "family": "llama", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/llama-4-scout-17b-16e-instruct", "modelKey": "meta/llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-31", "openWeights": true, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "meta-llama/llama-4-scout-17b-16e-instruct", "modelKey": "meta-llama/llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout 17B 16E", "family": "llama", "status": "beta", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "meta-llama/llama-4-scout-17b-16e-instruct", "modelKey": "meta-llama/llama-4-scout-17b-16e-instruct", "displayName": "Llama 4 Scout Instruct", "metadata": { "lastUpdated": "2025-04-06", "openWeights": true, "releaseDate": "2025-04-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", "modelKey": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "modelKey": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama 4 Scout 17B 16E Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2025-01-31" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/meta-llama/llama-4-scout-17b-16e-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lambda_ai", "model": "lambda_ai/llama-4-scout-17b-16e-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/meta-llama/llama-4-scout-17b-16e-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "metadata": { "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-4-scout-17b-16e-instruct-fp8", "provider": "meta-llama", "model": "llama-4-scout-17b-16e-instruct-fp8", "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llama", "meta_llama" ], "aliases": [ "llama/llama-4-scout-17b-16e-instruct-fp8", "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 10000000, "inputTokens": 10000000, "maxTokens": 4028, "outputTokens": 4096, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llama", "model": "llama-4-scout-17b-16e-instruct-fp8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "meta_llama", "model": "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Llama-4-Scout-17B-16E-Instruct-FP8" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llama", "providerName": "Llama", "providerApi": "https://api.llama.com/compat/v1/", "providerDoc": "https://llama.developer.meta.com/docs/models", "model": "llama-4-scout-17b-16e-instruct-fp8", "modelKey": "llama-4-scout-17b-16e-instruct-fp8", "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "meta_llama", "model": "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8", "mode": "chat", "metadata": { "source": "https://llama.developer.meta.com/docs/models" } } ] }, { "id": "meta-llama/llama-4-scout-17b-16e-instruct-maas", "provider": "meta-llama", "model": "llama-4-scout-17b-16e-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 10000000, "inputTokens": 10000000, "maxTokens": 10000000, "outputTokens": 10000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama-4-scout-17b-instruct", "provider": "meta-llama", "model": "llama-4-scout-17b-instruct", "displayName": "Llama 4 Scout 17B Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/llama-4-scout-17b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "llama-4-scout-17b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.66 } } ] }, "metadata": { "displayNames": [ "Llama 4 Scout 17B Instruct" ], "families": [ "llama" ], "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "llama-4-scout-17b-instruct", "modelKey": "llama-4-scout-17b-instruct", "displayName": "Llama 4 Scout 17B Instruct", "family": "llama", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } } ] }, { "id": "meta-llama/llama-guard-2-8b", "provider": "meta-llama", "model": "llama-guard-2-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b", "mode": "chat" } ] }, { "id": "meta-llama/llama-guard-3-11b-vision", "provider": "meta-llama", "model": "llama-guard-3-11b-vision", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/meta-llama/llama-guard-3-11b-vision" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/meta-llama/llama-guard-3-11b-vision", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.35 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/meta-llama/llama-guard-3-11b-vision", "mode": "chat" } ] }, { "id": "meta-llama/llama-guard-3-1b", "provider": "meta-llama", "model": "llama-guard-3-1b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b", "mode": "chat" } ] }, { "id": "meta-llama/llama-guard-3-8b", "provider": "meta-llama", "model": "llama-guard-3-8b", "displayName": "Llama Guard 3 8B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "fireworks_ai", "kilo", "nebius" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b", "cloudflare-workers-ai/@cf/meta/llama-guard-3-8b", "deepinfra/meta-llama/Llama-Guard-3-8B", "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b", "kilo/meta-llama/llama-guard-3-8b", "nebius/meta-llama/Llama-Guard-3-8B" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/llama-guard-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.48, "output": 0.03 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/meta/llama-guard-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.484, "output": 0.03 } }, { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-guard-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.06 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-Guard-3-8B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.055, "output": 0.055 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/meta-llama/Llama-Guard-3-8B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.06 } } ] }, "metadata": { "displayNames": [ "Llama Guard 3 8B" ], "families": [ "llama" ], "modes": [ "chat" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/llama-guard-3-8b", "modelKey": "workers-ai/@cf/meta/llama-guard-3-8b", "displayName": "Llama Guard 3 8B", "family": "llama", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/meta/llama-guard-3-8b", "modelKey": "@cf/meta/llama-guard-3-8b", "displayName": "Llama Guard 3 8B", "family": "llama", "metadata": { "lastUpdated": "2025-01-22", "openWeights": true, "releaseDate": "2025-01-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-guard-3-8b", "modelKey": "meta-llama/llama-guard-3-8b", "displayName": "Llama Guard 3 8B", "metadata": { "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-Guard-3-8B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/meta-llama/Llama-Guard-3-8B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "meta-llama/llama-guard-4", "provider": "meta-llama", "model": "llama-guard-4", "displayName": "Meta Llama Guard 4 12B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/llama-guard-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "llama-guard-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.21 } } ] }, "metadata": { "displayNames": [ "Meta Llama Guard 4 12B" ], "families": [ "llama" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-guard-4", "modelKey": "llama-guard-4", "displayName": "Meta Llama Guard 4 12B", "family": "llama", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "meta-llama/llama-guard-4-12b", "provider": "meta-llama", "model": "llama-guard-4-12b", "displayName": "Meta: Llama Guard 4 12B", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "deepinfra", "groq", "kilo", "nvidia", "openrouter" ], "aliases": [ "deepinfra/meta-llama/Llama-Guard-4-12B", "groq/meta-llama/llama-guard-4-12b", "kilo/meta-llama/llama-guard-4-12b", "nvidia/meta/llama-guard-4-12b", "openrouter/meta-llama/llama-guard-4-12b" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 163840, "inputTokens": 163840, "maxTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "meta-llama/llama-guard-4-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "models.dev", "provider": "nvidia", "model": "meta/llama-guard-4-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "meta-llama/llama-guard-4-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-Guard-4-12B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.18 } }, { "source": "litellm", "provider": "groq", "model": "groq/meta-llama/llama-guard-4-12b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "meta-llama/llama-guard-4-12b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.18 } } ] }, "metadata": { "displayNames": [ "Llama Guard 4 12B", "Meta: Llama Guard 4 12B" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-04-05", "lastUpdated": "2025-04-05", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "meta-llama/llama-guard-4-12b", "modelKey": "meta-llama/llama-guard-4-12b", "displayName": "Meta: Llama Guard 4 12B", "metadata": { "lastUpdated": "2025-04-05", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "meta/llama-guard-4-12b", "modelKey": "meta/llama-guard-4-12b", "displayName": "Llama Guard 4 12B", "family": "llama", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-04-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "meta-llama/llama-guard-4-12b", "modelKey": "meta-llama/llama-guard-4-12b", "displayName": "Llama Guard 4 12B", "family": "llama", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-04-30", "openWeights": true, "releaseDate": "2025-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Llama-Guard-4-12B", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/meta-llama/llama-guard-4-12b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "meta-llama/llama-guard-4-12b", "displayName": "Meta: Llama Guard 4 12B", "metadata": { "canonicalSlug": "meta-llama/llama-guard-4-12b", "createdAt": "2025-04-30T01:06:33.000Z", "huggingFaceId": "meta-llama/Llama-Guard-4-12B", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/meta-llama/llama-guard-4-12b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 163840, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "meta-llama/llama-nemotron-embed-vl-1b-v2", "provider": "meta-llama", "model": "llama-nemotron-embed-vl-1b-v2", "displayName": "llama-nemotron-embed-vl-1b-v2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/llama-nemotron-embed-vl-1b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/llama-nemotron-embed-vl-1b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "llama-nemotron-embed-vl-1b-v2" ], "families": [ "nemotron" ], "releaseDate": "2026-02-10", "lastUpdated": "2026-02-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/llama-nemotron-embed-vl-1b-v2", "modelKey": "nvidia/llama-nemotron-embed-vl-1b-v2", "displayName": "llama-nemotron-embed-vl-1b-v2", "family": "nemotron", "metadata": { "lastUpdated": "2026-02-10", "openWeights": true, "releaseDate": "2026-02-10" } } ] }, { "id": "meta-llama/llama-nemotron-rerank-vl-1b-v2", "provider": "meta-llama", "model": "llama-nemotron-rerank-vl-1b-v2", "displayName": "llama-nemotron-rerank-vl-1b-v2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/llama-nemotron-rerank-vl-1b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/llama-nemotron-rerank-vl-1b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "llama-nemotron-rerank-vl-1b-v2" ], "families": [ "nemotron" ], "releaseDate": "2026-03-31", "lastUpdated": "2026-03-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/llama-nemotron-rerank-vl-1b-v2", "modelKey": "nvidia/llama-nemotron-rerank-vl-1b-v2", "displayName": "llama-nemotron-rerank-vl-1b-v2", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-31", "openWeights": true, "releaseDate": "2026-03-31" } } ] }, { "id": "meta-llama/llama-prompt-guard-2-22m", "provider": "meta-llama", "model": "llama-prompt-guard-2-22m", "displayName": "Llama Prompt Guard 2 22M", "family": "llama", "sources": [ "models.dev" ], "providers": [ "groq", "helicone" ], "aliases": [ "groq/meta-llama/llama-prompt-guard-2-22m", "helicone/llama-prompt-guard-2-22m" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "groq", "model": "meta-llama/llama-prompt-guard-2-22m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.03 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-prompt-guard-2-22m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "displayNames": [ "Llama Prompt Guard 2 22M", "Meta Llama Prompt Guard 2 22M" ], "families": [ "llama" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-05-29", "lastUpdated": "2025-05-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "meta-llama/llama-prompt-guard-2-22m", "modelKey": "meta-llama/llama-prompt-guard-2-22m", "displayName": "Llama Prompt Guard 2 22M", "family": "llama", "status": "beta", "metadata": { "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-05-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-prompt-guard-2-22m", "modelKey": "llama-prompt-guard-2-22m", "displayName": "Meta Llama Prompt Guard 2 22M", "family": "llama", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-01", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "meta-llama/llama-prompt-guard-2-86m", "provider": "meta-llama", "model": "llama-prompt-guard-2-86m", "displayName": "Prompt Guard 2 86M", "family": "llama", "sources": [ "models.dev" ], "providers": [ "groq", "helicone" ], "aliases": [ "groq/meta-llama/llama-prompt-guard-2-86m", "helicone/llama-prompt-guard-2-86m" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "groq", "model": "meta-llama/llama-prompt-guard-2-86m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "models.dev", "provider": "helicone", "model": "llama-prompt-guard-2-86m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "displayNames": [ "Meta Llama Prompt Guard 2 86M", "Prompt Guard 2 86M" ], "families": [ "llama" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-05-29", "lastUpdated": "2025-05-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "meta-llama/llama-prompt-guard-2-86m", "modelKey": "meta-llama/llama-prompt-guard-2-86m", "displayName": "Prompt Guard 2 86M", "family": "llama", "status": "beta", "metadata": { "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-05-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "llama-prompt-guard-2-86m", "modelKey": "llama-prompt-guard-2-86m", "displayName": "Meta Llama Prompt Guard 2 86M", "family": "llama", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-01", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "meta-llama/llama-v2-13b", "provider": "meta-llama", "model": "llama-v2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-13b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v2-13b-chat", "provider": "meta-llama", "model": "llama-v2-13b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-v2-70b", "provider": "meta-llama", "model": "llama-v2-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-70b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v2-70b-chat", "provider": "meta-llama", "model": "llama-v2-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-v2-7b", "provider": "meta-llama", "model": "llama-v2-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-7b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v2-7b-chat", "provider": "meta-llama", "model": "llama-v2-7b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3-70b-instruct", "provider": "meta-llama", "model": "llama-v3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3-70b-instruct-hf", "provider": "meta-llama", "model": "llama-v3-70b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3-8b", "provider": "meta-llama", "model": "llama-v3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-8b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3-8b-instruct-hf", "provider": "meta-llama", "model": "llama-v3-8b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p1-405b-instruct", "provider": "meta-llama", "model": "llama-v3p1-405b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p1-405b-instruct-long", "provider": "meta-llama", "model": "llama-v3p1-405b-instruct-long", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p1-70b-instruct", "provider": "meta-llama", "model": "llama-v3p1-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p1-70b-instruct-1b", "provider": "meta-llama", "model": "llama-v3p1-70b-instruct-1b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p1-8b-instruct", "provider": "meta-llama", "model": "llama-v3p1-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p1-nemotron-70b-instruct", "provider": "meta-llama", "model": "llama-v3p1-nemotron-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p2-11b-vision-instruct", "provider": "meta-llama", "model": "llama-v3p2-11b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p2-1b", "provider": "meta-llama", "model": "llama-v3p2-1b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p2-1b-instruct", "provider": "meta-llama", "model": "llama-v3p2-1b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p2-3b", "provider": "meta-llama", "model": "llama-v3p2-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b", "mode": "chat" } ] }, { "id": "meta-llama/llama-v3p2-3b-instruct", "provider": "meta-llama", "model": "llama-v3p2-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p2-90b-vision-instruct", "provider": "meta-llama", "model": "llama-v3p2-90b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "meta-llama/llama-v3p3-70b-instruct", "provider": "meta-llama", "model": "llama-v3p3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct", "mode": "chat" } ] }, { "id": "meta-llama/llama-xlam-2-70b-fc-r", "provider": "meta-llama", "model": "llama-xlam-2-70b-fc-r", "displayName": "Llama-xLAM-2 70B fc-r", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Salesforce/Llama-xLAM-2-70b-fc-r" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Salesforce/Llama-xLAM-2-70b-fc-r", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Llama-xLAM-2 70B fc-r" ], "families": [ "llama" ], "releaseDate": "2025-04-13", "lastUpdated": "2025-04-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Salesforce/Llama-xLAM-2-70b-fc-r", "modelKey": "Salesforce/Llama-xLAM-2-70b-fc-r", "displayName": "Llama-xLAM-2 70B fc-r", "family": "llama", "metadata": { "lastUpdated": "2025-04-13", "openWeights": false, "releaseDate": "2025-04-13" } } ] }, { "id": "meta-llama/llama3-405b-instruct-maas", "provider": "meta-llama", "model": "llama3-405b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama3-405b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-405b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-405b-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama3-70b-instruct-maas", "provider": "meta-llama", "model": "llama3-70b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama3-70b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-70b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-70b-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/llama3-8b-instruct-maas", "provider": "meta-llama", "model": "llama3-8b-instruct-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-llama_models" ], "aliases": [ "vertex_ai-llama_models/vertex_ai/meta/llama3-8b-instruct-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-8b-instruct-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-llama_models", "model": "vertex_ai/meta/llama3-8b-instruct-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "meta-llama/m2m100-1.2b", "provider": "meta-llama", "model": "m2m100-1.2b", "displayName": "M2M100 1.2B", "family": "m2m", "sources": [ "models.dev" ], "providers": [ "cloudflare-ai-gateway" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/meta/m2m100-1.2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/meta/m2m100-1.2b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.34, "output": 0.34 } } ] }, "metadata": { "displayNames": [ "M2M100 1.2B" ], "families": [ "m2m" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/meta/m2m100-1.2b", "modelKey": "workers-ai/@cf/meta/m2m100-1.2b", "displayName": "M2M100 1.2B", "family": "m2m", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "meta-llama/meta-llama-3-1-70b-instruct", "provider": "meta-llama", "model": "meta-llama-3-1-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ovhcloud" ], "aliases": [ "ovhcloud/Meta-Llama-3_1-70B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "inputTokens": 131000, "maxTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Meta-Llama-3_1-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.67, "output": 0.67 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Meta-Llama-3_1-70B-Instruct", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct" } } ] }, { "id": "meta-llama/meta-llama-3-1-8b-instruct-fp8", "provider": "meta-llama", "model": "meta-llama-3-1-8b-instruct-fp8", "displayName": "Llama 3.1 8B (decentralized)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Meta-Llama-3-1-8B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B (decentralized)" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Meta-Llama-3-1-8B-Instruct-FP8", "modelKey": "Meta-Llama-3-1-8B-Instruct-FP8", "displayName": "Llama 3.1 8B (decentralized)", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "meta-llama/meta-llama-3-1-8b-instruct-gguf", "provider": "meta-llama", "model": "meta-llama-3-1-8b-instruct-gguf", "displayName": "Meta Llama 3.1 8B Instruct (GGUF)", "family": "llama", "sources": [ "models.dev" ], "providers": [ "atomic-chat" ], "aliases": [ "atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "atomic-chat", "model": "Meta-Llama-3_1-8B-Instruct-GGUF", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Meta Llama 3.1 8B Instruct (GGUF)" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "atomic-chat", "providerName": "Atomic Chat", "providerApi": "http://127.0.0.1:1337/v1", "providerDoc": "https://atomic.chat", "model": "Meta-Llama-3_1-8B-Instruct-GGUF", "modelKey": "Meta-Llama-3_1-8B-Instruct-GGUF", "displayName": "Meta Llama 3.1 8B Instruct (GGUF)", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "meta-llama/meta-llama-3-3-70b-instruct", "provider": "meta-llama", "model": "meta-llama-3-3-70b-instruct", "displayName": "Meta-Llama-3_3-70B-Instruct", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "ovhcloud" ], "aliases": [ "ovhcloud/Meta-Llama-3_3-70B-Instruct", "ovhcloud/meta-llama-3_3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131000, "maxTokens": 131000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "ovhcloud", "model": "meta-llama-3_3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.74, "output": 0.74 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Meta-Llama-3_3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.67, "output": 0.67 } } ] }, "metadata": { "displayNames": [ "Meta-Llama-3_3-70B-Instruct" ], "modes": [ "chat" ], "releaseDate": "2025-04-01", "lastUpdated": "2025-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "meta-llama-3_3-70b-instruct", "modelKey": "meta-llama-3_3-70b-instruct", "displayName": "Meta-Llama-3_3-70B-Instruct", "metadata": { "lastUpdated": "2025-04-01", "openWeights": true, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Meta-Llama-3_3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct" } } ] }, { "id": "meta-llama/meta-llama-3-70b-instruct", "provider": "meta-llama", "model": "meta-llama-3-70b-instruct", "displayName": "Meta-Llama-3-70B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anyscale", "azure", "azure-cognitive-services", "azure_ai", "github-models", "hyperbolic" ], "aliases": [ "anyscale/meta-llama/Meta-Llama-3-70B-Instruct", "azure-cognitive-services/meta-llama-3-70b-instruct", "azure/meta-llama-3-70b-instruct", "azure_ai/Meta-Llama-3-70B-Instruct", "github-models/meta/meta-llama-3-70b-instruct", "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "toolChoice": true, "functionCalling": true, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "meta-llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.68, "output": 3.54 } }, { "source": "models.dev", "provider": "azure", "model": "meta-llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.68, "output": 3.54 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/meta-llama-3-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "anyscale", "model": "anyscale/meta-llama/Meta-Llama-3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 0.37 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Meta-Llama-3-70B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-04-18", "lastUpdated": "2024-04-18", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3-70b-instruct", "modelKey": "meta-llama-3-70b-instruct", "displayName": "Meta-Llama-3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3-70b-instruct", "modelKey": "meta-llama-3-70b-instruct", "displayName": "Meta-Llama-3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/meta-llama-3-70b-instruct", "modelKey": "meta/meta-llama-3-70b-instruct", "displayName": "Meta-Llama-3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/meta-llama/Meta-Llama-3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct", "mode": "chat" } ] }, { "id": "meta-llama/meta-llama-3-70b-instruct-abliterated-v3.5", "provider": "meta-llama", "model": "meta-llama-3-70b-instruct-abliterated-v3.5", "displayName": "Llama 3 70B abliterated", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Llama 3 70B abliterated" ], "families": [ "llama" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5", "modelKey": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5", "displayName": "Llama 3 70B abliterated", "family": "llama", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "meta-llama/meta-llama-3-8b-instruct", "provider": "meta-llama", "model": "meta-llama-3-8b-instruct", "displayName": "Meta-Llama-3-8B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anyscale", "azure", "azure-cognitive-services", "deepinfra", "github-models" ], "aliases": [ "anyscale/meta-llama/Meta-Llama-3-8B-Instruct", "azure-cognitive-services/meta-llama-3-8b-instruct", "azure/meta-llama-3-8b-instruct", "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", "github-models/meta/meta-llama-3-8b-instruct" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "meta-llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.61 } }, { "source": "models.dev", "provider": "azure", "model": "meta-llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.61 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/meta-llama-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "anyscale", "model": "anyscale/meta-llama/Meta-Llama-3-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.06 } } ] }, "metadata": { "displayNames": [ "Meta-Llama-3-8B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-04-18", "lastUpdated": "2024-04-18", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3-8b-instruct", "modelKey": "meta-llama-3-8b-instruct", "displayName": "Meta-Llama-3-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3-8b-instruct", "modelKey": "meta-llama-3-8b-instruct", "displayName": "Meta-Llama-3-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/meta-llama-3-8b-instruct", "modelKey": "meta/meta-llama-3-8b-instruct", "displayName": "Meta-Llama-3-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/meta-llama/Meta-Llama-3-8B-Instruct", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", "mode": "chat" } ] }, { "id": "meta-llama/meta-llama-3-8b-instruct-lite", "provider": "meta-llama", "model": "meta-llama-3-8b-instruct-lite", "displayName": "Meta Llama 3 8B Instruct Lite", "family": "llama", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/meta-llama/Meta-Llama-3-8B-Instruct-Lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "meta-llama/Meta-Llama-3-8B-Instruct-Lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Meta Llama 3 8B Instruct Lite" ], "families": [ "llama" ], "releaseDate": "2024-04-18", "lastUpdated": "2024-04-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "meta-llama/Meta-Llama-3-8B-Instruct-Lite", "modelKey": "meta-llama/Meta-Llama-3-8B-Instruct-Lite", "displayName": "Meta Llama 3 8B Instruct Lite", "family": "llama", "metadata": { "lastUpdated": "2024-04-18", "openWeights": true, "releaseDate": "2024-04-18" } } ] }, { "id": "meta-llama/meta-llama-3.1-405b-instruct", "provider": "meta-llama", "model": "meta-llama-3.1-405b-instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "hyperbolic", "nebius", "sambanova" ], "aliases": [ "azure-cognitive-services/meta-llama-3.1-405b-instruct", "azure/meta-llama-3.1-405b-instruct", "azure_ai/Meta-Llama-3.1-405B-Instruct", "github-models/meta/meta-llama-3.1-405b-instruct", "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct", "sambanova/Meta-Llama-3.1-405B-Instruct" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "functionCalling": true, "parallelFunctionCalling": true, "systemMessages": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "meta-llama-3.1-405b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5.33, "output": 16 } }, { "source": "models.dev", "provider": "azure", "model": "meta-llama-3.1-405b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5.33, "output": 16 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/meta-llama-3.1-405b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-405B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.33, "output": 16 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.1-405B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Meta-Llama-3.1-405B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-405b-instruct", "modelKey": "meta-llama-3.1-405b-instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-405b-instruct", "modelKey": "meta-llama-3.1-405b-instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/meta-llama-3.1-405b-instruct", "modelKey": "meta/meta-llama-3.1-405b-instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-405B-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.1-405B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/meta-llama-3.1-405b-instruct-turbo", "provider": "meta-llama", "model": "meta-llama-3.1-405b-instruct-turbo", "displayName": "Llama 3.1 405B Instruct Turbo", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "together_ai" ], "aliases": [ "abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.5, "output": 3.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3.5, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 405B Instruct Turbo" ], "families": [ "llama" ], "modes": [ "chat" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "modelKey": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "displayName": "Llama 3.1 405B Instruct Turbo", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "meta-llama/meta-llama-3.1-70b-instruct", "provider": "meta-llama", "model": "meta-llama-3.1-70b-instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "deepinfra", "friendliai", "github-models", "hyperbolic", "nebius" ], "aliases": [ "azure-cognitive-services/meta-llama-3.1-70b-instruct", "azure/meta-llama-3.1-70b-instruct", "azure_ai/Meta-Llama-3.1-70B-Instruct", "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", "friendliai/meta-llama-3.1-70b-instruct", "github-models/meta/meta-llama-3.1-70b-instruct", "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "functionCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "meta-llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.68, "output": 3.54 } }, { "source": "models.dev", "provider": "azure", "model": "meta-llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.68, "output": 3.54 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/meta-llama-3.1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.68, "output": 3.54 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "litellm", "provider": "friendliai", "model": "friendliai/meta-llama-3.1-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Meta-Llama-3.1-70B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-70b-instruct", "modelKey": "meta-llama-3.1-70b-instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-70b-instruct", "modelKey": "meta-llama-3.1-70b-instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/meta-llama-3.1-70b-instruct", "modelKey": "meta/meta-llama-3.1-70b-instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-70B-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "friendliai", "model": "friendliai/meta-llama-3.1-70b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "meta-llama/meta-llama-3.1-70b-instruct-turbo", "provider": "meta-llama", "model": "meta-llama-3.1-70b-instruct-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra", "together_ai" ], "aliases": [ "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.28 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.88, "output": 0.88 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "meta-llama/meta-llama-3.1-8b-instruct", "provider": "meta-llama", "model": "meta-llama-3.1-8b-instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "azure_ai", "deepinfra", "friendliai", "github-models", "hyperbolic", "nebius", "sambanova" ], "aliases": [ "abacus/meta-llama/Meta-Llama-3.1-8B-Instruct", "azure-cognitive-services/meta-llama-3.1-8b-instruct", "azure/meta-llama-3.1-8b-instruct", "azure_ai/Meta-Llama-3.1-8B-Instruct", "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct", "friendliai/meta-llama-3.1-8b-instruct", "github-models/meta/meta-llama-3.1-8b-instruct", "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct", "sambanova/Meta-Llama-3.1-8B-Instruct" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "functionCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "meta-llama/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.05 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "meta-llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.61 } }, { "source": "models.dev", "provider": "azure", "model": "meta-llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.61 } }, { "source": "models.dev", "provider": "github-models", "model": "meta/meta-llama-3.1-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.61 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.05 } }, { "source": "litellm", "provider": "friendliai", "model": "friendliai/meta-llama-3.1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0.3 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.06 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.1-8B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B Instruct", "Meta-Llama-3.1-8B-Instruct" ], "families": [ "llama" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "meta-llama/Meta-Llama-3.1-8B-Instruct", "modelKey": "meta-llama/Meta-Llama-3.1-8B-Instruct", "displayName": "Llama 3.1 8B Instruct", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-8b-instruct", "modelKey": "meta-llama-3.1-8b-instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "meta-llama-3.1-8b-instruct", "modelKey": "meta-llama-3.1-8b-instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "meta/meta-llama-3.1-8b-instruct", "modelKey": "meta/meta-llama-3.1-8b-instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/Meta-Llama-3.1-8B-Instruct", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "friendliai", "model": "friendliai/meta-llama-3.1-8b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.1-8B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/meta-llama-3.1-8b-instruct-fp8", "provider": "meta-llama", "model": "meta-llama-3.1-8b-instruct-fp8", "displayName": "Llama 3.1 8B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "stackit" ], "aliases": [ "stackit/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.27 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8B" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelKey": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "displayName": "Llama 3.1 8B", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": true, "releaseDate": "2024-07-23" } } ] }, { "id": "meta-llama/meta-llama-3.1-8b-instruct-turbo", "provider": "meta-llama", "model": "meta-llama-3.1-8b-instruct-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "deepinfra", "together_ai" ], "aliases": [ "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": true, "responseSchema": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.03 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.18 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "mode": "chat" } ] }, { "id": "meta-llama/meta-llama-3.2-1b-instruct", "provider": "meta-llama", "model": "meta-llama-3.2-1b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sambanova" ], "aliases": [ "sambanova/Meta-Llama-3.2-1B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.2-1B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.08 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.2-1B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/meta-llama-3.2-3b-instruct", "provider": "meta-llama", "model": "meta-llama-3.2-3b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sambanova" ], "aliases": [ "sambanova/Meta-Llama-3.2-3B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.2-3B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.16 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.2-3B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/meta-llama-3.3-70b-instruct", "provider": "meta-llama", "model": "meta-llama-3.3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sambanova" ], "aliases": [ "sambanova/Meta-Llama-3.3-70B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.3-70B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-3.3-70B-Instruct", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "meta-llama/meta-llama-guard-3-8b", "provider": "meta-llama", "model": "meta-llama-guard-3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sambanova" ], "aliases": [ "sambanova/Meta-Llama-Guard-3-8B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sambanova", "model": "sambanova/Meta-Llama-Guard-3-8B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/Meta-Llama-Guard-3-8B", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } } ] }, { "id": "minimax/minimax-01", "provider": "minimax", "model": "minimax-01", "displayName": "MiniMax: MiniMax-01", "family": "minimax", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/minimax/minimax-01", "nano-gpt/minimax/minimax-01", "openrouter/minimax/minimax-01" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000192, "inputTokens": 1000192, "outputTokens": 1000192, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-01", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-01", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1394, "output": 1.1219999999999999 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-01", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-01", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "MiniMax 01", "MiniMax-01", "MiniMax: MiniMax-01" ], "families": [ "minimax" ], "knowledgeCutoff": "2024-03-31", "releaseDate": "2025-01-15", "lastUpdated": "2025-01-15", "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-01", "modelKey": "minimax/minimax-01", "displayName": "MiniMax: MiniMax-01", "metadata": { "lastUpdated": "2025-01-15", "openWeights": true, "releaseDate": "2025-01-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-01", "modelKey": "minimax/minimax-01", "displayName": "MiniMax 01", "family": "minimax", "metadata": { "lastUpdated": "2025-01-15", "openWeights": false, "releaseDate": "2025-01-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-01", "modelKey": "minimax/minimax-01", "displayName": "MiniMax-01", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-03-31", "lastUpdated": "2025-01-15", "openWeights": true, "releaseDate": "2025-01-15" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-01", "displayName": "MiniMax: MiniMax-01", "metadata": { "canonicalSlug": "minimax/minimax-01", "createdAt": "2025-01-15T04:31:02.000Z", "huggingFaceId": "MiniMaxAI/MiniMax-Text-01", "knowledgeCutoff": "2024-03-31", "links": { "details": "/api/v1/models/minimax/minimax-01/endpoints" }, "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1000192, "max_completion_tokens": 1000192, "is_moderated": false } } } ] }, { "id": "minimax/minimax-latest", "provider": "minimax", "model": "minimax-latest", "displayName": "MiniMax Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/minimax/minimax-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512000, "inputTokens": 512000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax Latest" ], "releaseDate": "2026-05-03", "lastUpdated": "2026-05-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-latest", "modelKey": "minimax/minimax-latest", "displayName": "MiniMax Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03" } } ] }, { "id": "minimax/minimax-m1", "provider": "minimax", "model": "minimax-m1", "displayName": "MiniMax-M1", "family": "minimax", "sources": [ "models.dev", "openrouter" ], "providers": [ "302ai", "kilo", "nano-gpt", "openrouter", "qiniu-ai" ], "aliases": [ "302ai/MiniMax-M1", "kilo/minimax/minimax-m1", "nano-gpt/MiniMax-M1", "openrouter/minimax/minimax-m1", "qiniu-ai/MiniMax-M1" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "MiniMax-M1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.132, "output": 1.254 } }, { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "MiniMax-M1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1394, "output": 1.3328 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M1", "MiniMax-M1", "MiniMax: MiniMax M1" ], "families": [ "minimax" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-06-16", "lastUpdated": "2025-06-16", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "MiniMax-M1", "modelKey": "MiniMax-M1", "displayName": "MiniMax-M1", "family": "minimax", "metadata": { "lastUpdated": "2025-06-16", "openWeights": false, "releaseDate": "2025-06-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m1", "modelKey": "minimax/minimax-m1", "displayName": "MiniMax: MiniMax M1", "metadata": { "lastUpdated": "2025-06-17", "openWeights": true, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "MiniMax-M1", "modelKey": "MiniMax-M1", "displayName": "MiniMax M1", "metadata": { "lastUpdated": "2025-06-16", "openWeights": false, "releaseDate": "2025-06-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m1", "modelKey": "minimax/minimax-m1", "displayName": "MiniMax M1", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-06-17", "openWeights": false, "releaseDate": "2025-06-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "MiniMax-M1", "modelKey": "MiniMax-M1", "displayName": "MiniMax M1", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m1", "displayName": "MiniMax: MiniMax M1", "metadata": { "canonicalSlug": "minimax/minimax-m1", "createdAt": "2025-06-17T22:46:54.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/minimax/minimax-m1/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1000000, "max_completion_tokens": 40000, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m1-80k", "provider": "minimax", "model": "minimax-m1-80k", "displayName": "MiniMax M1", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks_ai", "jiekou", "nano-gpt", "novita", "novita-ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/minimax-m1-80k", "jiekou/minimaxai/minimax-m1-80k", "nano-gpt/MiniMaxAI/MiniMax-M1-80k", "novita-ai/minimaxai/minimax-m1-80k", "novita/minimaxai/minimax-m1-80k" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 40000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "parallelFunctionCalling": true, "systemMessages": true, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "minimaxai/minimax-m1-80k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "MiniMaxAI/MiniMax-M1-80k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6052, "output": 2.4225000000000003 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimaxai/minimax-m1-80k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m1-80k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/minimaxai/minimax-m1-80k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M1", "MiniMax M1 80K" ], "families": [ "minimax" ], "modes": [ "chat" ], "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "minimaxai/minimax-m1-80k", "modelKey": "minimaxai/minimax-m1-80k", "displayName": "MiniMax M1", "family": "minimax", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "MiniMaxAI/MiniMax-M1-80k", "modelKey": "MiniMaxAI/MiniMax-M1-80k", "displayName": "MiniMax M1 80K", "family": "minimax", "metadata": { "lastUpdated": "2025-06-16", "openWeights": false, "releaseDate": "2025-06-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimaxai/minimax-m1-80k", "modelKey": "minimaxai/minimax-m1-80k", "displayName": "MiniMax M1", "family": "minimax", "metadata": { "lastUpdated": "2025-06-17", "openWeights": true, "releaseDate": "2025-06-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m1-80k", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/minimaxai/minimax-m1-80k", "mode": "chat" } ] }, { "id": "minimax/minimax-m2", "provider": "minimax", "model": "minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "cortecs", "fireworks_ai", "kilo", "llmgateway", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "nano-gpt", "novita", "novita-ai", "ollama-cloud", "openrouter", "qiniu-ai", "synthetic", "vercel", "zenmux" ], "aliases": [ "302ai/MiniMax-M2", "cortecs/minimax-m2", "fireworks_ai/accounts/fireworks/models/minimax-m2", "kilo/minimax/minimax-m2", "llmgateway/minimax-m2", "merge-gateway/minimax/minimax-m2", "minimax-cn-coding-plan/MiniMax-M2", "minimax-cn/MiniMax-M2", "minimax-coding-plan/MiniMax-M2", "minimax/MiniMax-M2", "nano-gpt/MiniMax-M2", "novita-ai/minimax/minimax-m2", "novita/minimax/minimax-m2", "ollama-cloud/minimax-m2", "openrouter/minimax/minimax-m2", "qiniu-ai/minimax/minimax-m2", "synthetic/hf:MiniMaxAI/MiniMax-M2", "vercel/minimax/minimax-m2", "zenmux/minimax/minimax-m2" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 1000000, "inputTokens": 204800, "maxTokens": 204800, "outputTokens": 400000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 1.32 } }, { "source": "models.dev", "provider": "cortecs", "model": "minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.39, "output": 1.57 } }, { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.255, "output": 1 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 1.53 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.255, "output": 1 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:MiniMaxAI/MiniMax-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.38, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/minimax/minimax-m2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 }, "extra": { "input_cost_per_token_cache_hit": 3e-8 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.255, "output": 1.02 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.255, "output": 1 } } ] }, "metadata": { "displayNames": [ "MiniMax M2", "MiniMax-M2", "MiniMax: MiniMax M2", "Minimax/Minimax-M2", "minimax-m2" ], "families": [ "minimax" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-11", "releaseDate": "2025-10-26", "lastUpdated": "2025-10-26", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax-M2", "metadata": { "lastUpdated": "2025-10-26", "openWeights": false, "releaseDate": "2025-10-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "minimax-m2", "modelKey": "minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax: MiniMax M2", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-10-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2", "modelKey": "minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "MiniMax-M2", "modelKey": "MiniMax-M2", "displayName": "MiniMax M2", "metadata": { "lastUpdated": "2025-10-25", "openWeights": false, "releaseDate": "2025-10-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "minimax-m2", "modelKey": "minimax-m2", "displayName": "minimax-m2", "family": "minimax", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-10-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "Minimax/Minimax-M2", "metadata": { "lastUpdated": "2025-10-28", "openWeights": false, "releaseDate": "2025-10-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:MiniMaxAI/MiniMax-M2", "modelKey": "hf:MiniMaxAI/MiniMax-M2", "displayName": "MiniMax-M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax M2", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2", "modelKey": "minimax/minimax-m2", "displayName": "MiniMax M2", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-10-27", "openWeights": false, "releaseDate": "2025-10-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/minimax/minimax-m2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m2", "displayName": "MiniMax: MiniMax M2", "metadata": { "canonicalSlug": "minimax/minimax-m2", "createdAt": "2025-10-23T20:41:33.000Z", "huggingFaceId": "MiniMaxAI/MiniMax-M2", "links": { "details": "/api/v1/models/minimax/minimax-m2/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 196608, "max_completion_tokens": 196608, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m2-5", "provider": "minimax", "model": "minimax-m2-5", "displayName": "MiniMax-M2.5", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "frogbot" ], "aliases": [ "frogbot/minimax-m2-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 192000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "minimax-m2-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.5" ], "families": [ "minimax" ], "knowledgeCutoff": "2024-09", "releaseDate": "2025-01-15", "lastUpdated": "2025-02-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "minimax-m2-5", "modelKey": "minimax-m2-5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-02-22", "openWeights": false, "releaseDate": "2025-01-15" } } ] }, { "id": "minimax/minimax-m2-5-high-throughput", "provider": "minimax", "model": "minimax-m2-5-high-throughput", "displayName": "MiniMax-M2.5 High Throughput", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.5 High Throughput" ], "families": [ "minimax" ], "releaseDate": "2026-02-12", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput", "modelKey": "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput", "displayName": "MiniMax-M2.5 High Throughput", "family": "minimax", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2026-02-12" } } ] }, { "id": "minimax/minimax-m2-7", "provider": "minimax", "model": "minimax-m2-7", "displayName": "MiniMax-M2.7", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "auriko", "frogbot" ], "aliases": [ "auriko/minimax-m2-7", "frogbot/minimax-m2-7" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "auriko", "model": "minimax-m2-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "frogbot", "model": "minimax-m2-7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.7" ], "families": [ "minimax" ], "knowledgeCutoff": "2024-09", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "minimax-m2-7", "modelKey": "minimax-m2-7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "minimax-m2-7", "modelKey": "minimax-m2-7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "minimax/minimax-m2-7-highspeed", "provider": "minimax", "model": "minimax-m2-7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "auriko" ], "aliases": [ "auriko/minimax-m2-7-highspeed" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "auriko", "model": "minimax-m2-7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.7-highspeed" ], "families": [ "minimax" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "minimax-m2-7-highspeed", "modelKey": "minimax-m2-7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "minimax/minimax-m2-her", "provider": "minimax", "model": "minimax-m2-her", "displayName": "MiniMax: MiniMax M2-her", "family": "minimax", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/minimax/minimax-m2-her", "nano-gpt/minimax/minimax-m2-her", "openrouter/minimax/minimax-m2-her" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 65536, "inputTokens": 65532, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m2-her", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m2-her", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.30200000000000005, "output": 1.2069999999999999 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m2-her", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m2-her", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M2-her", "MiniMax: MiniMax M2-her" ], "families": [ "minimax" ], "releaseDate": "2026-01-23", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m2-her", "modelKey": "minimax/minimax-m2-her", "displayName": "MiniMax: MiniMax M2-her", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-01-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m2-her", "modelKey": "minimax/minimax-m2-her", "displayName": "MiniMax M2-her", "family": "minimax", "metadata": { "lastUpdated": "2026-01-24", "openWeights": false, "releaseDate": "2026-01-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m2-her", "modelKey": "minimax/minimax-m2-her", "displayName": "MiniMax M2-her", "family": "minimax", "metadata": { "lastUpdated": "2026-01-23", "openWeights": false, "releaseDate": "2026-01-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m2-her", "displayName": "MiniMax: MiniMax M2-her", "metadata": { "canonicalSlug": "minimax/minimax-m2-her-20260123", "createdAt": "2026-01-23T14:07:19.000Z", "links": { "details": "/api/v1/models/minimax/minimax-m2-her-20260123/endpoints" }, "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 65536, "max_completion_tokens": 2048, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m2-maas", "provider": "minimax", "model": "minimax-m2-maas", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-minimax_models" ], "aliases": [ "vertex_ai-minimax_models/vertex_ai/minimaxai/minimax-m2-maas" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 196608, "inputTokens": 196608, "maxTokens": 196608, "outputTokens": 196608, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-minimax_models", "model": "vertex_ai/minimaxai/minimax-m2-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-minimax_models", "model": "vertex_ai/minimaxai/minimax-m2-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "minimax/minimax-m2.1", "provider": "minimax", "model": "minimax-m2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "cortecs", "gmi", "huggingface", "jiekou", "kilo", "llmgateway", "meganova", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "moark", "nano-gpt", "novita", "novita-ai", "ollama-cloud", "opencode", "openrouter", "poe", "qiniu-ai", "siliconflow-cn", "synthetic", "vercel", "zenmux" ], "aliases": [ "302ai/MiniMax-M2.1", "cortecs/minimax-m2.1", "gmi/MiniMaxAI/MiniMax-M2.1", "huggingface/MiniMaxAI/MiniMax-M2.1", "jiekou/minimax/minimax-m2.1", "kilo/minimax/minimax-m2.1", "llmgateway/minimax-m2.1", "meganova/MiniMaxAI/MiniMax-M2.1", "merge-gateway/minimax/minimax-m2.1", "minimax-cn-coding-plan/MiniMax-M2.1", "minimax-cn/MiniMax-M2.1", "minimax-coding-plan/MiniMax-M2.1", "minimax/MiniMax-M2.1", "moark/MiniMax-M2.1", "nano-gpt/minimax/minimax-m2.1", "novita-ai/minimax/minimax-m2.1", "novita/minimax/minimax-m2.1", "ollama-cloud/minimax-m2.1", "opencode/minimax-m2.1", "openrouter/minimax/minimax-m2.1", "poe/novita/minimax-m2.1", "qiniu-ai/minimax/minimax-m2.1", "siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.1", "synthetic/hf:MiniMaxAI/MiniMax-M2.1", "vercel/minimax/minimax-m2.1", "zenmux/minimax/minimax-m2.1" ], "mergedProviderModelRecords": 26, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 131072, "outputTokens": 196608, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": true, "structuredOutput": true, "computerUse": false, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "cortecs", "model": "minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.34, "output": 1.34 } }, { "source": "models.dev", "provider": "huggingface", "model": "MiniMaxAI/MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "jiekou", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.27, "output": 0.95 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "meganova", "model": "MiniMaxAI/MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "moark", "model": "MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.1, "output": 8.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 1.32 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode", "model": "minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.29, "output": 0.95 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/MiniMaxAI/MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:MiniMaxAI/MiniMax-M2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.38, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/MiniMaxAI/MiniMax-M2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/minimax/minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 }, "extra": { "input_cost_per_token_cache_hit": 3e-8 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0.27, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m2.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.29, "output": 0.95 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.1", "MiniMax-M2.1", "MiniMax: MiniMax M2.1", "Minimax M2.1", "Minimax/Minimax-M2.1", "Pro/MiniMaxAI/MiniMax-M2.1", "minimax-m2.1" ], "families": [ "minimax" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-10", "releaseDate": "2025-12-19", "lastUpdated": "2025-12-19", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 26 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "metadata": { "lastUpdated": "2025-12-19", "openWeights": false, "releaseDate": "2025-12-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "minimax-m2.1", "modelKey": "minimax-m2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "MiniMaxAI/MiniMax-M2.1", "modelKey": "MiniMaxAI/MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "Minimax M2.1", "family": "minimax", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 131071 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax: MiniMax M2.1", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.1", "modelKey": "minimax-m2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "MiniMaxAI/MiniMax-M2.1", "modelKey": "MiniMaxAI/MiniMax-M2.1", "displayName": "MiniMax M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moark", "providerName": "Moark", "providerApi": "https://moark.com/v1", "providerDoc": "https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90", "model": "MiniMax-M2.1", "modelKey": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-19", "openWeights": false, "releaseDate": "2025-12-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "Minimax M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "minimax-m2.1", "modelKey": "minimax-m2.1", "displayName": "minimax-m2.1", "family": "minimax", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.1", "modelKey": "minimax-m2.1", "displayName": "MiniMax M2.1", "family": "minimax", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/minimax-m2.1", "modelKey": "novita/minimax-m2.1", "displayName": "minimax-m2.1", "metadata": { "lastUpdated": "2025-12-26", "openWeights": false, "releaseDate": "2025-12-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "Minimax/Minimax-M2.1", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/MiniMaxAI/MiniMax-M2.1", "modelKey": "Pro/MiniMaxAI/MiniMax-M2.1", "displayName": "Pro/MiniMaxAI/MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:MiniMaxAI/MiniMax-M2.1", "modelKey": "hf:MiniMaxAI/MiniMax-M2.1", "displayName": "MiniMax-M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax M2.1", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-10-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2.1", "modelKey": "minimax/minimax-m2.1", "displayName": "MiniMax M2.1", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/MiniMaxAI/MiniMax-M2.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M2.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/minimax/minimax-m2.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2.1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m2.1", "displayName": "MiniMax: MiniMax M2.1", "metadata": { "canonicalSlug": "minimax/minimax-m2.1", "createdAt": "2025-12-23T01:56:37.000Z", "huggingFaceId": "MiniMaxAI/MiniMax-M2.1", "links": { "details": "/api/v1/models/minimax/minimax-m2.1/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 196608, "max_completion_tokens": 196608, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m2.1-free", "provider": "minimax", "model": "minimax-m2.1-free", "displayName": "MiniMax M2.1 Free", "family": "minimax-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/minimax-m2.1-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "minimax-m2.1-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.1 Free" ], "families": [ "minimax-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.1-free", "modelKey": "minimax-m2.1-free", "displayName": "MiniMax M2.1 Free", "family": "minimax-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } } ] }, { "id": "minimax/minimax-m2.1-lightning", "provider": "minimax", "model": "minimax-m2.1-lightning", "displayName": "MiniMax M2.1 Lightning", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "minimax", "vercel" ], "aliases": [ "llmgateway/minimax-m2.1-lightning", "minimax/MiniMax-M2.1-lightning", "vercel/minimax/minimax-m2.1-lightning" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true, "attachments": false, "openWeights": true, "structuredOutput": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.1-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.48 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.1-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 2.4 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M2.1-lightning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.1 Lightning" ], "families": [ "minimax" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.1-lightning", "modelKey": "minimax-m2.1-lightning", "displayName": "MiniMax M2.1 Lightning", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.1-lightning", "modelKey": "minimax/minimax-m2.1-lightning", "displayName": "MiniMax M2.1 Lightning", "family": "minimax", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-27", "openWeights": false, "releaseDate": "2025-10-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M2.1-lightning", "mode": "chat" } ] }, { "id": "minimax/minimax-m2.5", "provider": "minimax", "model": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "baseten", "cloudferro-sherlock", "cortecs", "crof", "deepinfra", "digitalocean", "dinference", "friendli", "hpc-ai", "huggingface", "inceptron", "kilo", "llmgateway", "meganova", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "nano-gpt", "nebius", "novita-ai", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "qiniu-ai", "regolo-ai", "routing-run", "siliconflow", "siliconflow-cn", "synthetic", "tencent-coding-plan", "togetherai", "vercel", "wandb", "zenmux" ], "aliases": [ "alibaba-cn/MiniMax-M2.5", "alibaba-coding-plan-cn/MiniMax-M2.5", "alibaba-coding-plan/MiniMax-M2.5", "alibaba-token-plan-cn/MiniMax-M2.5", "alibaba-token-plan/MiniMax-M2.5", "baseten/MiniMaxAI/MiniMax-M2.5", "cloudferro-sherlock/MiniMaxAI/MiniMax-M2.5", "cortecs/minimax-m2.5", "crof/minimax-m2.5", "deepinfra/MiniMaxAI/MiniMax-M2.5", "digitalocean/minimax-m2.5", "dinference/minimax-m2.5", "friendli/MiniMaxAI/MiniMax-M2.5", "hpc-ai/minimax/minimax-m2.5", "huggingface/MiniMaxAI/MiniMax-M2.5", "inceptron/MiniMaxAI/MiniMax-M2.5", "kilo/minimax/minimax-m2.5", "llmgateway/minimax-m2.5", "meganova/MiniMaxAI/MiniMax-M2.5", "merge-gateway/minimax/minimax-m2.5", "minimax-cn-coding-plan/MiniMax-M2.5", "minimax-cn/MiniMax-M2.5", "minimax-coding-plan/MiniMax-M2.5", "minimax/MiniMax-M2.5", "nano-gpt/TEE/minimax-m2.5", "nano-gpt/minimax/minimax-m2.5", "nebius/MiniMaxAI/MiniMax-M2.5", "novita-ai/minimax/minimax-m2.5", "ollama-cloud/minimax-m2.5", "opencode-go/minimax-m2.5", "opencode/minimax-m2.5", "openrouter/minimax/minimax-m2.5", "orcarouter/minimax/minimax-m2.5", "qiniu-ai/minimax/minimax-m2.5", "regolo-ai/minimax-m2.5", "routing-run/route/minimax-m2.5", "siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.5", "siliconflow/MiniMaxAI/MiniMax-M2.5", "synthetic/hf:MiniMaxAI/MiniMax-M2.5", "tencent-coding-plan/minimax-m2.5", "togetherai/MiniMaxAI/MiniMax-M2.5", "vercel/minimax/minimax-m2.5", "wandb/MiniMaxAI/MiniMax-M2.5", "zenmux/minimax/minimax-m2.5" ], "mergedProviderModelRecords": 44, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 197000, "outputTokens": 204000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": true, "structuredOutput": true, "computerUse": false, "vision": false, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-cn", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "baseten", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "cloudferro-sherlock", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "cortecs", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.32, "output": 1.18 } }, { "source": "models.dev", "provider": "crof", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.375, "input": 0.11, "output": 0.95 } }, { "source": "models.dev", "provider": "deepinfra", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.15, "output": 1.15 } }, { "source": "models.dev", "provider": "digitalocean", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "dinference", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 0.88 } }, { "source": "models.dev", "provider": "friendli", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "hpc-ai", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "huggingface", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "inceptron", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.24, "output": 0.9 } }, { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.029, "input": 0.25, "output": 1.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "meganova", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.38 } }, { "source": "models.dev", "provider": "nebius", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode-go", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.15, "output": 0.9 } }, { "source": "models.dev", "provider": "orcarouter", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 3.5 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.193, "output": 1.238 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.22 } }, { "source": "models.dev", "provider": "siliconflow", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "tencent-coding-plan", "model": "minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "togetherai", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "wandb", "model": "MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 1.1 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/MiniMaxAI/MiniMax-M2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m2.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.15, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "MiniMax 2.5", "MiniMax M2.5", "MiniMax M2.5 TEE", "MiniMax-M2.5", "MiniMax: MiniMax M2.5", "MiniMaxAI/MiniMax-M2.5", "Minimax/Minimax-M2.5", "Pro/MiniMaxAI/MiniMax-M2.5", "minimax-m2.5" ], "families": [ "minimax", "minimax-m2.5" ], "modes": [ "chat" ], "statuses": [ "beta", "deprecated" ], "knowledgeCutoff": "2026-01", "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 44 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudferro-sherlock", "providerName": "CloudFerro Sherlock", "providerApi": "https://api-sherlock.cloudferro.com/openai/v1/", "providerDoc": "https://docs.sherlock.cloudferro.com/", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-03-05", "openWeights": true, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax-m2.5", "status": "beta", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "dinference", "providerName": "DInference", "providerApi": "https://api.dinference.com/v1", "providerDoc": "https://dinference.com", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "hpc-ai", "providerName": "HPC-AI", "providerApi": "https://api.hpc-ai.com/inference/v1", "providerDoc": "https://www.hpc-ai.com/doc/docs/quickstart/", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax-m2.5", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inceptron", "providerName": "Inceptron", "providerApi": "https://api.inceptron.io/v1", "providerDoc": "https://docs.inceptron.io", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax: MiniMax M2.5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2.5", "modelKey": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/minimax-m2.5", "modelKey": "TEE/minimax-m2.5", "displayName": "MiniMax M2.5 TEE", "metadata": { "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "minimax-m2.5", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax-m2.5", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "Minimax/Minimax-M2.5", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax 2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-03-10", "openWeights": false, "releaseDate": "2026-03-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/minimax-m2.5", "modelKey": "route/minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/MiniMaxAI/MiniMax-M2.5", "modelKey": "Pro/MiniMaxAI/MiniMax-M2.5", "displayName": "Pro/MiniMaxAI/MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMaxAI/MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-06-15", "openWeights": false, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:MiniMaxAI/MiniMax-M2.5", "modelKey": "hf:MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-07", "openWeights": true, "releaseDate": "2026-02-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "minimax-m2.5", "modelKey": "minimax-m2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax-M2.5", "family": "minimax", "status": "deprecated", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "MiniMaxAI/MiniMax-M2.5", "modelKey": "MiniMaxAI/MiniMax-M2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2.5", "modelKey": "minimax/minimax-m2.5", "displayName": "MiniMax M2.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2026-02-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/MiniMaxAI/MiniMax-M2.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M2.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/minimax/minimax-m2.5", "mode": "chat", "metadata": { "source": "https://openrouter.ai/minimax/minimax-m2.5" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/MiniMaxAI/MiniMax-M2.5", "mode": "chat", "metadata": { "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m2.5", "displayName": "MiniMax: MiniMax M2.5", "metadata": { "canonicalSlug": "minimax/minimax-m2.5-20260211", "createdAt": "2026-02-12T15:01:42.000Z", "huggingFaceId": "MiniMaxAI/MiniMax-M2.5", "links": { "details": "/api/v1/models/minimax/minimax-m2.5-20260211/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 196608, "max_completion_tokens": 196608, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m2.5-fast", "provider": "minimax", "model": "minimax-m2.5-fast", "displayName": "MiniMax-M2.5-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/MiniMaxAI/MiniMax-M2.5-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "MiniMaxAI/MiniMax-M2.5-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.5-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-20", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "MiniMaxAI/MiniMax-M2.5-fast", "modelKey": "MiniMaxAI/MiniMax-M2.5-fast", "displayName": "MiniMax-M2.5-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-01-20" } } ] }, { "id": "minimax/minimax-m2.5-free", "provider": "minimax", "model": "minimax-m2.5-free", "displayName": "MiniMax M2.5 Free", "family": "minimax-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/minimax-m2.5-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "minimax-m2.5-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5 Free" ], "families": [ "minimax-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.5-free", "modelKey": "minimax-m2.5-free", "displayName": "MiniMax M2.5 Free", "family": "minimax-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } } ] }, { "id": "minimax/minimax-m2.5-highspeed", "provider": "minimax", "model": "minimax-m2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "llmgateway", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "novita-ai", "orcarouter", "qiniu-ai", "routing-run", "vercel" ], "aliases": [ "llmgateway/minimax-m2.5-highspeed", "merge-gateway/minimax/minimax-m2.5-highspeed", "minimax-cn-coding-plan/MiniMax-M2.5-highspeed", "minimax-cn/MiniMax-M2.5-highspeed", "minimax-coding-plan/MiniMax-M2.5-highspeed", "minimax/MiniMax-M2.5-highspeed", "novita-ai/minimax/minimax-m2.5-highspeed", "orcarouter/minimax/minimax-m2.5-highspeed", "qiniu-ai/minimax/minimax-m2.5-highspeed", "routing-run/route/minimax-m2.5-highspeed", "vercel/minimax/minimax-m2.5-highspeed" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 204800, "outputTokens": 131100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "orcarouter", "model": "minimax/minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.193, "output": 1.238 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.5-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5 High Speed", "MiniMax M2.5 Highspeed", "MiniMax-M2.5-highspeed", "Minimax/Minimax-M2.5 Highspeed" ], "families": [ "minimax", "minimax-m2.5" ], "releaseDate": "2026-02-13", "lastUpdated": "2026-02-13", "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.5-highspeed", "modelKey": "minimax-m2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2.5-highspeed", "modelKey": "minimax/minimax-m2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2.5-highspeed", "modelKey": "MiniMax-M2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2.5-highspeed", "modelKey": "MiniMax-M2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2.5-highspeed", "modelKey": "MiniMax-M2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2.5-highspeed", "modelKey": "MiniMax-M2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2.5-highspeed", "modelKey": "minimax/minimax-m2.5-highspeed", "displayName": "MiniMax M2.5 Highspeed", "family": "minimax-m2.5", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "minimax/minimax-m2.5-highspeed", "modelKey": "minimax/minimax-m2.5-highspeed", "displayName": "MiniMax-M2.5-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "minimax/minimax-m2.5-highspeed", "modelKey": "minimax/minimax-m2.5-highspeed", "displayName": "Minimax/Minimax-M2.5 Highspeed", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/minimax-m2.5-highspeed", "modelKey": "route/minimax-m2.5-highspeed", "displayName": "MiniMax M2.5 Highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-02-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.5-highspeed", "modelKey": "minimax/minimax-m2.5-highspeed", "displayName": "MiniMax M2.5 High Speed", "family": "minimax", "metadata": { "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2026-02-12" } } ] }, { "id": "minimax/minimax-m2.5-lightning", "provider": "minimax", "model": "minimax-m2.5-lightning", "displayName": "MiniMax M2.5 highspeed", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "minimax", "zenmux" ], "aliases": [ "minimax/MiniMax-M2.5-lightning", "zenmux/minimax/minimax-m2.5-lightning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true, "attachments": false, "openWeights": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2.5-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.75, "input": 0.6, "output": 4.8 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M2.5-lightning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.375, "input": 0.3, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5 highspeed" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-02-13", "lastUpdated": "2026-02-13", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2.5-lightning", "modelKey": "minimax/minimax-m2.5-lightning", "displayName": "MiniMax M2.5 highspeed", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2026-02-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M2.5-lightning", "mode": "chat" } ] }, { "id": "minimax/minimax-m2.5-tee", "provider": "minimax", "model": "minimax-m2.5-tee", "displayName": "MiniMax M2.5 TEE", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/MiniMaxAI/MiniMax-M2.5-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 196608, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "MiniMaxAI/MiniMax-M2.5-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5 TEE" ], "families": [ "minimax" ], "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "MiniMaxAI/MiniMax-M2.5-TEE", "modelKey": "MiniMaxAI/MiniMax-M2.5-TEE", "displayName": "MiniMax M2.5 TEE", "family": "minimax", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } } ] }, { "id": "minimax/minimax-m2.7", "provider": "minimax", "model": "minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "aihubmix", "alibaba-cn", "cortecs", "fastrouter", "huggingface", "kilo", "lilac", "llmgateway", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "nano-gpt", "novita-ai", "nvidia", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "routing-run", "sambanova", "togetherai", "vercel", "vultr", "zenmux" ], "aliases": [ "302ai/MiniMax-M2.7", "aihubmix/minimax-m2.7", "alibaba-cn/MiniMax/MiniMax-M2.7", "cortecs/minimax-m2.7", "fastrouter/minimax/minimax-m2.7", "huggingface/MiniMaxAI/MiniMax-M2.7", "kilo/minimax/minimax-m2.7", "lilac/minimaxai/minimax-m2.7", "llmgateway/minimax-m2.7", "merge-gateway/minimax/minimax-m2.7", "minimax-cn-coding-plan/MiniMax-M2.7", "minimax-cn/MiniMax-M2.7", "minimax-coding-plan/MiniMax-M2.7", "minimax/MiniMax-M2.7", "nano-gpt/minimax/minimax-m2.7", "novita-ai/minimax/minimax-m2.7", "nvidia/minimaxai/minimax-m2.7", "ollama-cloud/minimax-m2.7", "opencode-go/minimax-m2.7", "opencode/minimax-m2.7", "openrouter/minimax/minimax-m2.7", "orcarouter/minimax/minimax-m2.7", "routing-run/route/minimax-m2.7", "sambanova/MiniMax-M2.7", "togetherai/MiniMaxAI/MiniMax-M2.7", "vercel/minimax/minimax-m2.7", "vultr/MiniMaxAI/MiniMax-M2.7", "zenmux/minimax/minimax-m2.7" ], "mergedProviderModelRecords": 28, "limits": { "contextTokens": 204800, "inputTokens": 204800, "maxTokens": 131072, "outputTokens": 204800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "aihubmix", "model": "minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "MiniMax/MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "cortecs", "model": "minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.47, "output": 1.4 } }, { "source": "models.dev", "provider": "fastrouter", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "huggingface", "model": "MiniMaxAI/MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "kilo", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "lilac", "model": "minimaxai/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "nvidia", "model": "minimaxai/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "opencode-go", "model": "minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode", "model": "minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 1 } }, { "source": "models.dev", "provider": "orcarouter", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.33, "output": 1.32 } }, { "source": "models.dev", "provider": "togetherai", "model": "MiniMaxAI/MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "vultr", "model": "MiniMaxAI/MiniMax-M2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3055, "output": 1.2219 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/MiniMax-M2.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m2.7", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 1 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.7", "MiniMax-M2.7", "MiniMax-m2.7", "MiniMax: MiniMax M2.7", "Minimax M2.7", "minimax-m2.7" ], "families": [ "minimax", "minimax-m2.7" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 28 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "MiniMax-M2.7", "modelKey": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "metadata": { "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "MiniMax/MiniMax-M2.7", "modelKey": "MiniMax/MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "MiniMax-m2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "MiniMaxAI/MiniMax-M2.7", "modelKey": "MiniMaxAI/MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax: MiniMax M2.7", "family": "minimax-m2.7", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lilac", "providerName": "Lilac", "providerApi": "https://api.getlilac.com/v1", "providerDoc": "https://docs.getlilac.com/inference/models", "model": "minimaxai/minimax-m2.7", "modelKey": "minimaxai/minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2.7", "modelKey": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2.7", "modelKey": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2.7", "modelKey": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2.7", "modelKey": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax-m2.7", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "minimaxai/minimax-m2.7", "modelKey": "minimaxai/minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "minimax-m2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax-m2.7", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m2.7", "modelKey": "minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/minimax-m2.7", "modelKey": "route/minimax-m2.7", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "MiniMaxAI/MiniMax-M2.7", "modelKey": "MiniMaxAI/MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "Minimax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "MiniMaxAI/MiniMax-M2.7", "modelKey": "MiniMaxAI/MiniMax-M2.7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2.7", "modelKey": "minimax/minimax-m2.7", "displayName": "MiniMax M2.7", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/MiniMax-M2.7", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m2.7", "displayName": "MiniMax: MiniMax M2.7", "metadata": { "canonicalSlug": "minimax/minimax-m2.7-20260318", "createdAt": "2026-03-18T12:24:57.000Z", "huggingFaceId": "MiniMaxAI/MiniMax-M2.7", "links": { "details": "/api/v1/models/minimax/minimax-m2.7-20260318/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 196608, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m2.7-highspeed", "provider": "minimax", "model": "minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "302ai", "fastrouter", "llmgateway", "merge-gateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "novita-ai", "orcarouter", "routing-run", "vercel", "zenmux" ], "aliases": [ "302ai/MiniMax-M2.7-highspeed", "fastrouter/minimax/minimax-m2.7-highspeed", "llmgateway/minimax-m2.7-highspeed", "merge-gateway/minimax/minimax-m2.7-highspeed", "minimax-cn-coding-plan/MiniMax-M2.7-highspeed", "minimax-cn/MiniMax-M2.7-highspeed", "minimax-coding-plan/MiniMax-M2.7-highspeed", "minimax/MiniMax-M2.7-highspeed", "novita-ai/minimax/minimax-m2.7-highspeed", "orcarouter/minimax/minimax-m2.7-highspeed", "routing-run/route/minimax-m2.7-highspeed", "vercel/minimax/minimax-m2.7-highspeed", "zenmux/minimax/minimax-m2.7-highspeed" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 204800, "outputTokens": 131100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "MiniMax-M2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 4.8 } }, { "source": "models.dev", "provider": "fastrouter", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "orcarouter", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.33, "output": 1.32 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "cacheWrite": 0.375, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m2.7-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.611, "output": 2.4439 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.7 High Speed", "MiniMax M2.7 Highspeed", "MiniMax M2.7 highspeed", "MiniMax-M2.7-highspeed" ], "families": [ "minimax" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "MiniMax-M2.7-highspeed", "modelKey": "MiniMax-M2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "metadata": { "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m2.7-highspeed", "modelKey": "minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M2.7-highspeed", "modelKey": "MiniMax-M2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M2.7-highspeed", "modelKey": "MiniMax-M2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M2.7-highspeed", "modelKey": "MiniMax-M2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M2.7-highspeed", "modelKey": "MiniMax-M2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-05-27", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax-M2.7-highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/minimax-m2.7-highspeed", "modelKey": "route/minimax-m2.7-highspeed", "displayName": "MiniMax M2.7 Highspeed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax M2.7 High Speed", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m2.7-highspeed", "modelKey": "minimax/minimax-m2.7-highspeed", "displayName": "MiniMax M2.7 highspeed", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "minimax/minimax-m2.7-turbo", "provider": "minimax", "model": "minimax-m2.7-turbo", "displayName": "MiniMax M2.7 Turbo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/minimax/minimax-m2.7-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "inputTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m2.7-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.7 Turbo" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m2.7-turbo", "modelKey": "minimax/minimax-m2.7-turbo", "displayName": "MiniMax M2.7 Turbo", "metadata": { "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "minimax/minimax-m25", "provider": "minimax", "model": "minimax-m25", "displayName": "MiniMax M2.5", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "drun", "venice" ], "aliases": [ "drun/public/minimax-m25", "venice/minimax-m25" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "drun", "model": "public/minimax-m25", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 1.16 } }, { "source": "models.dev", "provider": "venice", "model": "minimax-m25", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.34, "output": 1.19 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5" ], "families": [ "minimax" ], "releaseDate": "2025-03-01", "lastUpdated": "2025-03-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "drun", "providerName": "D.Run (China)", "providerApi": "https://chat.d.run/v1", "providerDoc": "https://www.d.run", "model": "public/minimax-m25", "modelKey": "public/minimax-m25", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2025-03-01", "openWeights": false, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "minimax-m25", "modelKey": "minimax-m25", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "minimax/minimax-m27", "provider": "minimax", "model": "minimax-m27", "displayName": "MiniMax M2.7", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/minimax-m27" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "minimax-m27", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06875, "input": 0.375, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.7" ], "families": [ "minimax" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "minimax-m27", "modelKey": "minimax-m27", "displayName": "MiniMax M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "minimax/minimax-m2p1", "provider": "minimax", "model": "minimax-m2p1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/minimax-m2p1", "fireworks_ai/minimax-m2p1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204800, "inputTokens": 204800, "maxTokens": 204800, "outputTokens": 204800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m2p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/minimax-m2p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/minimax-m2p1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/minimax-m2p1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/minimax-m2p1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/minimax-m2p1" } } ] }, { "id": "minimax/minimax-m2p7", "provider": "minimax", "model": "minimax-m2p7", "displayName": "MiniMax-M2.7", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/minimax-m2p7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 196608, "outputTokens": 196608, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/minimax-m2p7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax-M2.7" ], "families": [ "minimax" ], "releaseDate": "2026-04-12", "lastUpdated": "2026-04-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/minimax-m2p7", "modelKey": "accounts/fireworks/models/minimax-m2p7", "displayName": "MiniMax-M2.7", "family": "minimax", "metadata": { "lastUpdated": "2026-04-12", "openWeights": true, "releaseDate": "2026-04-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "minimax/minimax-m3", "provider": "minimax", "model": "minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cortecs", "fireworks-ai", "llmgateway", "minimax", "minimax-cn", "minimax-cn-coding-plan", "minimax-coding-plan", "nano-gpt", "ollama-cloud", "opencode-go", "openrouter", "synthetic", "togetherai", "venice", "vercel", "zenmux" ], "aliases": [ "cortecs/minimax-m3", "fireworks-ai/accounts/fireworks/models/minimax-m3", "llmgateway/minimax-m3", "minimax-cn-coding-plan/MiniMax-M3", "minimax-cn/MiniMax-M3", "minimax-coding-plan/MiniMax-M3", "minimax/MiniMax-M3", "nano-gpt/minimax/minimax-m3", "ollama-cloud/minimax-m3", "opencode-go/minimax-m3", "openrouter/minimax/minimax-m3", "synthetic/hf:MiniMaxAI/MiniMax-M3", "togetherai/MiniMaxAI/MiniMax-M3", "venice/minimax-m3", "vercel/minimax/minimax-m3", "zenmux/minimax/minimax-m3" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1048576, "inputTokens": 512000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.089, "input": 0.355, "output": 1.775 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-cn-coding-plan", "model": "MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax-cn", "model": "MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "minimax-coding-plan", "model": "MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "minimax", "model": "MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "opencode-go", "model": "minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "minimax/minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:MiniMaxAI/MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "input": 0.6, "output": 1.2 } }, { "source": "models.dev", "provider": "togetherai", "model": "MiniMaxAI/MiniMax-M3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "venice", "model": "minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "vercel", "model": "minimax/minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "minimax/minimax-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } }, { "source": "litellm", "provider": "minimax", "model": "minimax/MiniMax-M3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "minimax/minimax-m3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M3", "MiniMax M3 (3x usage)", "MiniMax-M3", "MiniMax: MiniMax M3", "minimax-m3" ], "families": [ "minimax", "minimax-m3" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-01", "lastUpdated": "2026-06-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "minimax-m3", "modelKey": "minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/minimax-m3", "modelKey": "accounts/fireworks/models/minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-m3", "modelKey": "minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn-coding-plan", "providerName": "MiniMax Token Plan (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/token-plan/intro", "model": "MiniMax-M3", "modelKey": "MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-cn", "providerName": "MiniMax (minimaxi.com)", "providerApi": "https://api.minimaxi.com/anthropic/v1", "providerDoc": "https://platform.minimaxi.com/docs/guides/quickstart", "model": "MiniMax-M3", "modelKey": "MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax-coding-plan", "providerName": "MiniMax Token Plan (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/token-plan/intro", "model": "MiniMax-M3", "modelKey": "MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "minimax", "providerName": "MiniMax (minimax.io)", "providerApi": "https://api.minimax.io/anthropic/v1", "providerDoc": "https://platform.minimax.io/docs/guides/quickstart", "model": "MiniMax-M3", "modelKey": "MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m3", "modelKey": "minimax/minimax-m3", "displayName": "MiniMax M3", "metadata": { "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "minimax-m3", "modelKey": "minimax-m3", "displayName": "minimax-m3", "family": "minimax-m3", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "openWeights": true, "releaseDate": "2026-05-31", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m3", "modelKey": "minimax-m3", "displayName": "MiniMax M3 (3x usage)", "family": "minimax-m3", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "openWeights": true, "releaseDate": "2026-05-31", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "minimax/minimax-m3", "modelKey": "minimax/minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:MiniMaxAI/MiniMax-M3", "modelKey": "hf:MiniMaxAI/MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "status": "beta", "metadata": { "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "MiniMaxAI/MiniMax-M3", "modelKey": "MiniMaxAI/MiniMax-M3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "minimax-m3", "modelKey": "minimax-m3", "displayName": "MiniMax M3", "family": "minimax-m3", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "minimax/minimax-m3", "modelKey": "minimax/minimax-m3", "displayName": "MiniMax M3", "family": "minimax-m3", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-05-31", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "minimax/minimax-m3", "modelKey": "minimax/minimax-m3", "displayName": "MiniMax-M3", "family": "minimax", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-06-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/MiniMax-M3", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "minimax/minimax-m3", "displayName": "MiniMax: MiniMax M3", "metadata": { "canonicalSlug": "minimax/minimax-m3-20260531", "createdAt": "2026-05-31T16:36:14.000Z", "huggingFaceId": "MiniMaxAI/Minimax-M3", "links": { "details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 524288, "max_completion_tokens": 512000, "is_moderated": false } } } ] }, { "id": "minimax/minimax-m3-free", "provider": "minimax", "model": "minimax-m3-free", "displayName": "MiniMax M3 Free", "family": "minimax-m3-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/minimax-m3-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "minimax-m3-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiniMax M3 Free" ], "families": [ "minimax-m3-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-05-31", "lastUpdated": "2026-05-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "minimax-m3-free", "modelKey": "minimax-m3-free", "displayName": "MiniMax M3 Free", "family": "minimax-m3-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "openWeights": true, "releaseDate": "2026-05-31", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "minimax/minimax-m3-preview", "provider": "minimax", "model": "minimax-m3-preview", "displayName": "MiniMax M3 Preview", "family": "minimax-m3", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/minimax-m3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 524288, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "minimax-m3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M3 Preview" ], "families": [ "minimax-m3" ], "releaseDate": "2026-06-12", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "minimax-m3-preview", "modelKey": "minimax-m3-preview", "displayName": "MiniMax M3 Preview", "family": "minimax-m3", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "minimax/minimax-m3:thinking", "provider": "minimax", "model": "minimax-m3:thinking", "displayName": "MiniMax M3 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/minimax/minimax-m3:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512000, "inputTokens": 512000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "minimax/minimax-m3:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M3 Thinking" ], "releaseDate": "2026-06-01", "lastUpdated": "2026-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "minimax/minimax-m3:thinking", "modelKey": "minimax/minimax-m3:thinking", "displayName": "MiniMax M3 Thinking", "metadata": { "lastUpdated": "2026-06-01", "openWeights": false, "releaseDate": "2026-06-01" } } ] }, { "id": "minimax/minimax-text-01", "provider": "minimax", "model": "minimax-text-01", "displayName": "MiniMax Text 01", "family": "minimax", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/minimax-text-01" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "minimax-text-01", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "MiniMax Text 01" ], "families": [ "minimax" ], "releaseDate": "2025-01-15", "lastUpdated": "2025-01-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "minimax-text-01", "modelKey": "minimax-text-01", "displayName": "MiniMax Text 01", "family": "minimax", "metadata": { "lastUpdated": "2025-01-15", "openWeights": true, "releaseDate": "2025-01-15" } } ] }, { "id": "minimax/minimax.minimax-m2", "provider": "minimax", "model": "minimax.minimax-m2", "displayName": "MiniMax M2", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/minimax.minimax-m2", "bedrock_converse/minimax.minimax-m2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204608, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "minimax.minimax-m2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "minimax.minimax-m2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M2" ], "families": [ "minimax" ], "modes": [ "chat" ], "releaseDate": "2025-10-27", "lastUpdated": "2025-10-27", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "minimax.minimax-m2", "modelKey": "minimax.minimax-m2", "displayName": "MiniMax M2", "family": "minimax", "metadata": { "lastUpdated": "2025-10-27", "openWeights": true, "releaseDate": "2025-10-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "minimax.minimax-m2", "mode": "chat" } ] }, { "id": "minimax/minimax.minimax-m2.1", "provider": "minimax", "model": "minimax.minimax-m2.1", "displayName": "MiniMax M2.1", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/minimax.minimax-m2.1", "bedrock_converse/minimax.minimax-m2.1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 204800, "inputTokens": 196000, "maxTokens": 8192, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "minimax.minimax-m2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "minimax.minimax-m2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.1" ], "families": [ "minimax" ], "modes": [ "chat" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "minimax.minimax-m2.1", "modelKey": "minimax.minimax-m2.1", "displayName": "MiniMax M2.1", "family": "minimax", "metadata": { "lastUpdated": "2025-12-23", "openWeights": true, "releaseDate": "2025-12-23" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "minimax.minimax-m2.1", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "minimax/minimax.minimax-m2.5", "provider": "minimax", "model": "minimax.minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/minimax.minimax-m2.5", "bedrock_converse/minimax.minimax-m2.5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 8192, "outputTokens": 98304, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "minimax.minimax-m2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "minimax.minimax-m2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "MiniMax M2.5" ], "families": [ "minimax" ], "modes": [ "chat" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "minimax.minimax-m2.5", "modelKey": "minimax.minimax-m2.5", "displayName": "MiniMax M2.5", "family": "minimax", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "minimax.minimax-m2.5", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "minimax/speech-02-hd", "provider": "minimax", "model": "speech-02-hd", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "minimax" ], "aliases": [ "minimax/speech-02-hd" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "minimax", "model": "minimax/speech-02-hd", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.0001 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/speech-02-hd", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "minimax/speech-02-turbo", "provider": "minimax", "model": "speech-02-turbo", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "minimax" ], "aliases": [ "minimax/speech-02-turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "minimax", "model": "minimax/speech-02-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00006 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/speech-02-turbo", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "minimax/speech-2.6-hd", "provider": "minimax", "model": "speech-2.6-hd", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "minimax" ], "aliases": [ "minimax/speech-2.6-hd" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "minimax", "model": "minimax/speech-2.6-hd", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.0001 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/speech-2.6-hd", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "minimax/speech-2.6-turbo", "provider": "minimax", "model": "speech-2.6-turbo", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "minimax" ], "aliases": [ "minimax/speech-2.6-turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "minimax", "model": "minimax/speech-2.6-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00006 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "minimax", "model": "minimax/speech-2.6-turbo", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "mistral/codestral", "provider": "mistral", "model": "codestral", "displayName": "Codestral (latest)", "family": "codestral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/mistral/codestral", "vercel_ai_gateway/mistral/codestral" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 4000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/codestral", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/codestral", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Codestral (latest)" ], "families": [ "codestral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-05-29", "lastUpdated": "2025-01-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/codestral", "modelKey": "mistral/codestral", "displayName": "Codestral (latest)", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-04", "openWeights": true, "releaseDate": "2024-05-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/codestral", "mode": "chat" } ] }, { "id": "mistral/codestral-2", "provider": "mistral", "model": "codestral-2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/codestral-2", "vertex_ai-mistral_models/vertex_ai/mistralai/codestral-2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/codestral-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/codestral-2", "mode": "chat" } ] }, { "id": "mistral/codestral-2@001", "provider": "mistral", "model": "codestral-2@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/codestral-2@001", "vertex_ai-mistral_models/vertex_ai/mistralai/codestral-2@001" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/codestral-2@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2@001", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/codestral-2@001", "mode": "chat" } ] }, { "id": "mistral/codestral-2405", "provider": "mistral", "model": "codestral-2405", "mode": "chat", "sources": [ "litellm" ], "providers": [ "codestral", "mistral", "text-completion-codestral" ], "aliases": [ "codestral/codestral-2405", "mistral/codestral-2405", "text-completion-codestral/codestral-2405" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "codestral", "model": "codestral/codestral-2405", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-2405", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "text-completion-codestral", "model": "text-completion-codestral/codestral-2405", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat", "completion" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "codestral", "model": "codestral/codestral-2405", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/capabilities/code_generation/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-2405", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-codestral", "model": "text-completion-codestral/codestral-2405", "mode": "completion", "metadata": { "source": "https://docs.mistral.ai/capabilities/code_generation/" } } ] }, { "id": "mistral/codestral-2501", "provider": "mistral", "model": "codestral-2501", "displayName": "Codestral 25.01", "family": "codestral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "github-models", "vertex_ai-mistral_models" ], "aliases": [ "azure-cognitive-services/codestral-2501", "azure/codestral-2501", "github-models/mistral-ai/codestral-2501", "vertex_ai-mistral_models/vertex_ai/codestral-2501" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 256000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "codestral-2501", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "azure", "model": "codestral-2501", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/codestral-2501", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2501", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Codestral 25.01" ], "families": [ "codestral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-03", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "codestral-2501", "modelKey": "codestral-2501", "displayName": "Codestral 25.01", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "codestral-2501", "modelKey": "codestral-2501", "displayName": "Codestral 25.01", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/codestral-2501", "modelKey": "mistral-ai/codestral-2501", "displayName": "Codestral 25.01", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral-2501", "mode": "chat" } ] }, { "id": "mistral/codestral-2508", "provider": "mistral", "model": "codestral-2508", "displayName": "Codestral 2508", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cortecs", "kilo", "llmgateway", "mistral", "nano-gpt", "openrouter" ], "aliases": [ "cortecs/codestral-2508", "kilo/mistralai/codestral-2508", "llmgateway/codestral-2508", "mistral/codestral-2508", "nano-gpt/mistralai/codestral-2508", "openrouter/mistralai/codestral-2508" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "codestral-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/codestral-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "llmgateway", "model": "codestral-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/codestral-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.8999999999999999 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/codestral-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-2508", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/codestral-2508", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.03, "input": 0.3, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Codestral", "Codestral 2508", "Mistral: Codestral 2508" ], "families": [ "codestral", "mistral" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-07-30", "lastUpdated": "2025-07-30", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "codestral-2508", "modelKey": "codestral-2508", "displayName": "Codestral 2508", "family": "mistral", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/codestral-2508", "modelKey": "mistralai/codestral-2508", "displayName": "Mistral: Codestral 2508", "metadata": { "lastUpdated": "2025-08-01", "openWeights": true, "releaseDate": "2025-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "codestral-2508", "modelKey": "codestral-2508", "displayName": "Codestral", "family": "mistral", "metadata": { "lastUpdated": "2025-07-30", "openWeights": true, "releaseDate": "2025-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/codestral-2508", "modelKey": "mistralai/codestral-2508", "displayName": "Codestral 2508", "family": "codestral", "metadata": { "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/codestral-2508", "modelKey": "mistralai/codestral-2508", "displayName": "Codestral 2508", "family": "codestral", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-01", "openWeights": false, "releaseDate": "2025-08-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-2508", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/codestral-25-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/codestral-2508", "displayName": "Mistral: Codestral 2508", "metadata": { "canonicalSlug": "mistralai/codestral-2508", "createdAt": "2025-08-01T20:20:30.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/mistralai/codestral-2508/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 256000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/codestral-embed", "provider": "mistral", "model": "codestral-embed", "displayName": "Codestral Embed", "family": "codestral-embed", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "vercel", "vercel_ai_gateway" ], "aliases": [ "mistral/codestral-embed", "vercel/mistral/codestral-embed", "vercel_ai_gateway/mistral/codestral-embed" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-embed", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/codestral-embed", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0 } } ] }, "metadata": { "displayNames": [ "Codestral Embed" ], "families": [ "codestral-embed" ], "modes": [ "chat", "embedding" ], "releaseDate": "2025-05-28", "lastUpdated": "2025-05-28", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/codestral-embed", "modelKey": "mistral/codestral-embed", "displayName": "Codestral Embed", "family": "codestral-embed", "metadata": { "lastUpdated": "2025-05-28", "openWeights": false, "releaseDate": "2025-05-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-embed", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/codestral-embed", "mode": "chat" } ] }, { "id": "mistral/codestral-embed-2505", "provider": "mistral", "model": "codestral-embed-2505", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/codestral-embed-2505" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-embed-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-embed-2505", "mode": "embedding" } ] }, { "id": "mistral/codestral-latest", "provider": "mistral", "model": "codestral-latest", "displayName": "Codestral (latest)", "family": "codestral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "codestral", "merge-gateway", "mistral", "text-completion-codestral" ], "aliases": [ "codestral/codestral-latest", "merge-gateway/mistral/codestral-latest", "mistral/codestral-latest", "text-completion-codestral/codestral-latest" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 256000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/codestral-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "mistral", "model": "codestral-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "codestral", "model": "codestral/codestral-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "text-completion-codestral", "model": "text-completion-codestral/codestral-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Codestral (latest)" ], "families": [ "codestral" ], "modes": [ "chat", "completion" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-05-29", "lastUpdated": "2025-01-04", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/codestral-latest", "modelKey": "mistral/codestral-latest", "displayName": "Codestral (latest)", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-04", "openWeights": true, "releaseDate": "2024-05-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "codestral-latest", "modelKey": "codestral-latest", "displayName": "Codestral (latest)", "family": "codestral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-04", "openWeights": true, "releaseDate": "2024-05-29" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "codestral", "model": "codestral/codestral-latest", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/capabilities/code_generation/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-latest", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-codestral", "model": "text-completion-codestral/codestral-latest", "mode": "completion", "metadata": { "source": "https://docs.mistral.ai/capabilities/code_generation/" } } ] }, { "id": "mistral/codestral-mamba-latest", "provider": "mistral", "model": "codestral-mamba-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/codestral-mamba-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/codestral-mamba-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/codestral-mamba-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/technology/" } } ] }, { "id": "mistral/codestral@2405", "provider": "mistral", "model": "codestral@2405", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/codestral@2405" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral@2405", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral@2405", "mode": "chat" } ] }, { "id": "mistral/codestral@latest", "provider": "mistral", "model": "codestral@latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/codestral@latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral@latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/codestral@latest", "mode": "chat" } ] }, { "id": "mistral/devstral-2", "provider": "mistral", "model": "devstral-2", "displayName": "Devstral 2", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/mistral/devstral-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/devstral-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2" ], "families": [ "devstral" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/devstral-2", "modelKey": "mistral/devstral-2", "displayName": "Devstral 2", "family": "devstral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-09", "openWeights": false, "releaseDate": "2025-12-09" } } ] }, { "id": "mistral/devstral-2-123b-instruct-2512", "provider": "mistral", "model": "devstral-2-123b-instruct-2512", "displayName": "Devstral 2 123B", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "scaleway" ], "aliases": [ "nano-gpt/mistralai/devstral-2-123b-instruct-2512", "scaleway/devstral-2-123b-instruct-2512" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/devstral-2-123b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.4 } }, { "source": "models.dev", "provider": "scaleway", "model": "devstral-2-123b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2 123B", "Devstral 2 123B Instruct (2512)" ], "families": [ "devstral" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/devstral-2-123b-instruct-2512", "modelKey": "mistralai/devstral-2-123b-instruct-2512", "displayName": "Devstral 2 123B", "family": "devstral", "metadata": { "lastUpdated": "2025-12-09", "openWeights": false, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "devstral-2-123b-instruct-2512", "modelKey": "devstral-2-123b-instruct-2512", "displayName": "Devstral 2 123B Instruct (2512)", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2026-01-07" } } ] }, { "id": "mistral/devstral-2:123b", "provider": "mistral", "model": "devstral-2:123b", "displayName": "devstral-2:123b", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/devstral-2:123b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "devstral-2:123b" ], "families": [ "devstral" ], "releaseDate": "2025-12-09", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "devstral-2:123b", "modelKey": "devstral-2:123b", "displayName": "devstral-2:123b", "family": "devstral", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-09" } } ] }, { "id": "mistral/devstral-2512", "provider": "mistral", "model": "devstral-2512", "displayName": "Devstral 2", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "cortecs", "kilo", "llmgateway", "merge-gateway", "mistral", "openrouter" ], "aliases": [ "anyapi/mistralai/devstral-2512", "cortecs/devstral-2512", "kilo/mistralai/devstral-2512", "llmgateway/devstral-2512", "merge-gateway/mistral/devstral-2512", "mistral/devstral-2512", "openrouter/mistralai/devstral-2512" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true, "promptCaching": false, "vision": false, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "mistral", "model": "devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/devstral-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/devstral-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/devstral-2512", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2", "Devstral 2 2512", "Mistral: Devstral 2 2512" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "mistralai/devstral-2512", "modelKey": "mistralai/devstral-2512", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "devstral-2512", "modelKey": "devstral-2512", "displayName": "Devstral 2 2512", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/devstral-2512", "modelKey": "mistralai/devstral-2512", "displayName": "Mistral: Devstral 2 2512", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "devstral-2512", "modelKey": "devstral-2512", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/devstral-2512", "modelKey": "mistral/devstral-2512", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-2512", "modelKey": "devstral-2512", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/devstral-2512", "modelKey": "mistralai/devstral-2512", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-2512", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral-2-vibe-cli" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/devstral-2512", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/devstral-2512", "displayName": "Mistral: Devstral 2 2512", "metadata": { "canonicalSlug": "mistralai/devstral-2512", "createdAt": "2025-12-09T13:03:39.000Z", "huggingFaceId": "mistralai/Devstral-2-123B-Instruct-2512", "links": { "details": "/api/v1/models/mistralai/devstral-2512/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/devstral-latest", "provider": "mistral", "model": "devstral-latest", "displayName": "Devstral 2", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/devstral-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "devstral-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-latest", "modelKey": "devstral-latest", "displayName": "Devstral 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral-2-vibe-cli" } } ] }, { "id": "mistral/devstral-medium", "provider": "mistral", "model": "devstral-medium", "displayName": "Mistral: Devstral Medium", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/mistralai/devstral-medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 26215, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/devstral-medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral: Devstral Medium" ], "releaseDate": "2025-07-10", "lastUpdated": "2025-07-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/devstral-medium", "modelKey": "mistralai/devstral-medium", "displayName": "Mistral: Devstral Medium", "metadata": { "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-07-10" } } ] }, { "id": "mistral/devstral-medium-2507", "provider": "mistral", "model": "devstral-medium-2507", "displayName": "Devstral Medium", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "mistral" ], "aliases": [ "merge-gateway/mistral/devstral-medium-2507", "mistral/devstral-medium-2507" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/devstral-medium-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "mistral", "model": "devstral-medium-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-medium-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral Medium" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-07-10", "lastUpdated": "2025-07-10", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/devstral-medium-2507", "modelKey": "mistral/devstral-medium-2507", "displayName": "Devstral Medium", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "openWeights": false, "releaseDate": "2025-07-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-medium-2507", "modelKey": "devstral-medium-2507", "displayName": "Devstral Medium", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-07-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-medium-2507", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral" } } ] }, { "id": "mistral/devstral-medium-latest", "provider": "mistral", "model": "devstral-medium-latest", "displayName": "Devstral 2 (latest)", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "mistral" ], "aliases": [ "merge-gateway/mistral/devstral-medium-latest", "mistral/devstral-medium-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/devstral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "mistral", "model": "devstral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-medium-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2 (latest)" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/devstral-medium-latest", "modelKey": "mistral/devstral-medium-latest", "displayName": "Devstral 2 (latest)", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-medium-latest", "modelKey": "devstral-medium-latest", "displayName": "Devstral 2 (latest)", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-medium-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral-2-vibe-cli" } } ] }, { "id": "mistral/devstral-small", "provider": "mistral", "model": "devstral-small", "displayName": "Mistral: Devstral Small 1.1", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "kilo", "vercel", "vercel_ai_gateway" ], "aliases": [ "kilo/mistralai/devstral-small", "vercel/mistral/devstral-small", "vercel_ai_gateway/mistral/devstral-small" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/devstral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/devstral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/devstral-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Devstral Small 1.1", "Mistral: Devstral Small 1.1" ], "families": [ "devstral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-05-07", "lastUpdated": "2025-07-10", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/devstral-small", "modelKey": "mistralai/devstral-small", "displayName": "Mistral: Devstral Small 1.1", "metadata": { "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/devstral-small", "modelKey": "mistral/devstral-small", "displayName": "Devstral Small 1.1", "family": "devstral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/devstral-small", "mode": "chat" } ] }, { "id": "mistral/devstral-small-2", "provider": "mistral", "model": "devstral-small-2", "displayName": "Devstral Small 2", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/mistral/devstral-small-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/devstral-small-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Devstral Small 2" ], "families": [ "devstral" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-05-07", "lastUpdated": "2025-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/devstral-small-2", "modelKey": "mistral/devstral-small-2", "displayName": "Devstral Small 2", "family": "devstral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } } ] }, { "id": "mistral/devstral-small-2-24b-instruct-2512", "provider": "mistral", "model": "devstral-small-2-24b-instruct-2512", "displayName": "Devstral Small 2 24B Instruct 2512", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/mistralai/devstral-small-2-24b-instruct-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "mistralai/devstral-small-2-24b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.47 } } ] }, "metadata": { "displayNames": [ "Devstral Small 2 24B Instruct 2512" ], "families": [ "devstral" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "mistralai/devstral-small-2-24b-instruct-2512", "modelKey": "mistralai/devstral-small-2-24b-instruct-2512", "displayName": "Devstral Small 2 24B Instruct 2512", "family": "devstral", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } } ] }, { "id": "mistral/devstral-small-2:24b", "provider": "mistral", "model": "devstral-small-2:24b", "displayName": "devstral-small-2:24b", "family": "devstral", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/devstral-small-2:24b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "devstral-small-2:24b" ], "families": [ "devstral" ], "releaseDate": "2025-12-09", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "devstral-small-2:24b", "modelKey": "devstral-small-2:24b", "displayName": "devstral-small-2:24b", "family": "devstral", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-09" } } ] }, { "id": "mistral/devstral-small-2505", "provider": "mistral", "model": "devstral-small-2505", "displayName": "Devstral Small 2505", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks_ai", "io-net", "mistral", "nano-gpt" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/devstral-small-2505", "io-net/mistralai/Devstral-Small-2505", "mistral/devstral-small-2505", "nano-gpt/mistralai/Devstral-Small-2505" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "io-net", "model": "mistralai/Devstral-Small-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0.1, "input": 0.05, "output": 0.22 } }, { "source": "models.dev", "provider": "mistral", "model": "devstral-small-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/Devstral-Small-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.060000000000000005, "output": 0.060000000000000005 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/devstral-small-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-small-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Devstral Small 2505", "Mistral Devstral Small 2505" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-05-01", "lastUpdated": "2025-05-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "mistralai/Devstral-Small-2505", "modelKey": "mistralai/Devstral-Small-2505", "displayName": "Devstral Small 2505", "family": "devstral", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-05-01", "openWeights": false, "releaseDate": "2025-05-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-small-2505", "modelKey": "devstral-small-2505", "displayName": "Devstral Small 2505", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": true, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/Devstral-Small-2505", "modelKey": "mistralai/Devstral-Small-2505", "displayName": "Mistral Devstral Small 2505", "family": "devstral", "metadata": { "lastUpdated": "2025-08-02", "openWeights": false, "releaseDate": "2025-08-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/devstral-small-2505", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-small-2505", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral" } } ] }, { "id": "mistral/devstral-small-2507", "provider": "mistral", "model": "devstral-small-2507", "displayName": "Devstral Small", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "merge-gateway", "mistral" ], "aliases": [ "llmgateway/devstral-small-2507", "merge-gateway/mistral/devstral-small-2507", "mistral/devstral-small-2507" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "devstral-small-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/devstral-small-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "mistral", "model": "devstral-small-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-small-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Devstral Small" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-07-10", "lastUpdated": "2025-07-10", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "devstral-small-2507", "modelKey": "devstral-small-2507", "displayName": "Devstral Small", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-07-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/devstral-small-2507", "modelKey": "mistral/devstral-small-2507", "displayName": "Devstral Small", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-07-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "devstral-small-2507", "modelKey": "devstral-small-2507", "displayName": "Devstral Small", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "openWeights": true, "releaseDate": "2025-07-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-small-2507", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/devstral" } } ] }, { "id": "mistral/devstral-small-2512", "provider": "mistral", "model": "devstral-small-2512", "displayName": "Devstral Small 2 2512", "sources": [ "models.dev" ], "providers": [ "cortecs" ], "aliases": [ "cortecs/devstral-small-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "devstral-small-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Devstral Small 2 2512" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "devstral-small-2512", "modelKey": "devstral-small-2512", "displayName": "Devstral Small 2 2512", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } } ] }, { "id": "mistral/devstral-small-latest", "provider": "mistral", "model": "devstral-small-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/devstral-small-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/devstral-small-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/devstral-small-latest", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/models/devstral-small-2-25-12" } } ] }, { "id": "mistral/labs-devstral-small-2512", "provider": "mistral", "model": "labs-devstral-small-2512", "displayName": "Devstral Small 2", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/labs-devstral-small-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "labs-devstral-small-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/labs-devstral-small-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Devstral Small 2" ], "families": [ "devstral" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-09", "lastUpdated": "2025-12-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "labs-devstral-small-2512", "modelKey": "labs-devstral-small-2512", "displayName": "Devstral Small 2", "family": "devstral", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "openWeights": true, "releaseDate": "2025-12-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/labs-devstral-small-2512", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/models/devstral-small-2-25-12" } } ] }, { "id": "mistral/magistral-medium", "provider": "mistral", "model": "magistral-medium", "displayName": "Magistral Medium (latest)", "family": "magistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/mistral/magistral-medium", "vercel_ai_gateway/mistral/magistral-medium" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/magistral-medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/magistral-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "displayNames": [ "Magistral Medium (latest)" ], "families": [ "magistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-03-17", "lastUpdated": "2025-03-20", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/magistral-medium", "modelKey": "mistral/magistral-medium", "displayName": "Magistral Medium (latest)", "family": "magistral-medium", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-20", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/magistral-medium", "mode": "chat" } ] }, { "id": "mistral/magistral-medium-1-2-2509", "provider": "mistral", "model": "magistral-medium-1-2-2509", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/magistral-medium-1-2-2509" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-medium-1-2-2509", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-medium-1-2-2509", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/magistral" } } ] }, { "id": "mistral/magistral-medium-2506", "provider": "mistral", "model": "magistral-medium-2506", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/magistral-medium-2506" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-medium-2506", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-medium-2506", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/magistral" } } ] }, { "id": "mistral/magistral-medium-2509", "provider": "mistral", "model": "magistral-medium-2509", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/magistral-medium-2509" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-medium-2509", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-medium-2509", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/magistral" } } ] }, { "id": "mistral/magistral-medium-latest", "provider": "mistral", "model": "magistral-medium-latest", "displayName": "Magistral Medium (latest)", "family": "magistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "mistral" ], "aliases": [ "merge-gateway/mistral/magistral-medium-latest", "mistral/magistral-medium-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/magistral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 5 } }, { "source": "models.dev", "provider": "mistral", "model": "magistral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 5 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-medium-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "displayNames": [ "Magistral Medium (latest)" ], "families": [ "magistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-03-17", "lastUpdated": "2025-03-20", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/magistral-medium-latest", "modelKey": "mistral/magistral-medium-latest", "displayName": "Magistral Medium (latest)", "family": "magistral-medium", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-20", "openWeights": false, "releaseDate": "2025-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "magistral-medium-latest", "modelKey": "magistral-medium-latest", "displayName": "Magistral Medium (latest)", "family": "magistral-medium", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-20", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-medium-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/magistral" } } ] }, { "id": "mistral/magistral-small", "provider": "mistral", "model": "magistral-small", "displayName": "Magistral Small", "family": "magistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "vercel", "vercel_ai_gateway" ], "aliases": [ "mistral/magistral-small", "vercel/mistral/magistral-small", "vercel_ai_gateway/mistral/magistral-small" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 64000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "magistral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/magistral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/magistral-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Magistral Small" ], "families": [ "magistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-03-17", "lastUpdated": "2025-03-17", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "magistral-small", "modelKey": "magistral-small", "displayName": "Magistral Small", "family": "magistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-17", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/magistral-small", "modelKey": "mistral/magistral-small", "displayName": "Magistral Small", "family": "magistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-17", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/magistral-small", "mode": "chat" } ] }, { "id": "mistral/magistral-small-1-2-2509", "provider": "mistral", "model": "magistral-small-1-2-2509", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/magistral-small-1-2-2509" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-small-1-2-2509", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-small-1-2-2509", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing#api-pricing" } } ] }, { "id": "mistral/magistral-small-2506", "provider": "mistral", "model": "magistral-small-2506", "displayName": "Magistral Small 2506", "family": "magistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "io-net", "mistral", "nano-gpt", "nvidia" ], "aliases": [ "io-net/mistralai/Magistral-Small-2506", "mistral/magistral-small-2506", "nano-gpt/Magistral-Small-2506", "nvidia/mistralai/magistral-small-2506" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "temperature": true, "toolCalling": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "io-net", "model": "mistralai/Magistral-Small-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 1, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "Magistral-Small-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "mistralai/magistral-small-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-small-2506", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Magistral Small 2506" ], "families": [ "magistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "mistralai/Magistral-Small-2506", "modelKey": "mistralai/Magistral-Small-2506", "displayName": "Magistral Small 2506", "family": "magistral-small", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Magistral-Small-2506", "modelKey": "Magistral-Small-2506", "displayName": "Magistral Small 2506", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/magistral-small-2506", "modelKey": "mistralai/magistral-small-2506", "displayName": "Magistral Small 2506", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-small-2506", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing#api-pricing" } } ] }, { "id": "mistral/magistral-small-2509", "provider": "mistral", "model": "magistral-small-2509", "displayName": "Magistral Small 1.2 24B", "family": "magistral-small", "sources": [ "models.dev" ], "providers": [ "evroc" ], "aliases": [ "evroc/mistralai/Magistral-Small-2509" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "mistralai/Magistral-Small-2509", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.59, "output": 2.36 } } ] }, "metadata": { "displayNames": [ "Magistral Small 1.2 24B" ], "families": [ "magistral-small" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "mistralai/Magistral-Small-2509", "modelKey": "mistralai/Magistral-Small-2509", "displayName": "Magistral Small 1.2 24B", "family": "magistral-small", "metadata": { "lastUpdated": "2025-06-01", "openWeights": true, "releaseDate": "2025-06-01" } } ] }, { "id": "mistral/magistral-small-latest", "provider": "mistral", "model": "magistral-small-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/magistral-small-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "inputTokens": 40000, "maxTokens": 40000, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/magistral-small-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/magistral-small-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing#api-pricing" } } ] }, { "id": "mistral/ministral-14b", "provider": "mistral", "model": "ministral-14b", "displayName": "Ministral 14B", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/mistral/ministral-14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/ministral-14b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Ministral 14B" ], "families": [ "ministral" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/ministral-14b", "modelKey": "mistral/ministral-14b", "displayName": "Ministral 14B", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "mistral/ministral-14b-2512", "provider": "mistral", "model": "ministral-14b-2512", "displayName": "Ministral 3 14B 2512", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "302ai/ministral-14b-2512", "kilo/mistralai/ministral-14b-2512", "llmgateway/ministral-14b-2512", "nano-gpt/mistralai/ministral-14b-2512", "openrouter/mistralai/ministral-14b-2512" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "ministral-14b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 0.33 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/ministral-14b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "ministral-14b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/ministral-14b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/ministral-14b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/ministral-14b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/ministral-14b-2512", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Ministral 14B", "Ministral 3 14B 2512", "Mistral: Ministral 3 14B 2512", "ministral-14b-2512" ], "families": [ "ministral", "mistral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "ministral-14b-2512", "modelKey": "ministral-14b-2512", "displayName": "ministral-14b-2512", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/ministral-14b-2512", "modelKey": "mistralai/ministral-14b-2512", "displayName": "Mistral: Ministral 3 14B 2512", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "ministral-14b-2512", "modelKey": "ministral-14b-2512", "displayName": "Ministral 14B", "family": "mistral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/ministral-14b-2512", "modelKey": "mistralai/ministral-14b-2512", "displayName": "Ministral 14B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-04", "openWeights": false, "releaseDate": "2025-12-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/ministral-14b-2512", "modelKey": "mistralai/ministral-14b-2512", "displayName": "Ministral 3 14B 2512", "family": "ministral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/ministral-14b-2512", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/ministral-14b-2512", "displayName": "Mistral: Ministral 3 14B 2512", "metadata": { "canonicalSlug": "mistralai/ministral-14b-2512", "createdAt": "2025-12-02T13:22:15.000Z", "huggingFaceId": "mistralai/Ministral-3-14B-Instruct-2512", "links": { "details": "/api/v1/models/mistralai/ministral-14b-2512/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/ministral-14b-instruct-2512", "provider": "mistral", "model": "ministral-14b-instruct-2512", "displayName": "Ministral 3 14B", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistralai/ministral-14b-instruct-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/ministral-14b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Ministral 3 14B" ], "families": [ "ministral" ], "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/ministral-14b-instruct-2512", "modelKey": "mistralai/ministral-14b-instruct-2512", "displayName": "Ministral 3 14B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02" } } ] }, { "id": "mistral/ministral-3-14b-2512", "provider": "mistral", "model": "ministral-3-14b-2512", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/ministral-3-14b-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/ministral-3-14b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/ministral-3-14b-2512", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/ministral-3-14b-instruct-2512", "provider": "mistral", "model": "ministral-3-14b-instruct-2512", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512", "mode": "chat" } ] }, { "id": "mistral/ministral-3-14b-reasoning-2512", "provider": "mistral", "model": "ministral-3-14b-reasoning-2512", "displayName": "Ministral 3 14B Reasoning 2512", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/mistralai/completion/models/Ministral-3-14B-Reasoning-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "mistralai/completion/models/Ministral-3-14B-Reasoning-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 1.7 } } ] }, "metadata": { "displayNames": [ "Ministral 3 14B Reasoning 2512" ], "families": [ "ministral" ], "knowledgeCutoff": "2025-12", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "mistralai/completion/models/Ministral-3-14B-Reasoning-2512", "modelKey": "mistralai/completion/models/Ministral-3-14B-Reasoning-2512", "displayName": "Ministral 3 14B Reasoning 2512", "family": "ministral", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-12", "openWeights": true, "releaseDate": "2025-12-01" } } ] }, { "id": "mistral/ministral-3-3b-2512", "provider": "mistral", "model": "ministral-3-3b-2512", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/ministral-3-3b-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/ministral-3-3b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/ministral-3-3b-2512", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/ministral-3-3b-instruct-2512", "provider": "mistral", "model": "ministral-3-3b-instruct-2512", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512", "mode": "chat" } ] }, { "id": "mistral/ministral-3-3b-reasoning-2512", "provider": "mistral", "model": "ministral-3-3b-reasoning-2512", "displayName": "Ministral 3 3B Reasoning 2512", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/mistralai/completion/models/Ministral-3-3B-Reasoning-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "mistralai/completion/models/Ministral-3-3B-Reasoning-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.039, "output": 0.54825 } } ] }, "metadata": { "displayNames": [ "Ministral 3 3B Reasoning 2512" ], "families": [ "ministral" ], "releaseDate": "2025-12", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "mistralai/completion/models/Ministral-3-3B-Reasoning-2512", "modelKey": "mistralai/completion/models/Ministral-3-3B-Reasoning-2512", "displayName": "Ministral 3 3B Reasoning 2512", "family": "ministral", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-12" } } ] }, { "id": "mistral/ministral-3-8b-2512", "provider": "mistral", "model": "ministral-3-8b-2512", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/ministral-3-8b-2512" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/ministral-3-8b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/ministral-3-8b-2512", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/ministral-3-8b-instruct-2512", "provider": "mistral", "model": "ministral-3-8b-instruct-2512", "displayName": "Ministral 3 8B", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "digitalocean", "fireworks_ai" ], "aliases": [ "digitalocean/ministral-3-8b-instruct-2512", "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Ministral 3 8B" ], "families": [ "ministral" ], "modes": [ "chat" ], "releaseDate": "2025-12-15", "lastUpdated": "2025-12-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "ministral-3-8b-instruct-2512", "modelKey": "ministral-3-8b-instruct-2512", "displayName": "Ministral 3 8B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-15", "openWeights": true, "releaseDate": "2025-12-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512", "mode": "chat" } ] }, { "id": "mistral/ministral-3:14b", "provider": "mistral", "model": "ministral-3:14b", "displayName": "ministral-3:14b", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/ministral-3:14b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ministral-3:14b" ], "families": [ "ministral" ], "releaseDate": "2024-12-01", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "ministral-3:14b", "modelKey": "ministral-3:14b", "displayName": "ministral-3:14b", "family": "ministral", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "mistral/ministral-3:3b", "provider": "mistral", "model": "ministral-3:3b", "displayName": "ministral-3:3b", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/ministral-3:3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ministral-3:3b" ], "families": [ "ministral" ], "releaseDate": "2024-10-22", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "ministral-3:3b", "modelKey": "ministral-3:3b", "displayName": "ministral-3:3b", "family": "ministral", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2024-10-22" } } ] }, { "id": "mistral/ministral-3:8b", "provider": "mistral", "model": "ministral-3:8b", "displayName": "ministral-3:8b", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/ministral-3:8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ministral-3:8b" ], "families": [ "ministral" ], "releaseDate": "2024-12-01", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "ministral-3:8b", "modelKey": "ministral-3:8b", "displayName": "ministral-3:8b", "family": "ministral", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "mistral/ministral-3b", "provider": "mistral", "model": "ministral-3b", "displayName": "Ministral 3B", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/ministral-3b", "azure/ministral-3b", "azure_ai/ministral-3b", "github-models/mistral-ai/ministral-3b", "vercel/mistral/ministral-3b", "vercel_ai_gateway/mistral/ministral-3b" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "ministral-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "models.dev", "provider": "azure", "model": "ministral-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/ministral-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/ministral-3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/ministral-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/ministral-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.04 } } ] }, "metadata": { "displayNames": [ "Ministral 3B", "Ministral 3B (latest)" ], "families": [ "ministral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-03", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "ministral-3b", "modelKey": "ministral-3b", "displayName": "Ministral 3B", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-10-22", "openWeights": true, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "ministral-3b", "modelKey": "ministral-3b", "displayName": "Ministral 3B", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-10-22", "openWeights": true, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/ministral-3b", "modelKey": "mistral-ai/ministral-3b", "displayName": "Ministral 3B", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-10-22", "openWeights": true, "releaseDate": "2024-10-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/ministral-3b", "modelKey": "mistral/ministral-3b", "displayName": "Ministral 3B (latest)", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-04", "openWeights": true, "releaseDate": "2024-10-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/ministral-3b", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/ministral-3b", "mode": "chat" } ] }, { "id": "mistral/ministral-3b-2512", "provider": "mistral", "model": "ministral-3b-2512", "displayName": "Ministral 3 3B 2512", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "llmgateway", "nano-gpt", "openrouter" ], "aliases": [ "kilo/mistralai/ministral-3b-2512", "llmgateway/ministral-3b-2512", "nano-gpt/mistralai/ministral-3b-2512", "openrouter/mistralai/ministral-3b-2512" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/ministral-3b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "llmgateway", "model": "ministral-3b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/ministral-3b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/ministral-3b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/ministral-3b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/ministral-3b-2512", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Ministral 3 3B 2512", "Ministral 3B", "Mistral: Ministral 3 3B 2512" ], "families": [ "ministral", "mistral" ], "modes": [ "chat" ], "releaseDate": "2025-12-02", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/ministral-3b-2512", "modelKey": "mistralai/ministral-3b-2512", "displayName": "Mistral: Ministral 3 3B 2512", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "ministral-3b-2512", "modelKey": "ministral-3b-2512", "displayName": "Ministral 3B", "family": "mistral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/ministral-3b-2512", "modelKey": "mistralai/ministral-3b-2512", "displayName": "Ministral 3B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-04", "openWeights": false, "releaseDate": "2025-12-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/ministral-3b-2512", "modelKey": "mistralai/ministral-3b-2512", "displayName": "Ministral 3 3B 2512", "family": "ministral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/ministral-3b-2512", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/ministral-3b-2512", "displayName": "Mistral: Ministral 3 3B 2512", "metadata": { "canonicalSlug": "mistralai/ministral-3b-2512", "createdAt": "2025-12-02T13:19:20.000Z", "huggingFaceId": "mistralai/Ministral-3-3B-Instruct-2512", "links": { "details": "/api/v1/models/mistralai/ministral-3b-2512/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/ministral-3b-latest", "provider": "mistral", "model": "ministral-3b-latest", "displayName": "Ministral 3B (latest)", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/ministral-3b-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "ministral-3b-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } } ] }, "metadata": { "displayNames": [ "Ministral 3B (latest)" ], "families": [ "ministral" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-10-01", "lastUpdated": "2024-10-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "ministral-3b-latest", "modelKey": "ministral-3b-latest", "displayName": "Ministral 3B (latest)", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-04", "openWeights": true, "releaseDate": "2024-10-01" } } ] }, { "id": "mistral/ministral-8b", "provider": "mistral", "model": "ministral-8b", "displayName": "Ministral 8B (latest)", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/mistral/ministral-8b", "vercel_ai_gateway/mistral/ministral-8b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/ministral-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/ministral-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Ministral 8B (latest)" ], "families": [ "ministral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-10-01", "lastUpdated": "2024-10-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/ministral-8b", "modelKey": "mistral/ministral-8b", "displayName": "Ministral 8B (latest)", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-04", "openWeights": true, "releaseDate": "2024-10-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/ministral-8b", "mode": "chat" } ] }, { "id": "mistral/ministral-8b-2512", "provider": "mistral", "model": "ministral-8b-2512", "displayName": "Ministral 3 8B 2512", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "llmgateway", "mistral", "nano-gpt", "openrouter" ], "aliases": [ "kilo/mistralai/ministral-8b-2512", "llmgateway/ministral-8b-2512", "mistral/ministral-8b-2512", "nano-gpt/mistralai/ministral-8b-2512", "openrouter/mistralai/ministral-8b-2512" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "promptCaching": false, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/ministral-8b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "ministral-8b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/ministral-8b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/ministral-8b-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/ministral-8b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/ministral-8b-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/ministral-8b-2512", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Ministral 3 8B 2512", "Ministral 8B", "Mistral: Ministral 3 8B 2512" ], "families": [ "ministral", "mistral" ], "modes": [ "chat" ], "releaseDate": "2025-12-02", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/ministral-8b-2512", "modelKey": "mistralai/ministral-8b-2512", "displayName": "Mistral: Ministral 3 8B 2512", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "ministral-8b-2512", "modelKey": "ministral-8b-2512", "displayName": "Ministral 8B", "family": "mistral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/ministral-8b-2512", "modelKey": "mistralai/ministral-8b-2512", "displayName": "Ministral 8B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-04", "openWeights": false, "releaseDate": "2025-12-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/ministral-8b-2512", "modelKey": "mistralai/ministral-8b-2512", "displayName": "Ministral 3 8B 2512", "family": "ministral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/ministral-8b-2512", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/ministral-8b-2512", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/ministral-8b-2512", "displayName": "Mistral: Ministral 3 8B 2512", "metadata": { "canonicalSlug": "mistralai/ministral-8b-2512", "createdAt": "2025-12-02T13:20:54.000Z", "huggingFaceId": "mistralai/Ministral-3-8B-Instruct-2512", "links": { "details": "/api/v1/models/mistralai/ministral-8b-2512/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/ministral-8b-latest", "provider": "mistral", "model": "ministral-8b-latest", "displayName": "Ministral 8B (latest)", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/ministral-8b-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "ministral-8b-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/ministral-8b-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Ministral 8B (latest)" ], "families": [ "ministral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-10-01", "lastUpdated": "2024-10-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "ministral-8b-latest", "modelKey": "ministral-8b-latest", "displayName": "Ministral 8B (latest)", "family": "ministral", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-04", "openWeights": true, "releaseDate": "2024-10-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/ministral-8b-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/mistral", "provider": "mistral", "model": "mistral", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/mistral" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/mistral", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mistral", "mode": "completion" } ] }, { "id": "mistral/mistral-3-14b", "provider": "mistral", "model": "mistral-3-14b", "displayName": "Ministral 3 14B Instruct", "family": "ministral", "sources": [ "models.dev" ], "providers": [ "digitalocean" ], "aliases": [ "digitalocean/mistral-3-14B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "digitalocean", "model": "mistral-3-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Ministral 3 14B Instruct" ], "families": [ "ministral" ], "releaseDate": "2025-12-15", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "mistral-3-14B", "modelKey": "mistral-3-14B", "displayName": "Ministral 3 14B Instruct", "family": "ministral", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2025-12-15" } } ] }, { "id": "mistral/mistral-7b", "provider": "mistral", "model": "mistral-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "snowflake" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-7b", "snowflake/mistral-7b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/mistral-7b", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct", "provider": "mistral", "model": "mistral-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/mistralai/mistral-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mistral-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.13 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mistral-7b-instruct", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct-4k", "provider": "mistral", "model": "mistral-7b-instruct-4k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct-v0.1", "provider": "mistral", "model": "mistral-7b-instruct-v0.1", "displayName": "Mistral 7B Instruct v0.1", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anyscale", "cloudflare", "cloudflare-ai-gateway", "kilo", "ollama", "together_ai" ], "aliases": [ "anyscale/mistralai/Mistral-7B-Instruct-v0.1", "cloudflare-ai-gateway/workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "kilo/mistralai/mistral-7b-instruct-v0.1", "ollama/mistral-7B-Instruct-v0.1", "together_ai/mistralai/Mistral-7B-Instruct-v0.1" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.19 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-7b-instruct-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.19 } }, { "source": "litellm", "provider": "anyscale", "model": "anyscale/mistralai/Mistral-7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "cloudflare", "model": "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.923, "output": 1.923 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/mistral-7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/mistralai/Mistral-7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Mistral 7B Instruct v0.1", "Mistral: Mistral 7B Instruct v0.1" ], "families": [ "mistral" ], "modes": [ "chat" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", "modelKey": "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", "displayName": "Mistral 7B Instruct v0.1", "family": "mistral", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-7b-instruct-v0.1", "modelKey": "mistralai/mistral-7b-instruct-v0.1", "displayName": "Mistral: Mistral 7B Instruct v0.1", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/mistralai/Mistral-7B-Instruct-v0.1", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cloudflare", "model": "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mistral-7B-Instruct-v0.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/mistralai/Mistral-7B-Instruct-v0.1", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct-v0.2", "provider": "mistral", "model": "mistral-7b-instruct-v0.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama", "replicate" ], "aliases": [ "ollama/mistral-7B-Instruct-v0.2", "replicate/mistralai/mistral-7b-instruct-v0.2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "toolChoice": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/mistral-7B-Instruct-v0.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/mistralai/mistral-7b-instruct-v0.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mistral-7B-Instruct-v0.2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/mistralai/mistral-7b-instruct-v0.2", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct-v0.3", "provider": "mistral", "model": "mistral-7b-instruct-v0.3", "displayName": "Mistral-7B-Instruct-v0.3", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "digitalocean", "ovhcloud" ], "aliases": [ "digitalocean/mistral-7b-instruct-v0.3", "ovhcloud/Mistral-7B-Instruct-v0.3", "ovhcloud/mistral-7b-instruct-v0.3" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 127000, "inputTokens": 127000, "maxTokens": 127000, "outputTokens": 127000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "ovhcloud", "model": "mistral-7b-instruct-v0.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.11, "output": 0.11 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Mistral-7B-Instruct-v0.3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Mistral 7B Instruct v0.3", "Mistral-7B-Instruct-v0.3" ], "families": [ "mistral" ], "modes": [ "chat" ], "releaseDate": "2024-05-22", "lastUpdated": "2024-05-22", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "mistral-7b-instruct-v0.3", "modelKey": "mistral-7b-instruct-v0.3", "displayName": "Mistral 7B Instruct v0.3", "family": "mistral", "metadata": { "lastUpdated": "2024-05-22", "openWeights": true, "releaseDate": "2024-05-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "mistral-7b-instruct-v0.3", "modelKey": "mistral-7b-instruct-v0.3", "displayName": "Mistral-7B-Instruct-v0.3", "metadata": { "lastUpdated": "2025-04-01", "openWeights": true, "releaseDate": "2025-04-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Mistral-7B-Instruct-v0.3", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3" } } ] }, { "id": "mistral/mistral-7b-instruct-v03", "provider": "mistral", "model": "mistral-7b-instruct-v03", "displayName": "Mistral-7B-Instruct-v0.3", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/mistralai/mistral-7b-instruct-v03" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mistral-7b-instruct-v03", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mistral-7B-Instruct-v0.3" ], "releaseDate": "2025-04-01", "lastUpdated": "2025-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mistral-7b-instruct-v03", "modelKey": "mistralai/mistral-7b-instruct-v03", "displayName": "Mistral-7B-Instruct-v0.3", "metadata": { "lastUpdated": "2025-04-01", "openWeights": true, "releaseDate": "2025-04-01" } } ] }, { "id": "mistral/mistral-7b-instruct-v0p2", "provider": "mistral", "model": "mistral-7b-instruct-v0p2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-instruct-v3", "provider": "mistral", "model": "mistral-7b-instruct-v3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-v0.1", "provider": "mistral", "model": "mistral-7b-v0.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/mistralai/mistral-7b-v0.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/mistralai/mistral-7b-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/mistralai/mistral-7b-v0.1", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-v0.3", "provider": "mistral", "model": "mistral-7b-v0.3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "llamagate" ], "aliases": [ "llamagate/mistral-7b-v0.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "llamagate", "model": "llamagate/mistral-7b-v0.3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "llamagate", "model": "llamagate/mistral-7b-v0.3", "mode": "chat" } ] }, { "id": "mistral/mistral-7b-v0p2", "provider": "mistral", "model": "mistral-7b-v0p2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2", "mode": "chat" } ] }, { "id": "mistral/mistral-code-agent-latest", "provider": "mistral", "model": "mistral-code-agent-latest", "displayName": "Mistral Code Agent Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistral-code-agent-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistral-code-agent-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral Code Agent Latest" ], "releaseDate": "2026-06-02", "lastUpdated": "2026-06-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistral-code-agent-latest", "modelKey": "mistral-code-agent-latest", "displayName": "Mistral Code Agent Latest", "metadata": { "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02" } } ] }, { "id": "mistral/mistral-code-latest", "provider": "mistral", "model": "mistral-code-latest", "displayName": "Mistral Code Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistral-code-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistral-code-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Mistral Code Latest" ], "releaseDate": "2026-06-02", "lastUpdated": "2026-06-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistral-code-latest", "modelKey": "mistral-code-latest", "displayName": "Mistral Code Latest", "metadata": { "lastUpdated": "2026-06-02", "openWeights": false, "releaseDate": "2026-06-02" } } ] }, { "id": "mistral/mistral-document-ai-2505", "provider": "mistral", "model": "mistral-document-ai-2505", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/mistral-document-ai-2505" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-document-ai-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.003 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-document-ai-2505", "mode": "ocr", "metadata": { "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "mistral/mistral-document-ai-2512", "provider": "mistral", "model": "mistral-document-ai-2512", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "azure_ai" ], "aliases": [ "azure_ai/mistral-document-ai-2512" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-document-ai-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.003 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-document-ai-2512", "mode": "ocr", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "mistral/mistral-embed", "provider": "mistral", "model": "mistral-embed", "displayName": "Mistral Embed", "family": "mistral-embed", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "vercel", "vercel_ai_gateway" ], "aliases": [ "mistral/mistral-embed", "vercel/mistral/mistral-embed", "vercel_ai_gateway/mistral/mistral-embed" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "mistral-embed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-embed", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-embed", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mistral Embed" ], "families": [ "mistral-embed" ], "modes": [ "chat", "embedding" ], "releaseDate": "2023-12-11", "lastUpdated": "2023-12-11", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-embed", "modelKey": "mistral-embed", "displayName": "Mistral Embed", "family": "mistral-embed", "metadata": { "lastUpdated": "2023-12-11", "openWeights": false, "releaseDate": "2023-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-embed", "modelKey": "mistral/mistral-embed", "displayName": "Mistral Embed", "family": "mistral-embed", "metadata": { "lastUpdated": "2023-12-11", "openWeights": false, "releaseDate": "2023-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-embed", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-embed", "mode": "chat" } ] }, { "id": "mistral/mistral-large", "provider": "mistral", "model": "mistral-large", "displayName": "Mistral Large", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure_ai", "kilo", "nano-gpt", "openrouter", "snowflake", "vercel_ai_gateway", "watsonx" ], "aliases": [ "azure_ai/mistral-large", "kilo/mistralai/mistral-large", "nano-gpt/mistralai/mistral-large", "openrouter/mistralai/mistral-large", "snowflake/mistral-large", "vercel_ai_gateway/mistral/mistral-large", "watsonx/mistralai/mistral-large" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false, "functionCalling": true, "promptCaching": true, "systemMessages": true, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 6.001 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 4, "output": 12 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mistral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/mistral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/mistralai/mistral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-large", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral Large", "Mistral Large 2411" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11-30", "releaseDate": "2024-07-24", "lastUpdated": "2025-12-02", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-large", "modelKey": "mistralai/mistral-large", "displayName": "Mistral Large", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-07-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-large", "modelKey": "mistralai/mistral-large", "displayName": "Mistral Large 2411", "family": "mistral-large", "metadata": { "lastUpdated": "2024-02-26", "openWeights": false, "releaseDate": "2024-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-large", "modelKey": "mistralai/mistral-large", "displayName": "Mistral Large", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11-30", "lastUpdated": "2024-02-26", "openWeights": false, "releaseDate": "2024-02-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-large", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mistral-large", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/mistral-large", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-large", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/mistralai/mistral-large", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-large", "displayName": "Mistral Large", "metadata": { "canonicalSlug": "mistralai/mistral-large", "createdAt": "2024-02-26T00:00:00.000Z", "knowledgeCutoff": "2024-11-30", "links": { "details": "/api/v1/models/mistralai/mistral-large/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-large-2402", "provider": "mistral", "model": "mistral-large-2402", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "mistral" ], "aliases": [ "azure/mistral-large-2402", "mistral/mistral-large-2402" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/mistral-large-2402", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-2402", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 4, "output": 12 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/mistral-large-2402", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-2402", "mode": "chat" } ] }, { "id": "mistral/mistral-large-2407", "provider": "mistral", "model": "mistral-large-2407", "displayName": "Mistral Large 2407", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure_ai", "kilo", "mistral", "openrouter" ], "aliases": [ "azure_ai/mistral-large-2407", "kilo/mistralai/mistral-large-2407", "mistral/mistral-large-2407", "openrouter/mistralai/mistral-large-2407" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-large-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-large-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-large-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 9 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-large-2407", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral Large 2407" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-03-31", "releaseDate": "2024-11-19", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-large-2407", "modelKey": "mistralai/mistral-large-2407", "displayName": "Mistral Large 2407", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-11-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-large-2407", "modelKey": "mistralai/mistral-large-2407", "displayName": "Mistral Large 2407", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-03-31", "lastUpdated": "2024-11-19", "openWeights": false, "releaseDate": "2024-11-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-large-2407", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-2407", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-large-2407", "displayName": "Mistral Large 2407", "metadata": { "canonicalSlug": "mistralai/mistral-large-2407", "createdAt": "2024-11-19T01:06:55.000Z", "knowledgeCutoff": "2024-03-31", "links": { "details": "/api/v1/models/mistralai/mistral-large-2407/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-large-2411", "provider": "mistral", "model": "mistral-large-2411", "displayName": "Mistral Large 2.1", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "github-models", "helicone", "kilo", "merge-gateway", "mistral", "vertex_ai-mistral_models" ], "aliases": [ "azure-cognitive-services/mistral-large-2411", "azure/mistral-large-2411", "github-models/mistral-ai/mistral-large-2411", "helicone/mistral-large-2411", "kilo/mistralai/mistral-large-2411", "merge-gateway/mistral/mistral-large-2411", "mistral/mistral-large-2411", "vertex_ai-mistral_models/vertex_ai/mistral-large-2411" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "azure", "model": "mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-2411", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large-2411", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral Large 2.1", "Mistral Large 24.11", "Mistral Large 2411", "Mistral-Large" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-11-01", "lastUpdated": "2024-11-01", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-large-2411", "modelKey": "mistral-large-2411", "displayName": "Mistral Large 24.11", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-large-2411", "modelKey": "mistral-large-2411", "displayName": "Mistral Large 24.11", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/mistral-large-2411", "modelKey": "mistral-ai/mistral-large-2411", "displayName": "Mistral Large 24.11", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "mistral-large-2411", "modelKey": "mistral-large-2411", "displayName": "Mistral-Large", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-24", "openWeights": false, "releaseDate": "2024-07-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-large-2411", "modelKey": "mistralai/mistral-large-2411", "displayName": "Mistral Large 2411", "metadata": { "lastUpdated": "2024-11-04", "openWeights": true, "releaseDate": "2024-07-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-large-2411", "modelKey": "mistral/mistral-large-2411", "displayName": "Mistral Large 2.1", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-18", "openWeights": true, "releaseDate": "2024-11-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-large-2411", "modelKey": "mistral-large-2411", "displayName": "Mistral Large 2.1", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-18", "openWeights": true, "releaseDate": "2024-11-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-2411", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large-2411", "mode": "chat" } ] }, { "id": "mistral/mistral-large-2512", "provider": "mistral", "model": "mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "anyapi", "cortecs", "kilo", "llmgateway", "merge-gateway", "mistral", "openrouter" ], "aliases": [ "302ai/mistral-large-2512", "anyapi/mistralai/mistral-large-2512", "cortecs/mistral-large-2512", "kilo/mistralai/mistral-large-2512", "llmgateway/mistral-large-2512", "merge-gateway/mistral/mistral-large-2512", "mistral/mistral-large-2512", "openrouter/mistralai/mistral-large-2512" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true, "promptCaching": false, "parallelFunctionCalling": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.3 } }, { "source": "models.dev", "provider": "cortecs", "model": "mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-large-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mistral-large-2512", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-large-2512", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Mistral Large 3", "Mistral Large 3 2512", "Mistral: Mistral Large 3 2512", "mistral-large-2512" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "mistral-large-2512", "modelKey": "mistral-large-2512", "displayName": "mistral-large-2512", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "mistralai/mistral-large-2512", "modelKey": "mistralai/mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "mistral-large-2512", "modelKey": "mistral-large-2512", "displayName": "Mistral Large 3 2512", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-large-2512", "modelKey": "mistralai/mistral-large-2512", "displayName": "Mistral: Mistral Large 3 2512", "metadata": { "lastUpdated": "2025-12-16", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mistral-large-2512", "modelKey": "mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-large-2512", "modelKey": "mistral/mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-large-2512", "modelKey": "mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-large-2512", "modelKey": "mistralai/mistral-large-2512", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-2512", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/models/mistral-large-3-25-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mistral-large-2512", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-large-2512", "displayName": "Mistral: Mistral Large 3 2512", "metadata": { "canonicalSlug": "mistralai/mistral-large-2512", "createdAt": "2025-12-01T21:27:52.000Z", "links": { "details": "/api/v1/models/mistralai/mistral-large-2512/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-large-3", "provider": "mistral", "model": "mistral-large-3", "displayName": "Mistral Large 3", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure_ai", "mistral", "routing-run", "vercel" ], "aliases": [ "azure_ai/mistral-large-3", "mistral/mistral-large-3", "routing-run/route/mistral-large-3", "vercel/mistral/mistral-large-3" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/mistral-large-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/mistral-large-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-large-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Mistral Large 3" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "lastUpdated": "2025-12-02", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mistral-large-3", "modelKey": "route/mistral-large-3", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-large-3", "modelKey": "mistral/mistral-large-3", "displayName": "Mistral Large 3", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-large-3", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-3", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/models/mistral-large-3-25-12" } } ] }, { "id": "mistral/mistral-large-3-675b-instruct-2512", "provider": "mistral", "model": "mistral-large-3-675b-instruct-2512", "displayName": "Mistral Large 3 675B", "family": "mistral-large", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "nvidia" ], "aliases": [ "nano-gpt/mistralai/mistral-large-3-675b-instruct-2512", "nvidia/mistralai/mistral-large-3-675b-instruct-2512" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-large-3-675b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mistral-large-3-675b-instruct-2512", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mistral Large 3 675B", "Mistral Large 3 675B Instruct 2512" ], "families": [ "mistral-large" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-large-3-675b-instruct-2512", "modelKey": "mistralai/mistral-large-3-675b-instruct-2512", "displayName": "Mistral Large 3 675B", "family": "mistral-large", "metadata": { "lastUpdated": "2025-12-02", "openWeights": false, "releaseDate": "2025-12-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mistral-large-3-675b-instruct-2512", "modelKey": "mistralai/mistral-large-3-675b-instruct-2512", "displayName": "Mistral Large 3 675B Instruct 2512", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } } ] }, { "id": "mistral/mistral-large-3-fp8", "provider": "mistral", "model": "mistral-large-3-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8", "mode": "chat" } ] }, { "id": "mistral/mistral-large-3:675b", "provider": "mistral", "model": "mistral-large-3:675b", "displayName": "mistral-large-3:675b", "family": "mistral-large", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/mistral-large-3:675b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "mistral-large-3:675b" ], "families": [ "mistral-large" ], "releaseDate": "2025-12-02", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "mistral-large-3:675b", "modelKey": "mistral-large-3:675b", "displayName": "mistral-large-3:675b", "family": "mistral-large", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-02" } } ] }, { "id": "mistral/mistral-large-instruct-2407", "provider": "mistral", "model": "mistral-large-instruct-2407", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/mistral-large-instruct-2407" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/mistral-large-instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mistral-large-instruct-2407", "mode": "chat" } ] }, { "id": "mistral/mistral-large-instruct-2411", "provider": "mistral", "model": "mistral-large-instruct-2411", "displayName": "Mistral Large Instruct 2411", "family": "mistral-large", "sources": [ "models.dev" ], "providers": [ "io-net" ], "aliases": [ "io-net/mistralai/Mistral-Large-Instruct-2411" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "io-net", "model": "mistralai/Mistral-Large-Instruct-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "cacheWrite": 4, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral Large Instruct 2411" ], "families": [ "mistral-large" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-11-01", "lastUpdated": "2024-11-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "mistralai/Mistral-Large-Instruct-2411", "modelKey": "mistralai/Mistral-Large-Instruct-2411", "displayName": "Mistral Large Instruct 2411", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } } ] }, { "id": "mistral/mistral-large-latest", "provider": "mistral", "model": "mistral-large-latest", "displayName": "Mistral Large (latest)", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure_ai", "llmgateway", "merge-gateway", "mistral" ], "aliases": [ "azure/mistral-large-latest", "azure_ai/mistral-large-latest", "llmgateway/mistral-large-latest", "merge-gateway/mistral/mistral-large-latest", "mistral/mistral-large-latest" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mistral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-large-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "azure", "model": "azure/mistral-large-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-large-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Mistral Large (latest)" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "lastUpdated": "2025-12-02", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mistral-large-latest", "modelKey": "mistral-large-latest", "displayName": "Mistral Large (latest)", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-large-latest", "modelKey": "mistral/mistral-large-latest", "displayName": "Mistral Large (latest)", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-large-latest", "modelKey": "mistral-large-latest", "displayName": "Mistral Large (latest)", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-large-latest", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/mistral-large-latest", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-large-latest", "mode": "chat", "metadata": { "source": "https://docs.mistral.ai/models/mistral-large-3-25-12" } } ] }, { "id": "mistral/mistral-large@2407", "provider": "mistral", "model": "mistral-large@2407", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-large@2407" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@2407", "mode": "chat" } ] }, { "id": "mistral/mistral-large@2411-001", "provider": "mistral", "model": "mistral-large@2411-001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-large@2411-001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@2411-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@2411-001", "mode": "chat" } ] }, { "id": "mistral/mistral-large@latest", "provider": "mistral", "model": "mistral-large@latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-large@latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-large@latest", "mode": "chat" } ] }, { "id": "mistral/mistral-large2", "provider": "mistral", "model": "mistral-large2", "displayName": "Mistral Large (latest)", "family": "mistral-large", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "snowflake", "snowflake-cortex" ], "aliases": [ "snowflake-cortex/mistral-large2", "snowflake/mistral-large2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/mistral-large2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral Large (latest)" ], "families": [ "mistral-large" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "mistral-large2", "modelKey": "mistral-large2", "displayName": "Mistral Large (latest)", "family": "mistral-large", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/mistral-large2", "mode": "chat" } ] }, { "id": "mistral/mistral-medium", "provider": "mistral", "model": "mistral-medium", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "vercel" ], "aliases": [ "mistral/mistral-medium", "vercel/mistral/mistral-medium" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/mistral-medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.7, "output": 8.1 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.1" ], "families": [ "mistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-05-07", "lastUpdated": "2025-05-07", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-medium", "modelKey": "mistral/mistral-medium", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-medium", "mode": "chat" } ] }, { "id": "mistral/mistral-medium-2312", "provider": "mistral", "model": "mistral-medium-2312", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-medium-2312" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-medium-2312", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.7, "output": 8.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-medium-2312", "mode": "chat" } ] }, { "id": "mistral/mistral-medium-2505", "provider": "mistral", "model": "mistral-medium-2505", "displayName": "Mistral Medium 3", "family": "mistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "merge-gateway", "mistral", "routing-run", "watsonx" ], "aliases": [ "azure-cognitive-services/mistral-medium-2505", "azure/mistral-medium-2505", "azure_ai/mistral-medium-2505", "github-models/mistral-ai/mistral-medium-2505", "merge-gateway/mistral/mistral-medium-2505", "mistral/mistral-medium-2505", "routing-run/route/mistral-medium-2505", "watsonx/mistralai/mistral-medium-2505" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "parallelFunctionCalling": true, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/mistral-medium-2505", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-medium-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-medium-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/mistralai/mistral-medium-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 10 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 2505", "Mistral Medium 3", "Mistral Medium 3 (25.05)" ], "families": [ "mistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-05-07", "lastUpdated": "2025-05-07", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-medium-2505", "modelKey": "mistral-medium-2505", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-medium-2505", "modelKey": "mistral-medium-2505", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/mistral-medium-2505", "modelKey": "mistral-ai/mistral-medium-2505", "displayName": "Mistral Medium 3 (25.05)", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-05-01", "openWeights": false, "releaseDate": "2025-05-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-medium-2505", "modelKey": "mistral/mistral-medium-2505", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-medium-2505", "modelKey": "mistral-medium-2505", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mistral-medium-2505", "modelKey": "route/mistral-medium-2505", "displayName": "Mistral Medium 2505", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-medium-2505", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-medium-2505", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/mistralai/mistral-medium-2505", "mode": "chat" } ] }, { "id": "mistral/mistral-medium-2508", "provider": "mistral", "model": "mistral-medium-2508", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "sources": [ "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-medium-2508" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "mistral-medium-2508", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.1" ], "families": [ "mistral-medium" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-08-12", "lastUpdated": "2025-08-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-medium-2508", "modelKey": "mistral-medium-2508", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } } ] }, { "id": "mistral/mistral-medium-2604", "provider": "mistral", "model": "mistral-medium-2604", "displayName": "Mistral Medium 3.5", "family": "mistral-medium", "sources": [ "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-medium-2604" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "mistral-medium-2604", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.5" ], "families": [ "mistral-medium" ], "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-medium-2604", "modelKey": "mistral-medium-2604", "displayName": "Mistral Medium 3.5", "family": "mistral-medium", "metadata": { "lastUpdated": "2026-04-29", "openWeights": true, "releaseDate": "2026-04-29", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } } ] }, { "id": "mistral/mistral-medium-3", "provider": "mistral", "model": "mistral-medium-3", "displayName": "Mistral: Mistral Medium 3", "family": "mistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter", "vertex_ai-mistral_models" ], "aliases": [ "kilo/mistralai/mistral-medium-3", "nano-gpt/mistralai/mistral-medium-3", "openrouter/mistralai/mistral-medium-3", "vertex_ai-mistral_models/vertex_ai/mistral-medium-3", "vertex_ai-mistral_models/vertex_ai/mistralai/mistral-medium-3" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 8191, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-medium-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-medium-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-medium-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-medium-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/mistral-medium-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-medium-3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3", "Mistral: Mistral Medium 3" ], "families": [ "mistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-07", "lastUpdated": "2025-05-07", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-medium-3", "modelKey": "mistralai/mistral-medium-3", "displayName": "Mistral: Mistral Medium 3", "metadata": { "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-medium-3", "modelKey": "mistralai/mistral-medium-3", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-medium-3", "modelKey": "mistralai/mistral-medium-3", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-medium-3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/mistral-medium-3", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-medium-3", "displayName": "Mistral: Mistral Medium 3", "metadata": { "canonicalSlug": "mistralai/mistral-medium-3", "createdAt": "2025-05-07T14:15:41.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/mistralai/mistral-medium-3/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-medium-3-1-2508", "provider": "mistral", "model": "mistral-medium-3-1-2508", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-medium-3-1-2508" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-medium-3-1-2508", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-medium-3-1-2508", "mode": "chat", "metadata": { "source": "https://mistral.ai/news/mistral-medium-3" } } ] }, { "id": "mistral/mistral-medium-3-5", "provider": "mistral", "model": "mistral-medium-3-5", "displayName": "Mistral: Mistral Medium 3.5", "family": "mistral-medium", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/mistralai/mistral-medium-3-5", "openrouter/mistralai/mistral-medium-3-5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-medium-3-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-medium-3-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-medium-3-5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.5", "Mistral: Mistral Medium 3.5" ], "families": [ "mistral-medium" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-05-07", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-medium-3-5", "modelKey": "mistralai/mistral-medium-3-5", "displayName": "Mistral: Mistral Medium 3.5", "metadata": { "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-04-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-medium-3-5", "modelKey": "mistralai/mistral-medium-3-5", "displayName": "Mistral Medium 3.5", "family": "mistral-medium", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-medium-3-5", "displayName": "Mistral: Mistral Medium 3.5", "metadata": { "canonicalSlug": "mistralai/mistral-medium-3.5-20260430", "createdAt": "2026-04-30T17:33:59.000Z", "links": { "details": "/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "high", "none" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-medium-3-instruct", "provider": "mistral", "model": "mistral-medium-3-instruct", "displayName": "Mistral Medium 3", "family": "mistral-medium", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/mistralai/mistral-medium-3-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mistral-medium-3-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3" ], "families": [ "mistral-medium" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mistral-medium-3-instruct", "modelKey": "mistralai/mistral-medium-3-instruct", "displayName": "Mistral Medium 3", "family": "mistral-medium", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "mistral/mistral-medium-3.1", "provider": "mistral", "model": "mistral-medium-3.1", "displayName": "Mistral: Mistral Medium 3.1", "family": "mistral-medium", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/mistralai/mistral-medium-3.1", "nano-gpt/mistralai/mistral-medium-3.1", "openrouter/mistralai/mistral-medium-3.1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-medium-3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-medium-3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-medium-3.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-medium-3.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.04, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.1", "Mistral: Mistral Medium 3.1" ], "families": [ "mistral-medium" ], "knowledgeCutoff": "2025-06-30", "releaseDate": "2025-08-12", "lastUpdated": "2025-08-12", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-medium-3.1", "modelKey": "mistralai/mistral-medium-3.1", "displayName": "Mistral: Mistral Medium 3.1", "metadata": { "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-medium-3.1", "modelKey": "mistralai/mistral-medium-3.1", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "metadata": { "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-medium-3.1", "modelKey": "mistralai/mistral-medium-3.1", "displayName": "Mistral Medium 3.1", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-06-30", "lastUpdated": "2025-08-13", "openWeights": false, "releaseDate": "2025-08-13" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-medium-3.1", "displayName": "Mistral: Mistral Medium 3.1", "metadata": { "canonicalSlug": "mistralai/mistral-medium-3.1", "createdAt": "2025-08-13T14:33:59.000Z", "knowledgeCutoff": "2025-06-30", "links": { "details": "/api/v1/models/mistralai/mistral-medium-3.1/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-medium-3.5", "provider": "mistral", "model": "mistral-medium-3.5", "displayName": "Mistral Medium 3.5", "family": "mistral-medium", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "vercel" ], "aliases": [ "nano-gpt/mistral/mistral-medium-3.5", "vercel/mistral/mistral-medium-3.5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistral/mistral-medium-3.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/mistral-medium-3.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.5", "Mistral Medium Latest" ], "families": [ "mistral-medium" ], "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistral/mistral-medium-3.5", "modelKey": "mistral/mistral-medium-3.5", "displayName": "Mistral Medium 3.5", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2026-04-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-medium-3.5", "modelKey": "mistral/mistral-medium-3.5", "displayName": "Mistral Medium Latest", "family": "mistral-medium", "metadata": { "lastUpdated": "2026-05-21", "openWeights": false, "releaseDate": "2026-05-21", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } } ] }, { "id": "mistral/mistral-medium-3.5-128b", "provider": "mistral", "model": "mistral-medium-3.5-128b", "displayName": "Mistral Medium 3.5 128B", "family": "mistral-medium", "sources": [ "models.dev" ], "providers": [ "berget", "scaleway" ], "aliases": [ "berget/mistralai/Mistral-Medium-3.5-128B", "scaleway/mistral-medium-3.5-128b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "berget", "model": "mistralai/Mistral-Medium-3.5-128B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.65, "output": 5.5 } }, { "source": "models.dev", "provider": "scaleway", "model": "mistral-medium-3.5-128b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.5 128B" ], "families": [ "mistral-medium" ], "knowledgeCutoff": "2026-04", "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "mistralai/Mistral-Medium-3.5-128B", "modelKey": "mistralai/Mistral-Medium-3.5-128B", "displayName": "Mistral Medium 3.5 128B", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2026-04", "lastUpdated": "2026-04-29", "openWeights": true, "releaseDate": "2026-04-29", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "mistral-medium-3.5-128b", "modelKey": "mistral-medium-3.5-128b", "displayName": "Mistral Medium 3.5 128B", "family": "mistral-medium", "metadata": { "lastUpdated": "2026-04-29", "openWeights": true, "releaseDate": "2026-04-29" } } ] }, { "id": "mistral/mistral-medium-3.5:thinking", "provider": "mistral", "model": "mistral-medium-3.5:thinking", "displayName": "Mistral Medium 3.5 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistral/mistral-medium-3.5:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistral/mistral-medium-3.5:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Mistral Medium 3.5 Thinking" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistral/mistral-medium-3.5:thinking", "modelKey": "mistral/mistral-medium-3.5:thinking", "displayName": "Mistral Medium 3.5 Thinking", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } } ] }, { "id": "mistral/mistral-medium-3@001", "provider": "mistral", "model": "mistral-medium-3@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-medium-3@001", "vertex_ai-mistral_models/vertex_ai/mistralai/mistral-medium-3@001" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-medium-3@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/mistral-medium-3@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-medium-3@001", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistralai/mistral-medium-3@001", "mode": "chat" } ] }, { "id": "mistral/mistral-medium-latest", "provider": "mistral", "model": "mistral-medium-latest", "displayName": "Mistral Medium (latest)", "family": "mistral-medium", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "mistral" ], "aliases": [ "merge-gateway/mistral/mistral-medium-latest", "mistral/mistral-medium-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-medium-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-medium-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Mistral Medium (latest)" ], "families": [ "mistral-medium" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-08-12", "lastUpdated": "2025-08-12", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-medium-latest", "modelKey": "mistral/mistral-medium-latest", "displayName": "Mistral Medium (latest)", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-medium-latest", "modelKey": "mistral-medium-latest", "displayName": "Mistral Medium (latest)", "family": "mistral-medium", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-08-12", "openWeights": false, "releaseDate": "2025-08-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-medium-latest", "mode": "chat" } ] }, { "id": "mistral/mistral-nemo", "provider": "mistral", "model": "mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "helicone", "kilo", "mistral", "novita", "novita-ai", "openrouter", "vercel" ], "aliases": [ "azure-cognitive-services/mistral-nemo", "azure/mistral-nemo", "azure_ai/mistral-nemo", "github-models/mistral-ai/mistral-nemo", "helicone/mistral-nemo", "kilo/mistralai/mistral-nemo", "mistral/mistral-nemo", "novita-ai/mistralai/mistral-nemo", "novita/mistralai/mistral-nemo", "openrouter/mistralai/mistral-nemo", "vercel/mistral/mistral-nemo" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "azure", "model": "mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 40 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.04 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "novita-ai", "model": "mistralai/mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.17 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.03 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-nemo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "novita", "model": "novita/mistralai/mistral-nemo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.17 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-nemo", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo", "Mistral: Mistral Nemo" ], "families": [ "mistral-nemo" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-07-18", "lastUpdated": "2024-07-18", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-nemo", "modelKey": "mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-18", "openWeights": true, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-nemo", "modelKey": "mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-18", "openWeights": true, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/mistral-nemo", "modelKey": "mistral-ai/mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-03", "lastUpdated": "2024-07-18", "openWeights": true, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "mistral-nemo", "modelKey": "mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-nemo", "modelKey": "mistralai/mistral-nemo", "displayName": "Mistral: Mistral Nemo", "metadata": { "lastUpdated": "2024-07-30", "openWeights": true, "releaseDate": "2024-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-nemo", "modelKey": "mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-01", "openWeights": true, "releaseDate": "2024-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "mistralai/mistral-nemo", "modelKey": "mistralai/mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-30", "openWeights": true, "releaseDate": "2024-07-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-nemo", "modelKey": "mistralai/mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-01", "openWeights": true, "releaseDate": "2024-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-nemo", "modelKey": "mistral/mistral-nemo", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-nemo", "mode": "chat", "metadata": { "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/mistralai/mistral-nemo", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-nemo", "displayName": "Mistral: Mistral Nemo", "metadata": { "canonicalSlug": "mistralai/mistral-nemo", "createdAt": "2024-07-19T00:00:00.000Z", "huggingFaceId": "mistralai/Mistral-Nemo-Instruct-2407", "instructType": "mistral", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/mistralai/mistral-nemo/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-nemo-12b-instruct", "provider": "mistral", "model": "mistral-nemo-12b-instruct", "displayName": "Mistral Nemo 12B Instruct", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "inference" ], "aliases": [ "inference/mistral/mistral-nemo-12b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "inference", "model": "mistral/mistral-nemo-12b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.038, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo 12B Instruct" ], "families": [ "mistral-nemo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inference", "providerName": "Inference", "providerApi": "https://inference.net/v1", "providerDoc": "https://inference.net/models", "model": "mistral/mistral-nemo-12b-instruct", "modelKey": "mistral/mistral-nemo-12b-instruct", "displayName": "Mistral Nemo 12B Instruct", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-01-01", "openWeights": true, "releaseDate": "2025-01-01" } } ] }, { "id": "mistral/mistral-nemo-base-2407", "provider": "mistral", "model": "mistral-nemo-base-2407", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407", "mode": "chat" } ] }, { "id": "mistral/mistral-nemo-instruct-2407", "provider": "mistral", "model": "mistral-nemo-instruct-2407", "displayName": "Mistral-Nemo-Instruct-2407", "family": "unsloth", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "chutes", "deepinfra", "digitalocean", "fireworks_ai", "gradient_ai", "io-net", "meganova", "nano-gpt", "nebius", "ovhcloud" ], "aliases": [ "chutes/unsloth/Mistral-Nemo-Instruct-2407", "deepinfra/mistralai/Mistral-Nemo-Instruct-2407", "digitalocean/mistral-nemo-instruct-2407", "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407", "gradient_ai/mistral-nemo-instruct-2407", "io-net/mistralai/Mistral-Nemo-Instruct-2407", "meganova/mistralai/Mistral-Nemo-Instruct-2407", "nano-gpt/mistralai/Mistral-Nemo-Instruct-2407", "nebius/mistralai/Mistral-Nemo-Instruct-2407", "ovhcloud/Mistral-Nemo-Instruct-2407", "ovhcloud/mistral-nemo-instruct-2407" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "unsloth/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.02, "output": 0.04 } }, { "source": "models.dev", "provider": "digitalocean", "model": "mistral-nemo-instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } }, { "source": "models.dev", "provider": "io-net", "model": "mistralai/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.04, "input": 0.02, "output": 0.04 } }, { "source": "models.dev", "provider": "meganova", "model": "mistralai/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.04 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1207 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "mistral-nemo-instruct-2407", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.04 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "gradient_ai", "model": "gradient_ai/mistral-nemo-instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } }, { "source": "litellm", "provider": "nebius", "model": "nebius/mistralai/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.12 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Mistral-Nemo-Instruct-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.13 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo", "Mistral Nemo Instruct", "Mistral Nemo Instruct 2407", "Mistral-Nemo-Instruct-2407" ], "families": [ "mistral", "mistral-nemo", "unsloth" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "unsloth/Mistral-Nemo-Instruct-2407", "modelKey": "unsloth/Mistral-Nemo-Instruct-2407", "displayName": "Mistral Nemo Instruct 2407", "family": "unsloth", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "mistral-nemo-instruct-2407", "modelKey": "mistral-nemo-instruct-2407", "displayName": "Mistral Nemo Instruct", "family": "mistral", "status": "deprecated", "metadata": { "lastUpdated": "2024-07-18", "openWeights": true, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "mistralai/Mistral-Nemo-Instruct-2407", "modelKey": "mistralai/Mistral-Nemo-Instruct-2407", "displayName": "Mistral Nemo Instruct 2407", "family": "mistral-nemo", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-07-01", "openWeights": true, "releaseDate": "2024-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "mistralai/Mistral-Nemo-Instruct-2407", "modelKey": "mistralai/Mistral-Nemo-Instruct-2407", "displayName": "Mistral Nemo Instruct 2407", "family": "mistral", "metadata": { "lastUpdated": "2024-07-18", "openWeights": true, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/Mistral-Nemo-Instruct-2407", "modelKey": "mistralai/Mistral-Nemo-Instruct-2407", "displayName": "Mistral Nemo", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "mistral-nemo-instruct-2407", "modelKey": "mistral-nemo-instruct-2407", "displayName": "Mistral-Nemo-Instruct-2407", "metadata": { "lastUpdated": "2024-11-20", "openWeights": true, "releaseDate": "2024-11-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Nemo-Instruct-2407", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gradient_ai", "model": "gradient_ai/mistral-nemo-instruct-2407", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/mistralai/Mistral-Nemo-Instruct-2407", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Mistral-Nemo-Instruct-2407", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407" } } ] }, { "id": "mistral/mistral-nemo-instruct-2407-fp8", "provider": "mistral", "model": "mistral-nemo-instruct-2407-fp8", "displayName": "Mistral Nemo", "family": "mistral", "sources": [ "models.dev" ], "providers": [ "stackit" ], "aliases": [ "stackit/neuralmagic/Mistral-Nemo-Instruct-2407-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "neuralmagic/Mistral-Nemo-Instruct-2407-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49, "output": 0.71 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo" ], "families": [ "mistral" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "neuralmagic/Mistral-Nemo-Instruct-2407-FP8", "modelKey": "neuralmagic/Mistral-Nemo-Instruct-2407-FP8", "displayName": "Mistral Nemo", "family": "mistral", "metadata": { "lastUpdated": "2024-07-01", "openWeights": true, "releaseDate": "2024-07-01" } } ] }, { "id": "mistral/mistral-nemo@2407", "provider": "mistral", "model": "mistral-nemo@2407", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-nemo@2407" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-nemo@2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-nemo@2407", "mode": "chat" } ] }, { "id": "mistral/mistral-nemo@latest", "provider": "mistral", "model": "mistral-nemo@latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-nemo@latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-nemo@latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-nemo@latest", "mode": "chat" } ] }, { "id": "mistral/mistral-nemotron", "provider": "mistral", "model": "mistral-nemotron", "displayName": "mistral-nemotron", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/mistralai/mistral-nemotron" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mistral-nemotron", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "mistral-nemotron" ], "families": [ "nemotron" ], "releaseDate": "2025-06-11", "lastUpdated": "2025-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mistral-nemotron", "modelKey": "mistralai/mistral-nemotron", "displayName": "mistral-nemotron", "family": "nemotron", "metadata": { "lastUpdated": "2025-06-12", "openWeights": true, "releaseDate": "2025-06-11" } } ] }, { "id": "mistral/mistral-ocr-2505", "provider": "mistral", "model": "mistral-ocr-2505", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "vertex_ai" ], "aliases": [ "vertex_ai/mistral-ocr-2505" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/mistral-ocr-2505", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "ocr": 0.0005 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/mistral-ocr-2505", "mode": "ocr", "metadata": { "source": "https://cloud.google.com/generative-ai-app-builder/pricing", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "mistral/mistral-ocr-2505-completion", "provider": "mistral", "model": "mistral-ocr-2505-completion", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-ocr-2505-completion" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-ocr-2505-completion", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "annotation": 0.003, "ocr": 0.001 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-ocr-2505-completion", "mode": "ocr", "metadata": { "source": "https://mistral.ai/pricing#api-pricing", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "mistral/mistral-ocr-latest", "provider": "mistral", "model": "mistral-ocr-latest", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-ocr-latest" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-ocr-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPage": { "annotation": 0.003, "ocr": 0.001 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-ocr-latest", "mode": "ocr", "metadata": { "source": "https://mistral.ai/pricing#api-pricing", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "mistral/mistral-saba", "provider": "mistral", "model": "mistral-saba", "displayName": "Mistral: Saba", "family": "mistral", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/mistralai/mistral-saba", "nano-gpt/mistralai/mistral-saba", "openrouter/mistralai/mistral-saba" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32768, "inputTokens": 32000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-saba", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-saba", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1989, "output": 0.595 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-saba", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-saba", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Mistral Saba", "Mistral: Saba", "Saba" ], "families": [ "mistral" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-02-17", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-saba", "modelKey": "mistralai/mistral-saba", "displayName": "Mistral: Saba", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-saba", "modelKey": "mistralai/mistral-saba", "displayName": "Mistral Saba", "family": "mistral", "metadata": { "lastUpdated": "2025-02-17", "openWeights": false, "releaseDate": "2025-02-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-saba", "modelKey": "mistralai/mistral-saba", "displayName": "Saba", "family": "mistral", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-02-17", "openWeights": false, "releaseDate": "2025-02-17" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-saba", "displayName": "Mistral: Saba", "metadata": { "canonicalSlug": "mistralai/mistral-saba-2502", "createdAt": "2025-02-17T14:40:39.000Z", "knowledgeCutoff": "2024-09-30", "links": { "details": "/api/v1/models/mistralai/mistral-saba-2502/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-saba-24b", "provider": "mistral", "model": "mistral-saba-24b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/mistral/mistral-saba-24b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-saba-24b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.79, "output": 0.79 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-saba-24b", "mode": "chat" } ] }, { "id": "mistral/mistral-small", "provider": "mistral", "model": "mistral-small", "displayName": "Mistral Small 3.2", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure_ai", "helicone", "mistral", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure_ai/mistral-small", "helicone/mistral-small", "mistral/mistral-small", "vercel/mistral/mistral-small", "vercel_ai_gateway/mistral/mistral-small" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "mistral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.2 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/mistral-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Mistral Small (latest)", "Mistral Small 3.2" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-06-20", "lastUpdated": "2025-06-20", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "mistral-small", "modelKey": "mistral-small", "displayName": "Mistral Small 3.2", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/mistral-small", "modelKey": "mistral/mistral-small", "displayName": "Mistral Small (latest)", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2024-09-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-small", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-small", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mistral-small", "mode": "chat" } ] }, { "id": "mistral/mistral-small-24b-instruct-2501", "provider": "mistral", "model": "mistral-small-24b-instruct-2501", "displayName": "Mistral: Mistral Small 3", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "deepinfra", "fireworks_ai", "kilo", "openrouter", "together_ai" ], "aliases": [ "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501", "kilo/mistralai/mistral-small-24b-instruct-2501", "openrouter/mistralai/mistral-small-24b-instruct-2501", "together_ai/mistralai/Mistral-Small-24B-Instruct-2501" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-small-24b-instruct-2501", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.08 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-small-24b-instruct-2501", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.08 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/mistralai/Mistral-Small-24B-Instruct-2501", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-small-24b-instruct-2501", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.08 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3", "Mistral: Mistral Small 3" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-12-29", "lastUpdated": "2026-01-10", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-small-24b-instruct-2501", "modelKey": "mistralai/mistral-small-24b-instruct-2501", "displayName": "Mistral: Mistral Small 3", "metadata": { "lastUpdated": "2026-01-10", "openWeights": true, "releaseDate": "2025-12-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-small-24b-instruct-2501", "modelKey": "mistralai/mistral-small-24b-instruct-2501", "displayName": "Mistral Small 3", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-01-30", "openWeights": true, "releaseDate": "2025-01-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/mistralai/Mistral-Small-24B-Instruct-2501", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-small-24b-instruct-2501", "displayName": "Mistral: Mistral Small 3", "metadata": { "canonicalSlug": "mistralai/mistral-small-24b-instruct-2501", "createdAt": "2025-01-30T16:43:29.000Z", "huggingFaceId": "mistralai/Mistral-Small-24B-Instruct-2501", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 32768, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "mistral/mistral-small-2503", "provider": "mistral", "model": "mistral-small-2503", "displayName": "Mistral Small 3.1", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "azure_ai", "github-models", "routing-run", "vertex_ai-mistral_models", "watsonx" ], "aliases": [ "azure-cognitive-services/mistral-small-2503", "azure/mistral-small-2503", "azure_ai/mistral-small-2503", "github-models/mistral-ai/mistral-small-2503", "routing-run/route/mistral-small-2503", "vertex_ai-mistral_models/vertex_ai/mistral-small-2503", "watsonx/mistralai/mistral-small-2503" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "mistral-small-2503", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "azure", "model": "mistral-small-2503", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "github-models", "model": "mistral-ai/mistral-small-2503", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/mistral-small-2503", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/mistral-small-2503", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-small-2503", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/mistralai/mistral-small-2503", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Mistral Small 2503", "Mistral Small 3.1" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2025-03-01", "lastUpdated": "2025-03-01", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-small-2503", "modelKey": "mistral-small-2503", "displayName": "Mistral Small 3.1", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-03-01", "openWeights": false, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "mistral-small-2503", "modelKey": "mistral-small-2503", "displayName": "Mistral Small 3.1", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-03-01", "openWeights": false, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "mistral-ai/mistral-small-2503", "modelKey": "mistral-ai/mistral-small-2503", "displayName": "Mistral Small 3.1", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-03-01", "openWeights": false, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mistral-small-2503", "modelKey": "route/mistral-small-2503", "displayName": "Mistral Small 2503", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/mistral-small-2503", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-small-2503", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/mistralai/mistral-small-2503", "mode": "chat" } ] }, { "id": "mistral/mistral-small-2503@001", "provider": "mistral", "model": "mistral-small-2503@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-mistral_models" ], "aliases": [ "vertex_ai-mistral_models/vertex_ai/mistral-small-2503@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-small-2503@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-mistral_models", "model": "vertex_ai/mistral-small-2503@001", "mode": "chat" } ] }, { "id": "mistral/mistral-small-2506", "provider": "mistral", "model": "mistral-small-2506", "displayName": "Mistral Small 3.2", "family": "mistral-small", "sources": [ "models.dev" ], "providers": [ "llmgateway", "mistral" ], "aliases": [ "llmgateway/mistral-small-2506", "mistral/mistral-small-2506" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "mistral-small-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-small-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.2" ], "families": [ "mistral-small" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-06-20", "lastUpdated": "2025-06-20", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "mistral-small-2506", "modelKey": "mistral-small-2506", "displayName": "Mistral Small 3.2", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-small-2506", "modelKey": "mistral-small-2506", "displayName": "Mistral Small 3.2", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } } ] }, { "id": "mistral/mistral-small-2603", "provider": "mistral", "model": "mistral-small-2603", "displayName": "Mistral Small 4", "family": "mistral-small", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "mistral", "openrouter", "venice" ], "aliases": [ "kilo/mistralai/mistral-small-2603", "mistral/mistral-small-2603", "openrouter/mistralai/mistral-small-2603", "venice/mistral-small-2603" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-small-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-small-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-small-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "venice", "model": "mistral-small-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1875, "output": 0.75 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-small-2603", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Mistral Small 4", "Mistral: Mistral Small 4" ], "families": [ "mistral-small" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-03-16", "lastUpdated": "2026-04-11", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-small-2603", "modelKey": "mistralai/mistral-small-2603", "displayName": "Mistral: Mistral Small 4", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-small-2603", "modelKey": "mistral-small-2603", "displayName": "Mistral Small 4", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-small-2603", "modelKey": "mistralai/mistral-small-2603", "displayName": "Mistral Small 4", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "mistral-small-2603", "modelKey": "mistral-small-2603", "displayName": "Mistral Small 4", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-small-2603", "displayName": "Mistral: Mistral Small 4", "metadata": { "canonicalSlug": "mistralai/mistral-small-2603", "createdAt": "2026-03-16T21:14:45.000Z", "huggingFaceId": "mistralai/Mistral-Small-4-119B-2603", "links": { "details": "/api/v1/models/mistralai/mistral-small-2603/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "high", "none" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mistral-small-3-1-24b-instruct-2503", "provider": "mistral", "model": "mistral-small-3-1-24b-instruct-2503", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", "mode": "chat" } ] }, { "id": "mistral/mistral-small-3-2-24b-instruct", "provider": "mistral", "model": "mistral-small-3-2-24b-instruct", "displayName": "Mistral Small 3.2 24B Instruct", "family": "mistral-small", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/mistral-small-3-2-24b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "mistral-small-3-2-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09375, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.2 24B Instruct" ], "families": [ "mistral-small" ], "releaseDate": "2026-01-15", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "mistral-small-3-2-24b-instruct", "modelKey": "mistral-small-3-2-24b-instruct", "displayName": "Mistral Small 3.2 24B Instruct", "family": "mistral-small", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-01-15" } } ] }, { "id": "mistral/mistral-small-3-2-2506", "provider": "mistral", "model": "mistral-small-3-2-2506", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-small-3-2-2506" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-small-3-2-2506", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.18 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-small-3-2-2506", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/mistral-small-3.1-24b-instruct", "provider": "mistral", "model": "mistral-small-3.1-24b-instruct", "displayName": "Mistral Small 3.1 24B", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "kilo", "openrouter" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "kilo/mistralai/mistral-small-3.1-24b-instruct", "openrouter/mistralai/mistral-small-3.1-24b-instruct" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.56 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.351, "output": 0.555 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.35, "output": 0.56 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.351, "output": 0.555 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-small-3.1-24b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.351, "output": 0.555 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.1 24B", "Mistral Small 3.1 24B Instruct", "Mistral: Mistral Small 3.1 24B" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-04-11", "lastUpdated": "2025-04-11", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "modelKey": "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "displayName": "Mistral Small 3.1 24B Instruct", "family": "mistral-small", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/mistralai/mistral-small-3.1-24b-instruct", "modelKey": "@cf/mistralai/mistral-small-3.1-24b-instruct", "displayName": "Mistral Small 3.1 24B Instruct", "family": "mistral-small", "metadata": { "lastUpdated": "2025-03-18", "openWeights": true, "releaseDate": "2025-03-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-small-3.1-24b-instruct", "modelKey": "mistralai/mistral-small-3.1-24b-instruct", "displayName": "Mistral: Mistral Small 3.1 24B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-small-3.1-24b-instruct", "modelKey": "mistralai/mistral-small-3.1-24b-instruct", "displayName": "Mistral Small 3.1 24B", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-03-17", "openWeights": true, "releaseDate": "2025-03-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mistral-small-3.1-24b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-small-3.1-24b-instruct", "displayName": "Mistral: Mistral Small 3.1 24B", "metadata": { "canonicalSlug": "mistralai/mistral-small-3.1-24b-instruct-2503", "createdAt": "2025-03-17T19:15:37.000Z", "huggingFaceId": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 128000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "mistral/mistral-small-3.2-24b-instruct", "provider": "mistral", "model": "mistral-small-3.2-24b-instruct", "displayName": "Mistral Small 3.2 24B", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/mistralai/mistral-small-3.2-24b-instruct", "openrouter/mistralai/mistral-small-3.2-24b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mistral-small-3.2-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.06, "output": 0.18 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mistral-small-3.2-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mistral-small-3.2-24b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mistral-small-3.2-24b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.2 24B", "Mistral: Mistral Small 3.2 24B" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-06-20", "lastUpdated": "2025-06-20", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mistral-small-3.2-24b-instruct", "modelKey": "mistralai/mistral-small-3.2-24b-instruct", "displayName": "Mistral: Mistral Small 3.2 24B", "metadata": { "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mistral-small-3.2-24b-instruct", "modelKey": "mistralai/mistral-small-3.2-24b-instruct", "displayName": "Mistral Small 3.2 24B", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mistral-small-3.2-24b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mistral-small-3.2-24b-instruct", "displayName": "Mistral: Mistral Small 3.2 24B", "metadata": { "canonicalSlug": "mistralai/mistral-small-3.2-24b-instruct-2506", "createdAt": "2025-06-20T18:10:16.000Z", "huggingFaceId": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "mistral/mistral-small-3.2-24b-instruct-2506", "provider": "mistral", "model": "mistral-small-3.2-24b-instruct-2506", "displayName": "Mistral-Small-3.2-24B-Instruct-2506", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "berget", "deepinfra", "meganova", "nano-gpt", "ovhcloud", "scaleway" ], "aliases": [ "berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "meganova/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "nano-gpt/chutesai/Mistral-Small-3.2-24B-Instruct-2506", "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "ovhcloud/mistral-small-3.2-24b-instruct-2506", "scaleway/mistral-small-3.2-24b-instruct-2506" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "berget", "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 0.33 } }, { "source": "models.dev", "provider": "meganova", "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "chutesai/Mistral-Small-3.2-24B-Instruct-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.4 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "mistral-small-3.2-24b-instruct-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.31 } }, { "source": "models.dev", "provider": "scaleway", "model": "mistral-small-3.2-24b-instruct-2506", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.35 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.2 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.2 24B Instruct", "Mistral Small 3.2 24B Instruct (2506)", "Mistral Small 3.2 24B Instruct 2506", "Mistral Small 3.2 24b Instruct", "Mistral-Small-3.2-24B-Instruct-2506" ], "families": [ "chutesai", "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-10-01", "lastUpdated": "2025-10-01", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "modelKey": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "displayName": "Mistral Small 3.2 24B Instruct 2506", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-10-01", "openWeights": true, "releaseDate": "2025-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "modelKey": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "displayName": "Mistral Small 3.2 24B Instruct", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-06-20", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "chutesai/Mistral-Small-3.2-24B-Instruct-2506", "modelKey": "chutesai/Mistral-Small-3.2-24B-Instruct-2506", "displayName": "Mistral Small 3.2 24b Instruct", "family": "chutesai", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "mistral-small-3.2-24b-instruct-2506", "modelKey": "mistral-small-3.2-24b-instruct-2506", "displayName": "Mistral-Small-3.2-24B-Instruct-2506", "metadata": { "lastUpdated": "2025-07-16", "openWeights": true, "releaseDate": "2025-07-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "mistral-small-3.2-24b-instruct-2506", "modelKey": "mistral-small-3.2-24b-instruct-2506", "displayName": "Mistral Small 3.2 24B Instruct (2506)", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2025-06-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506" } } ] }, { "id": "mistral/mistral-small-31-24b-instruct", "provider": "mistral", "model": "mistral-small-31-24b-instruct", "displayName": "Mistral Small 31 24b Instruct", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistral-small-31-24b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistral-small-31-24b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Mistral Small 31 24b Instruct" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistral-small-31-24b-instruct", "modelKey": "mistral-small-31-24b-instruct", "displayName": "Mistral Small 31 24b Instruct", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "mistral/mistral-small-4-119b", "provider": "mistral", "model": "mistral-small-4-119b", "displayName": "Mistral Small 4 119B", "family": "mistral-small", "sources": [ "models.dev" ], "providers": [ "regolo-ai" ], "aliases": [ "regolo-ai/mistral-small-4-119b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "regolo-ai", "model": "mistral-small-4-119b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 3 } } ] }, "metadata": { "displayNames": [ "Mistral Small 4 119B" ], "families": [ "mistral-small" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "mistral-small-4-119b", "modelKey": "mistral-small-4-119b", "displayName": "Mistral Small 4 119B", "family": "mistral-small", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } } ] }, { "id": "mistral/mistral-small-4-119b-2603", "provider": "mistral", "model": "mistral-small-4-119b-2603", "displayName": "Mistral Small 4 119B", "sources": [ "models.dev" ], "providers": [ "nano-gpt", "nvidia" ], "aliases": [ "nano-gpt/mistralai/mistral-small-4-119b-2603", "nvidia/mistralai/mistral-small-4-119b-2603" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-small-4-119b-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mistral-small-4-119b-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mistral Small 4 119B", "mistral-small-4-119b-2603" ], "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-small-4-119b-2603", "modelKey": "mistralai/mistral-small-4-119b-2603", "displayName": "Mistral Small 4 119B", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mistral-small-4-119b-2603", "modelKey": "mistralai/mistral-small-4-119b-2603", "displayName": "mistral-small-4-119b-2603", "metadata": { "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } } ] }, { "id": "mistral/mistral-small-4-119b-2603:thinking", "provider": "mistral", "model": "mistral-small-4-119b-2603:thinking", "displayName": "Mistral Small 4 119B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mistralai/mistral-small-4-119b-2603:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mistral-small-4-119b-2603:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "Mistral Small 4 119B Thinking" ], "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mistral-small-4-119b-2603:thinking", "modelKey": "mistralai/mistral-small-4-119b-2603:thinking", "displayName": "Mistral Small 4 119B Thinking", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } } ] }, { "id": "mistral/mistral-small-latest", "provider": "mistral", "model": "mistral-small-latest", "displayName": "Mistral Small (latest)", "family": "mistral-small", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "mistral" ], "aliases": [ "merge-gateway/mistral/mistral-small-latest", "mistral/mistral-small-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/mistral-small-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "mistral", "model": "mistral-small-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-small-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.18 } } ] }, "metadata": { "displayNames": [ "Mistral Small (latest)" ], "families": [ "mistral-small" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/mistral-small-latest", "modelKey": "mistral/mistral-small-latest", "displayName": "Mistral Small (latest)", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "mistral-small-latest", "modelKey": "mistral-small-latest", "displayName": "Mistral Small (latest)", "family": "mistral-small", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-small-latest", "mode": "chat", "metadata": { "source": "https://mistral.ai/pricing" } } ] }, { "id": "mistral/mistral-small3.2", "provider": "mistral", "model": "mistral-small3.2", "displayName": "Mistral Small 3.2", "family": "mistral-small", "sources": [ "models.dev" ], "providers": [ "regolo-ai" ], "aliases": [ "regolo-ai/mistral-small3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "outputTokens": 120000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "regolo-ai", "model": "mistral-small3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "Mistral Small 3.2" ], "families": [ "mistral-small" ], "releaseDate": "2025-01-31", "lastUpdated": "2025-01-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "mistral-small3.2", "modelKey": "mistral-small3.2", "displayName": "Mistral Small 3.2", "family": "mistral-small", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } } ] }, { "id": "mistral/mistral-tiny", "provider": "mistral", "model": "mistral-tiny", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/mistral-tiny" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/mistral-tiny", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/mistral-tiny", "mode": "chat" } ] }, { "id": "mistral/mistral.devstral-2-123b", "provider": "mistral", "model": "mistral.devstral-2-123b", "displayName": "Devstral 2 123B", "family": "devstral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.devstral-2-123b", "bedrock_converse/mistral.devstral-2-123b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.devstral-2-123b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.devstral-2-123b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "Devstral 2 123B" ], "families": [ "devstral" ], "modes": [ "chat" ], "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.devstral-2-123b", "modelKey": "mistral.devstral-2-123b", "displayName": "Devstral 2 123B", "family": "devstral", "metadata": { "lastUpdated": "2026-02-17", "openWeights": true, "releaseDate": "2026-02-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.devstral-2-123b", "mode": "chat", "metadata": { "source": "https://aws.amazon.com/bedrock/pricing/" } } ] }, { "id": "mistral/mistral.magistral-small-2509", "provider": "mistral", "model": "mistral.magistral-small-2509", "displayName": "Magistral Small 1.2", "family": "magistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.magistral-small-2509", "bedrock_converse/mistral.magistral-small-2509" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 40000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.magistral-small-2509", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.magistral-small-2509", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Magistral Small 1.2" ], "families": [ "magistral" ], "modes": [ "chat" ], "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.magistral-small-2509", "modelKey": "mistral.magistral-small-2509", "displayName": "Magistral Small 1.2", "family": "magistral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.magistral-small-2509", "mode": "chat" } ] }, { "id": "mistral/mistral.ministral-3-14b-instruct", "provider": "mistral", "model": "mistral.ministral-3-14b-instruct", "displayName": "Ministral 14B 3.0", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.ministral-3-14b-instruct", "bedrock_converse/mistral.ministral-3-14b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.ministral-3-14b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.ministral-3-14b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Ministral 14B 3.0" ], "families": [ "ministral" ], "modes": [ "chat" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.ministral-3-14b-instruct", "modelKey": "mistral.ministral-3-14b-instruct", "displayName": "Ministral 14B 3.0", "family": "ministral", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.ministral-3-14b-instruct", "mode": "chat" } ] }, { "id": "mistral/mistral.ministral-3-3b-instruct", "provider": "mistral", "model": "mistral.ministral-3-3b-instruct", "displayName": "Ministral 3 3B", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.ministral-3-3b-instruct", "bedrock_converse/mistral.ministral-3-3b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.ministral-3-3b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.ministral-3-3b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Ministral 3 3B" ], "families": [ "ministral" ], "modes": [ "chat" ], "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.ministral-3-3b-instruct", "modelKey": "mistral.ministral-3-3b-instruct", "displayName": "Ministral 3 3B", "family": "ministral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.ministral-3-3b-instruct", "mode": "chat" } ] }, { "id": "mistral/mistral.ministral-3-8b-instruct", "provider": "mistral", "model": "mistral.ministral-3-8b-instruct", "displayName": "Ministral 3 8B", "family": "ministral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.ministral-3-8b-instruct", "bedrock_converse/mistral.ministral-3-8b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.ministral-3-8b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.ministral-3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Ministral 3 8B" ], "families": [ "ministral" ], "modes": [ "chat" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.ministral-3-8b-instruct", "modelKey": "mistral.ministral-3-8b-instruct", "displayName": "Ministral 3 8B", "family": "ministral", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.ministral-3-8b-instruct", "mode": "chat" } ] }, { "id": "mistral/mistral.mistral-7b-instruct-v0:2", "provider": "mistral", "model": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/mistral.mistral-7b-instruct-v0:2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "mistral.mistral-7b-instruct-v0:2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "mistral.mistral-7b-instruct-v0:2", "mode": "chat" } ] }, { "id": "mistral/mistral.mistral-large-2402-v1:0", "provider": "mistral", "model": "mistral.mistral-large-2402-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/mistral.mistral-large-2402-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "mistral.mistral-large-2402-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8, "output": 24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "mistral.mistral-large-2402-v1:0", "mode": "chat" } ] }, { "id": "mistral/mistral.mistral-large-2407-v1:0", "provider": "mistral", "model": "mistral.mistral-large-2407-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/mistral.mistral-large-2407-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "mistral.mistral-large-2407-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "mistral.mistral-large-2407-v1:0", "mode": "chat" } ] }, { "id": "mistral/mistral.mistral-large-3-675b-instruct", "provider": "mistral", "model": "mistral.mistral-large-3-675b-instruct", "displayName": "Mistral Large 3", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.mistral-large-3-675b-instruct", "bedrock_converse/mistral.mistral-large-3-675b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.mistral-large-3-675b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.mistral-large-3-675b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Mistral Large 3" ], "families": [ "mistral" ], "modes": [ "chat" ], "releaseDate": "2025-12-02", "lastUpdated": "2025-12-02", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.mistral-large-3-675b-instruct", "modelKey": "mistral.mistral-large-3-675b-instruct", "displayName": "Mistral Large 3", "family": "mistral", "metadata": { "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-12-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.mistral-large-3-675b-instruct", "mode": "chat" } ] }, { "id": "mistral/mistral.mistral-small-2402-v1:0", "provider": "mistral", "model": "mistral.mistral-small-2402-v1:0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/mistral.mistral-small-2402-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "mistral.mistral-small-2402-v1:0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "mistral.mistral-small-2402-v1:0", "mode": "chat" } ] }, { "id": "mistral/mistral.mixtral-8x7b-instruct-v0:1", "provider": "mistral", "model": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "bedrock" ], "aliases": [ "bedrock/mistral.mixtral-8x7b-instruct-v0:1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "bedrock", "model": "mistral.mixtral-8x7b-instruct-v0:1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 0.7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock", "model": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat" } ] }, { "id": "mistral/mistral.pixtral-large-2502-v1:0", "provider": "mistral", "model": "mistral.pixtral-large-2502-v1:0", "displayName": "Pixtral Large (25.02)", "family": "mistral", "sources": [ "models.dev" ], "providers": [ "amazon-bedrock" ], "aliases": [ "amazon-bedrock/mistral.pixtral-large-2502-v1:0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.pixtral-large-2502-v1:0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Pixtral Large (25.02)" ], "families": [ "mistral" ], "releaseDate": "2025-04-08", "lastUpdated": "2025-04-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.pixtral-large-2502-v1:0", "modelKey": "mistral.pixtral-large-2502-v1:0", "displayName": "Pixtral Large (25.02)", "family": "mistral", "metadata": { "lastUpdated": "2025-04-08", "openWeights": false, "releaseDate": "2025-04-08" } } ] }, { "id": "mistral/mistral.voxtral-mini-3b-2507", "provider": "mistral", "model": "mistral.voxtral-mini-3b-2507", "displayName": "Voxtral Mini 3B 2507", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.voxtral-mini-3b-2507", "bedrock_converse/mistral.voxtral-mini-3b-2507" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.voxtral-mini-3b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.04 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.voxtral-mini-3b-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.04 } } ] }, "metadata": { "displayNames": [ "Voxtral Mini 3B 2507" ], "families": [ "mistral" ], "modes": [ "chat" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.voxtral-mini-3b-2507", "modelKey": "mistral.voxtral-mini-3b-2507", "displayName": "Voxtral Mini 3B 2507", "family": "mistral", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.voxtral-mini-3b-2507", "mode": "chat" } ] }, { "id": "mistral/mistral.voxtral-small-24b-2507", "provider": "mistral", "model": "mistral.voxtral-small-24b-2507", "displayName": "Voxtral Small 24B 2507", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "amazon-bedrock", "bedrock_converse" ], "aliases": [ "amazon-bedrock/mistral.voxtral-small-24b-2507", "bedrock_converse/mistral.voxtral-small-24b-2507" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "nativeStructuredOutput": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "amazon-bedrock", "model": "mistral.voxtral-small-24b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.35 } }, { "source": "litellm", "provider": "bedrock_converse", "model": "mistral.voxtral-small-24b-2507", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Voxtral Small 24B 2507" ], "families": [ "mistral" ], "modes": [ "chat" ], "releaseDate": "2025-07-01", "lastUpdated": "2025-07-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "amazon-bedrock", "providerName": "Amazon Bedrock", "providerDoc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "model": "mistral.voxtral-small-24b-2507", "modelKey": "mistral.voxtral-small-24b-2507", "displayName": "Voxtral Small 24B 2507", "family": "mistral", "metadata": { "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "bedrock_converse", "model": "mistral.voxtral-small-24b-2507", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x22b", "provider": "mistral", "model": "mixtral-8x22b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x22b-instruct", "provider": "mistral", "model": "mixtral-8x22b-instruct", "displayName": "Mixtral 8x22B Instruct", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fireworks_ai", "kilo", "nvidia", "openrouter", "vercel_ai_gateway" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct", "kilo/mistralai/mixtral-8x22b-instruct", "nvidia/mistralai/mixtral-8x22b-instruct", "openrouter/mistralai/mixtral-8x22b-instruct", "vercel_ai_gateway/mistral/mixtral-8x22b-instruct" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false, "functionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/mixtral-8x22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mixtral-8x22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/mixtral-8x22b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mistralai/mixtral-8x22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.65 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mixtral-8x22b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/mixtral-8x22b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral: Mixtral 8x22B Instruct", "Mixtral 8x22B Instruct" ], "families": [ "mistral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-01-31", "releaseDate": "2024-04-17", "lastUpdated": "2024-04-17", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/mixtral-8x22b-instruct", "modelKey": "mistralai/mixtral-8x22b-instruct", "displayName": "Mistral: Mixtral 8x22B Instruct", "metadata": { "lastUpdated": "2024-04-17", "openWeights": true, "releaseDate": "2024-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mixtral-8x22b-instruct", "modelKey": "mistralai/mixtral-8x22b-instruct", "displayName": "Mistral: Mixtral 8x22B Instruct", "metadata": { "lastUpdated": "2024-04-17", "openWeights": true, "releaseDate": "2024-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/mixtral-8x22b-instruct", "modelKey": "mistralai/mixtral-8x22b-instruct", "displayName": "Mixtral 8x22B Instruct", "family": "mistral", "metadata": { "knowledgeCutoff": "2024-01-31", "lastUpdated": "2024-04-17", "openWeights": true, "releaseDate": "2024-04-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mistralai/mixtral-8x22b-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/mixtral-8x22b-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/mixtral-8x22b-instruct", "displayName": "Mistral: Mixtral 8x22B Instruct", "metadata": { "canonicalSlug": "mistralai/mixtral-8x22b-instruct", "createdAt": "2024-04-17T00:00:00.000Z", "huggingFaceId": "mistralai/Mixtral-8x22B-Instruct-v0.1", "instructType": "mistral", "knowledgeCutoff": "2024-01-31", "links": { "details": "/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 65536, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "mistral/mixtral-8x22b-instruct-hf", "provider": "mistral", "model": "mixtral-8x22b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "mistral/mixtral-8x22b-instruct-v0.1", "provider": "mistral", "model": "mixtral-8x22b-instruct-v0.1", "displayName": "Mixtral 8x22B", "family": "mixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anyscale", "nano-gpt", "nscale", "ollama" ], "aliases": [ "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1", "nano-gpt/mistralai/mixtral-8x22b-instruct-v0.1", "nscale/mistralai/mixtral-8x22b-instruct-v0.1", "ollama/mixtral-8x22B-Instruct-v0.1" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mixtral-8x22b-instruct-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8999999999999999, "output": 0.8999999999999999 } }, { "source": "litellm", "provider": "anyscale", "model": "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } }, { "source": "litellm", "provider": "nscale", "model": "nscale/mistralai/mixtral-8x22b-instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/mixtral-8x22B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Mixtral 8x22B" ], "families": [ "mixtral" ], "modes": [ "chat" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mixtral-8x22b-instruct-v0.1", "modelKey": "mistralai/mixtral-8x22b-instruct-v0.1", "displayName": "Mixtral 8x22B", "family": "mixtral", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/mistralai/mixtral-8x22b-instruct-v0.1", "mode": "chat", "metadata": { "metadata": { "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." }, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mixtral-8x22B-Instruct-v0.1", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x7b", "provider": "mistral", "model": "mixtral-8x7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai", "snowflake" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x7b", "snowflake/mixtral-8x7b" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } }, { "source": "litellm", "provider": "snowflake", "model": "snowflake/mixtral-8x7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/mixtral-8x7b", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x7b-instruct", "provider": "mistral", "model": "mixtral-8x7b-instruct", "displayName": "Mistral: Mixtral 8x7B Instruct", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks_ai", "nvidia" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct", "nvidia/mistralai/mixtral-8x7b-instruct" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "mistralai/mixtral-8x7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Mistral: Mixtral 8x7B Instruct" ], "modes": [ "chat" ], "releaseDate": "2023-12-10", "lastUpdated": "2026-03-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "mistralai/mixtral-8x7b-instruct", "modelKey": "mistralai/mixtral-8x7b-instruct", "displayName": "Mistral: Mixtral 8x7B Instruct", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2023-12-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x7b-instruct-hf", "provider": "mistral", "model": "mixtral-8x7b-instruct-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf", "mode": "chat" } ] }, { "id": "mistral/mixtral-8x7b-instruct-v0.1", "provider": "mistral", "model": "mixtral-8x7b-instruct-v0.1", "displayName": "Mixtral 8x7B Instruct v0.1", "family": "mixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "anyscale", "cortecs", "deepinfra", "nano-gpt", "ollama", "ovhcloud", "replicate", "together_ai" ], "aliases": [ "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1", "cortecs/mixtral-8x7B-instruct-v0.1", "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1", "nano-gpt/mistralai/mixtral-8x7b-instruct-v0.1", "ollama/mixtral-8x7B-Instruct-v0.1", "ovhcloud/Mixtral-8x7B-Instruct-v0.1", "replicate/mistralai/mixtral-8x7b-instruct-v0.1", "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "toolChoice": true, "responseSchema": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "mixtral-8x7B-instruct-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.438, "output": 0.68 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "mistralai/mixtral-8x7b-instruct-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.27, "output": 0.27 } }, { "source": "litellm", "provider": "anyscale", "model": "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "litellm", "provider": "ollama", "model": "ollama/mixtral-8x7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/Mixtral-8x7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.63, "output": 0.63 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/mistralai/mixtral-8x7b-instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Mixtral 8x7B", "Mixtral 8x7B Instruct v0.1" ], "families": [ "mixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2023-12-11", "lastUpdated": "2023-12-11", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "mixtral-8x7B-instruct-v0.1", "modelKey": "mixtral-8x7B-instruct-v0.1", "displayName": "Mixtral 8x7B Instruct v0.1", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2023-12-11", "openWeights": true, "releaseDate": "2023-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mistralai/mixtral-8x7b-instruct-v0.1", "modelKey": "mistralai/mixtral-8x7b-instruct-v0.1", "displayName": "Mixtral 8x7B", "family": "mixtral", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "anyscale", "model": "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "metadata": { "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/mixtral-8x7B-Instruct-v0.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/mistralai/mixtral-8x7b-instruct-v0.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1", "mode": "chat" } ] }, { "id": "mistral/open-codestral-mamba", "provider": "mistral", "model": "open-codestral-mamba", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-codestral-mamba" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/open-codestral-mamba", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-codestral-mamba", "mode": "chat", "metadata": { "source": "https://mistral.ai/technology/" } } ] }, { "id": "mistral/open-mistral-7b", "provider": "mistral", "model": "open-mistral-7b", "displayName": "Mistral 7B", "family": "mistral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-mistral-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "open-mistral-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.25 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/open-mistral-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "Mistral 7B" ], "families": [ "mistral" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2023-09-27", "lastUpdated": "2023-09-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "open-mistral-7b", "modelKey": "open-mistral-7b", "displayName": "Mistral 7B", "family": "mistral", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2023-09-27", "openWeights": true, "releaseDate": "2023-09-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-mistral-7b", "mode": "chat" } ] }, { "id": "mistral/open-mistral-nemo", "provider": "mistral", "model": "open-mistral-nemo", "displayName": "Open Mistral Nemo", "family": "mistral-nemo", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-mistral-nemo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "open-mistral-nemo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/open-mistral-nemo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Open Mistral Nemo" ], "families": [ "mistral-nemo" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "open-mistral-nemo", "modelKey": "open-mistral-nemo", "displayName": "Open Mistral Nemo", "family": "mistral-nemo", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-01", "openWeights": true, "releaseDate": "2024-07-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-mistral-nemo", "mode": "chat", "metadata": { "source": "https://mistral.ai/technology/" } } ] }, { "id": "mistral/open-mistral-nemo-2407", "provider": "mistral", "model": "open-mistral-nemo-2407", "mode": "chat", "sources": [ "litellm" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-mistral-nemo-2407" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "mistral", "model": "mistral/open-mistral-nemo-2407", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-mistral-nemo-2407", "mode": "chat", "metadata": { "source": "https://mistral.ai/technology/" } } ] }, { "id": "mistral/open-mixtral-8x22b", "provider": "mistral", "model": "open-mixtral-8x22b", "displayName": "Mixtral 8x22B", "family": "mixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-mixtral-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65336, "inputTokens": 65336, "maxTokens": 8191, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "open-mixtral-8x22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/open-mixtral-8x22b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mixtral 8x22B" ], "families": [ "mixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-04-17", "lastUpdated": "2024-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "open-mixtral-8x22b", "modelKey": "open-mixtral-8x22b", "displayName": "Mixtral 8x22B", "family": "mixtral", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-04-17", "openWeights": true, "releaseDate": "2024-04-17" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-mixtral-8x22b", "mode": "chat" } ] }, { "id": "mistral/open-mixtral-8x7b", "provider": "mistral", "model": "open-mixtral-8x7b", "displayName": "Mixtral 8x7B", "family": "mixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral" ], "aliases": [ "mistral/open-mixtral-8x7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8191, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "open-mixtral-8x7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/open-mixtral-8x7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Mixtral 8x7B" ], "families": [ "mixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-01", "releaseDate": "2023-12-11", "lastUpdated": "2023-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "open-mixtral-8x7b", "modelKey": "open-mixtral-8x7b", "displayName": "Mixtral 8x7B", "family": "mixtral", "metadata": { "knowledgeCutoff": "2024-01", "lastUpdated": "2023-12-11", "openWeights": true, "releaseDate": "2023-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/open-mixtral-8x7b", "mode": "chat" } ] }, { "id": "mistral/pixtral-12b", "provider": "mistral", "model": "pixtral-12b", "displayName": "Pixtral 12B", "family": "pixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "vercel", "vercel_ai_gateway" ], "aliases": [ "mistral/pixtral-12b", "vercel/mistral/pixtral-12b", "vercel_ai_gateway/mistral/pixtral-12b" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "mistral", "model": "pixtral-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "models.dev", "provider": "vercel", "model": "mistral/pixtral-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/pixtral-12b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Pixtral 12B" ], "families": [ "pixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-01", "lastUpdated": "2024-09-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "pixtral-12b", "modelKey": "pixtral-12b", "displayName": "Pixtral 12B", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-01", "openWeights": true, "releaseDate": "2024-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/pixtral-12b", "modelKey": "mistral/pixtral-12b", "displayName": "Pixtral 12B", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-01", "openWeights": true, "releaseDate": "2024-09-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/pixtral-12b", "mode": "chat" } ] }, { "id": "mistral/pixtral-12b-2409", "provider": "mistral", "model": "pixtral-12b-2409", "displayName": "Pixtral 12B 2409", "family": "pixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "mistral", "scaleway", "watsonx" ], "aliases": [ "mistral/pixtral-12b-2409", "scaleway/pixtral-12b-2409", "watsonx/mistralai/pixtral-12b-2409" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true, "parallelFunctionCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "scaleway", "model": "pixtral-12b-2409", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/pixtral-12b-2409", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/mistralai/pixtral-12b-2409", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "Pixtral 12B 2409" ], "families": [ "pixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-25", "lastUpdated": "2026-03-17", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "pixtral-12b-2409", "modelKey": "pixtral-12b-2409", "displayName": "Pixtral 12B 2409", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2024-09-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/pixtral-12b-2409", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/mistralai/pixtral-12b-2409", "mode": "chat" } ] }, { "id": "mistral/pixtral-large", "provider": "mistral", "model": "pixtral-large", "displayName": "Pixtral Large (latest)", "family": "pixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vercel_ai_gateway" ], "aliases": [ "vercel/mistral/pixtral-large", "vercel_ai_gateway/mistral/pixtral-large" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "mistral/pixtral-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/pixtral-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Pixtral Large (latest)" ], "families": [ "pixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "lastUpdated": "2024-11-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "mistral/pixtral-large", "modelKey": "mistral/pixtral-large", "displayName": "Pixtral Large (latest)", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-04", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/mistral/pixtral-large", "mode": "chat" } ] }, { "id": "mistral/pixtral-large-2411", "provider": "mistral", "model": "pixtral-large-2411", "displayName": "Mistral: Pixtral Large 2411", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "kilo", "mistral" ], "aliases": [ "kilo/mistralai/pixtral-large-2411", "mistral/pixtral-large-2411" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": true, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "mistralai/pixtral-large-2411", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/pixtral-large-2411", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Mistral: Pixtral Large 2411" ], "modes": [ "chat" ], "releaseDate": "2024-11-19", "lastUpdated": "2026-03-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/pixtral-large-2411", "modelKey": "mistralai/pixtral-large-2411", "displayName": "Mistral: Pixtral Large 2411", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2024-11-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/pixtral-large-2411", "mode": "chat" } ] }, { "id": "mistral/pixtral-large-latest", "provider": "mistral", "model": "pixtral-large-latest", "displayName": "Pixtral Large (latest)", "family": "pixtral", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "merge-gateway", "mistral" ], "aliases": [ "llmgateway/pixtral-large-latest", "merge-gateway/mistral/pixtral-large-latest", "mistral/pixtral-large-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "assistantPrefill": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "pixtral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "mistral/pixtral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "mistral", "model": "pixtral-large-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "mistral", "model": "mistral/pixtral-large-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Pixtral Large (latest)" ], "families": [ "pixtral" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-11", "releaseDate": "2024-11-01", "lastUpdated": "2024-11-04", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "pixtral-large-latest", "modelKey": "pixtral-large-latest", "displayName": "Pixtral Large (latest)", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-04", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "mistral/pixtral-large-latest", "modelKey": "mistral/pixtral-large-latest", "displayName": "Pixtral Large (latest)", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-04", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "mistral", "providerName": "Mistral", "providerDoc": "https://docs.mistral.ai/getting-started/models/", "model": "pixtral-large-latest", "modelKey": "pixtral-large-latest", "displayName": "Pixtral Large (latest)", "family": "pixtral", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2024-11-04", "openWeights": true, "releaseDate": "2024-11-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "mistral", "model": "mistral/pixtral-large-latest", "mode": "chat" } ] }, { "id": "mistral/voxtral-small-24b-2507", "provider": "mistral", "model": "voxtral-small-24b-2507", "displayName": "Voxtral Small 24B", "family": "voxtral", "sources": [ "models.dev", "openrouter" ], "providers": [ "evroc", "kilo", "openrouter", "scaleway" ], "aliases": [ "evroc/mistralai/Voxtral-Small-24B-2507", "kilo/mistralai/voxtral-small-24b-2507", "openrouter/mistralai/voxtral-small-24b-2507", "scaleway/voxtral-small-24b-2507" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "temperature": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "mistralai/Voxtral-Small-24B-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.00236, "output": 0.00236, "outputAudio": 2.36 } }, { "source": "models.dev", "provider": "kilo", "model": "mistralai/voxtral-small-24b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "openrouter", "model": "mistralai/voxtral-small-24b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "scaleway", "model": "voxtral-small-24b-2507", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.35 } }, { "source": "openrouter", "provider": "openrouter", "model": "mistralai/voxtral-small-24b-2507", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 }, "other": { "audio": 0.0001 } } ] }, "metadata": { "displayNames": [ "Mistral: Voxtral Small 24B 2507", "Voxtral Small 24B", "Voxtral Small 24B 2507" ], "families": [ "mistral", "voxtral" ], "releaseDate": "2025-03-01", "lastUpdated": "2025-03-01", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "mistralai/Voxtral-Small-24B-2507", "modelKey": "mistralai/Voxtral-Small-24B-2507", "displayName": "Voxtral Small 24B", "family": "voxtral", "metadata": { "lastUpdated": "2025-03-01", "openWeights": true, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "mistralai/voxtral-small-24b-2507", "modelKey": "mistralai/voxtral-small-24b-2507", "displayName": "Mistral: Voxtral Small 24B 2507", "metadata": { "lastUpdated": "2025-07-01", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mistralai/voxtral-small-24b-2507", "modelKey": "mistralai/voxtral-small-24b-2507", "displayName": "Voxtral Small 24B 2507", "family": "mistral", "metadata": { "lastUpdated": "2025-10-30", "openWeights": true, "releaseDate": "2025-10-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "voxtral-small-24b-2507", "modelKey": "voxtral-small-24b-2507", "displayName": "Voxtral Small 24B 2507", "family": "voxtral", "metadata": { "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2025-07-01" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mistralai/voxtral-small-24b-2507", "displayName": "Mistral: Voxtral Small 24B 2507", "metadata": { "canonicalSlug": "mistralai/voxtral-small-24b-2507", "createdAt": "2025-10-30T14:39:04.000Z", "huggingFaceId": "mistralai/Voxtral-Small-24B-2507", "links": { "details": "/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 32000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2", "provider": "moonshotai", "model": "kimi-k2", "displayName": "Kimi K2", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fastrouter", "iflowcn", "kilo", "llmgateway", "opencode", "openrouter", "qiniu-ai", "vercel", "vercel_ai_gateway" ], "aliases": [ "fastrouter/moonshotai/kimi-k2", "iflowcn/kimi-k2", "kilo/moonshotai/kimi-k2", "llmgateway/kimi-k2", "opencode/kimi-k2", "openrouter/moonshotai/kimi-k2", "qiniu-ai/kimi-k2", "vercel/moonshotai/kimi-k2", "vercel_ai_gateway/moonshotai/kimi-k2" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "moonshotai/kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "models.dev", "provider": "iflowcn", "model": "kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "moonshotai/kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "opencode", "model": "kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 0.4, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.3 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.3 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/moonshotai/kimi-k2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.57, "output": 2.3 } } ] }, "metadata": { "displayNames": [ "Kimi K2", "Kimi K2 0711", "Kimi K2 Instruct", "Kimi-K2", "MoonshotAI: Kimi K2 0711" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-07-11", "lastUpdated": "2025-07-11", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "moonshotai/kimi-k2", "modelKey": "moonshotai/kimi-k2", "displayName": "Kimi K2", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-11", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "kimi-k2", "modelKey": "kimi-k2", "displayName": "Kimi-K2", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "moonshotai/kimi-k2", "modelKey": "moonshotai/kimi-k2", "displayName": "MoonshotAI: Kimi K2 0711", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2", "modelKey": "kimi-k2", "displayName": "Kimi K2", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-07-11", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2", "modelKey": "kimi-k2", "displayName": "Kimi K2", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2", "modelKey": "moonshotai/kimi-k2", "displayName": "Kimi K2 0711", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-12-31", "lastUpdated": "2025-07-11", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "kimi-k2", "modelKey": "kimi-k2", "displayName": "Kimi K2", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2", "modelKey": "moonshotai/kimi-k2", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/moonshotai/kimi-k2", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2", "displayName": "MoonshotAI: Kimi K2 0711", "metadata": { "canonicalSlug": "moonshotai/kimi-k2", "createdAt": "2025-07-11T19:47:32.000Z", "huggingFaceId": "moonshotai/Kimi-K2-Instruct", "knowledgeCutoff": "2024-12-31", "links": { "details": "/api/v1/models/moonshotai/kimi-k2/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2-0711", "provider": "moonshotai", "model": "kimi-k2-0711", "displayName": "Kimi K2 (07/11)", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "helicone" ], "aliases": [ "helicone/kimi-k2-0711" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "kimi-k2-0711", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5700000000000001, "output": 2.3 } } ] }, "metadata": { "displayNames": [ "Kimi K2 (07/11)" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "kimi-k2-0711", "modelKey": "kimi-k2-0711", "displayName": "Kimi K2 (07/11)", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "moonshotai/kimi-k2-0711-preview", "provider": "moonshotai", "model": "kimi-k2-0711-preview", "displayName": "Kimi K2 0711", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "moonshot", "moonshotai", "moonshotai-cn" ], "aliases": [ "moonshot/kimi-k2-0711-preview", "moonshotai-cn/kimi-k2-0711-preview", "moonshotai/kimi-k2-0711-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2-0711-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2-0711-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2-0711-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0711" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-07-14", "lastUpdated": "2025-07-14", "deprecationDate": "2026-05-25", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2-0711-preview", "modelKey": "kimi-k2-0711-preview", "displayName": "Kimi K2 0711", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-14", "openWeights": true, "releaseDate": "2025-07-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2-0711-preview", "modelKey": "kimi-k2-0711-preview", "displayName": "Kimi K2 0711", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-14", "openWeights": true, "releaseDate": "2025-07-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2-0711-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-05-25", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } } ] }, { "id": "moonshotai/kimi-k2-0905", "provider": "moonshotai", "model": "kimi-k2-0905", "displayName": "Kimi K2 (09/05)", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "helicone", "iflowcn", "jiekou", "kilo", "novita", "novita-ai", "openrouter", "qiniu-ai", "zenmux" ], "aliases": [ "helicone/kimi-k2-0905", "iflowcn/kimi-k2-0905", "jiekou/moonshotai/kimi-k2-0905", "kilo/moonshotai/kimi-k2-0905", "novita-ai/moonshotai/kimi-k2-0905", "novita/moonshotai/kimi-k2-0905", "openrouter/moonshotai/kimi-k2-0905", "qiniu-ai/moonshotai/kimi-k2-0905", "zenmux/moonshotai/kimi-k2-0905" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.39999999999999997, "input": 0.5, "output": 2 } }, { "source": "models.dev", "provider": "iflowcn", "model": "kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "jiekou", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "kilo", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "novita", "model": "novita/moonshotai/kimi-k2-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2-0905", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 (09/05)", "Kimi K2 0905", "Kimi-K2-0905", "MoonshotAI: Kimi K2 0905" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09", "releaseDate": "2025-09-05", "lastUpdated": "2025-09-05", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "kimi-k2-0905", "modelKey": "kimi-k2-0905", "displayName": "Kimi K2 (09/05)", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "kimi-k2-0905", "modelKey": "kimi-k2-0905", "displayName": "Kimi-K2-0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "MoonshotAI: Kimi K2 0905", "metadata": { "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-12-31", "lastUpdated": "2025-09-04", "openWeights": true, "releaseDate": "2025-09-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "Kimi K2 0905", "metadata": { "lastUpdated": "2025-09-08", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2-0905", "modelKey": "moonshotai/kimi-k2-0905", "displayName": "Kimi K2 0905", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-04", "openWeights": false, "releaseDate": "2025-09-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/moonshotai/kimi-k2-0905", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2-0905", "displayName": "MoonshotAI: Kimi K2 0905", "metadata": { "canonicalSlug": "moonshotai/kimi-k2-0905", "createdAt": "2025-09-04T21:25:47.000Z", "huggingFaceId": "moonshotai/Kimi-K2-Instruct-0905", "knowledgeCutoff": "2024-12-31", "links": { "details": "/api/v1/models/moonshotai/kimi-k2-0905/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2-0905-preview", "provider": "moonshotai", "model": "kimi-k2-0905-preview", "displayName": "Kimi K2 0905", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "moonshot", "moonshotai", "moonshotai-cn" ], "aliases": [ "302ai/kimi-k2-0905-preview", "moonshot/kimi-k2-0905-preview", "moonshotai-cn/kimi-k2-0905-preview", "moonshotai/kimi-k2-0905-preview" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "kimi-k2-0905-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.632, "output": 2.53 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2-0905-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2-0905-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2-0905-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0905", "kimi-k2-0905-preview" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-09-05", "lastUpdated": "2025-09-05", "deprecationDate": "2026-05-25", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "kimi-k2-0905-preview", "modelKey": "kimi-k2-0905-preview", "displayName": "kimi-k2-0905-preview", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2-0905-preview", "modelKey": "kimi-k2-0905-preview", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2-0905-preview", "modelKey": "kimi-k2-0905-preview", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2-0905-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-05-25", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } } ] }, { "id": "moonshotai/kimi-k2-5", "provider": "moonshotai", "model": "kimi-k2-5", "displayName": "Kimi K2.5", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/kimi-k2-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "kimi-k2-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 0.56, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2024-04", "releaseDate": "2026-01-27", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "kimi-k2-5", "modelKey": "kimi-k2-5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "moonshotai/kimi-k2-6", "provider": "moonshotai", "model": "kimi-k2-6", "displayName": "Kimi K2.6", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "clarifai", "frogbot", "venice" ], "aliases": [ "clarifai/moonshotai/chat-completion/models/Kimi-K2_6", "frogbot/kimi-k2-6", "venice/kimi-k2-6" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "moonshotai/chat-completion/models/Kimi-K2_6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "frogbot", "model": "kimi-k2-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "venice", "model": "kimi-k2-6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 0.85, "output": 4.655 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6", "Kimi-K2.6" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "moonshotai/chat-completion/models/Kimi-K2_6", "modelKey": "moonshotai/chat-completion/models/Kimi-K2_6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "kimi-k2-6", "modelKey": "kimi-k2-6", "displayName": "Kimi-K2.6", "metadata": { "lastUpdated": "1970-01-01", "openWeights": false, "releaseDate": "1970-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "kimi-k2-6", "modelKey": "kimi-k2-6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "moonshotai/kimi-k2-7-code", "provider": "moonshotai", "model": "kimi-k2-7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/kimi-k2-7-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "kimi-k2-7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.9, "output": 4.3 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-13", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "kimi-k2-7-code", "modelKey": "kimi-k2-7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "moonshotai/kimi-k2-instruct", "provider": "moonshotai", "model": "kimi-k2-instruct", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "cortecs", "deepinfra", "fireworks_ai", "huggingface", "hyperbolic", "jiekou", "nano-gpt", "novita", "novita-ai", "siliconflow", "together_ai", "wandb" ], "aliases": [ "cortecs/kimi-k2-instruct", "deepinfra/moonshotai/Kimi-K2-Instruct", "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "huggingface/moonshotai/Kimi-K2-Instruct", "hyperbolic/moonshotai/Kimi-K2-Instruct", "jiekou/moonshotai/kimi-k2-instruct", "nano-gpt/moonshotai/kimi-k2-instruct", "novita-ai/moonshotai/kimi-k2-instruct", "novita/moonshotai/kimi-k2-instruct", "siliconflow/moonshotai/Kimi-K2-Instruct", "together_ai/moonshotai/Kimi-K2-Instruct", "wandb/moonshotai/Kimi-K2-Instruct" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "responseSchema": true, "parallelFunctionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cortecs", "model": "kimi-k2-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.551, "output": 2.646 } }, { "source": "models.dev", "provider": "huggingface", "model": "moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "jiekou", "model": "moonshotai/kimi-k2-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "moonshotai/kimi-k2-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.57, "output": 2.3 } }, { "source": "models.dev", "provider": "siliconflow", "model": "moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.58, "output": 2.29 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "hyperbolic", "model": "hyperbolic/moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "litellm", "provider": "novita", "model": "novita/moonshotai/kimi-k2-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.57, "output": 2.3 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/moonshotai/Kimi-K2-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Instruct", "Kimi-K2-Instruct", "moonshotai/Kimi-K2-Instruct" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-07-11", "lastUpdated": "2025-09-05", "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "kimi-k2-instruct", "modelKey": "kimi-k2-instruct", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "moonshotai/Kimi-K2-Instruct", "modelKey": "moonshotai/Kimi-K2-Instruct", "displayName": "Kimi-K2-Instruct", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-14", "openWeights": true, "releaseDate": "2025-07-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "moonshotai/kimi-k2-instruct", "modelKey": "moonshotai/kimi-k2-instruct", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2-instruct", "modelKey": "moonshotai/kimi-k2-instruct", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-07-01", "openWeights": false, "releaseDate": "2025-07-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "moonshotai/kimi-k2-instruct", "modelKey": "moonshotai/kimi-k2-instruct", "displayName": "Kimi K2 Instruct", "metadata": { "lastUpdated": "2025-07-11", "openWeights": true, "releaseDate": "2025-07-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2-Instruct", "modelKey": "moonshotai/Kimi-K2-Instruct", "displayName": "moonshotai/Kimi-K2-Instruct", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/moonshotai/Kimi-K2-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "hyperbolic", "model": "hyperbolic/moonshotai/Kimi-K2-Instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/moonshotai/kimi-k2-instruct", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2-Instruct", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/kimi-k2-instruct" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/moonshotai/Kimi-K2-Instruct", "mode": "chat" } ] }, { "id": "moonshotai/kimi-k2-instruct-0711", "provider": "moonshotai", "model": "kimi-k2-instruct-0711", "displayName": "Kimi K2 0711", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/moonshotai/kimi-k2-instruct-0711" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2-instruct-0711", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 2 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0711" ], "families": [ "kimi-k2" ], "releaseDate": "2025-07-11", "lastUpdated": "2025-07-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2-instruct-0711", "modelKey": "moonshotai/kimi-k2-instruct-0711", "displayName": "Kimi K2 0711", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-07-11", "openWeights": false, "releaseDate": "2025-07-11" } } ] }, { "id": "moonshotai/kimi-k2-instruct-0905", "provider": "moonshotai", "model": "kimi-k2-instruct-0905", "displayName": "Kimi-K2-Instruct-0905", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "baseten", "deepinfra", "fireworks_ai", "groq", "huggingface", "io-net", "nano-gpt", "nvidia", "siliconflow", "siliconflow-cn", "synthetic", "together_ai" ], "aliases": [ "baseten/moonshotai/Kimi-K2-Instruct-0905", "deepinfra/moonshotai/Kimi-K2-Instruct-0905", "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "groq/moonshotai/kimi-k2-instruct-0905", "huggingface/moonshotai/Kimi-K2-Instruct-0905", "io-net/moonshotai/Kimi-K2-Instruct-0905", "nano-gpt/moonshotai/Kimi-K2-Instruct-0905", "nvidia/moonshotai/kimi-k2-instruct-0905", "siliconflow-cn/Pro/moonshotai/Kimi-K2-Instruct-0905", "siliconflow-cn/moonshotai/Kimi-K2-Instruct-0905", "siliconflow/moonshotai/Kimi-K2-Instruct-0905", "synthetic/hf:moonshotai/Kimi-K2-Instruct-0905", "together_ai/moonshotai/Kimi-K2-Instruct-0905" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "toolChoice": true, "responseSchema": true, "parallelFunctionCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "huggingface", "model": "moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "io-net", "model": "moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.195, "cacheWrite": 0.78, "input": 0.39, "output": 1.9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "nvidia", "model": "moonshotai/kimi-k2-instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "siliconflow", "model": "moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 1.2 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 0.5, "output": 2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "groq", "model": "groq/moonshotai/kimi-k2-instruct-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 1, "output": 3 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2-Instruct-0905", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0905", "Kimi K2 Instruct", "Kimi-K2-Instruct-0905", "Pro/moonshotai/Kimi-K2-Instruct-0905", "moonshotai/Kimi-K2-Instruct-0905" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-09-04", "lastUpdated": "2025-09-04", "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "moonshotai/Kimi-K2-Instruct-0905", "modelKey": "moonshotai/Kimi-K2-Instruct-0905", "displayName": "Kimi-K2-Instruct-0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-04", "openWeights": true, "releaseDate": "2025-09-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "moonshotai/Kimi-K2-Instruct-0905", "modelKey": "moonshotai/Kimi-K2-Instruct-0905", "displayName": "Kimi K2 Instruct", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2024-09-05", "openWeights": false, "releaseDate": "2024-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/Kimi-K2-Instruct-0905", "modelKey": "moonshotai/Kimi-K2-Instruct-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "moonshotai/kimi-k2-instruct-0905", "modelKey": "moonshotai/kimi-k2-instruct-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2-Instruct-0905", "modelKey": "moonshotai/Kimi-K2-Instruct-0905", "displayName": "moonshotai/Kimi-K2-Instruct-0905", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/moonshotai/Kimi-K2-Instruct-0905", "modelKey": "Pro/moonshotai/Kimi-K2-Instruct-0905", "displayName": "Pro/moonshotai/Kimi-K2-Instruct-0905", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2-Instruct-0905", "modelKey": "moonshotai/Kimi-K2-Instruct-0905", "displayName": "moonshotai/Kimi-K2-Instruct-0905", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:moonshotai/Kimi-K2-Instruct-0905", "modelKey": "hf:moonshotai/Kimi-K2-Instruct-0905", "displayName": "Kimi K2 0905", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2-Instruct-0905", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/moonshotai/Kimi-K2-Instruct-0905", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "mode": "chat", "metadata": { "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/moonshotai/kimi-k2-instruct-0905", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2-Instruct-0905", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/kimi-k2-0905" } } ] }, { "id": "moonshotai/kimi-k2-instruct-fast", "provider": "moonshotai", "model": "kimi-k2-instruct-fast", "displayName": "Kimi K2 0711 Fast", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/kimi-k2-instruct-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "kimi-k2-instruct-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 2 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0711 Fast" ], "releaseDate": "2025-07-15", "lastUpdated": "2025-07-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "kimi-k2-instruct-fast", "modelKey": "kimi-k2-instruct-fast", "displayName": "Kimi K2 0711 Fast", "metadata": { "lastUpdated": "2025-07-15", "openWeights": false, "releaseDate": "2025-07-15" } } ] }, { "id": "moonshotai/kimi-k2-instruct-fp4", "provider": "moonshotai", "model": "kimi-k2-instruct-fp4", "displayName": "Kimi K2 0711 Instruct FP4", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/baseten/Kimi-K2-Instruct-FP4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "baseten/Kimi-K2-Instruct-FP4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 2 } } ] }, "metadata": { "displayNames": [ "Kimi K2 0711 Instruct FP4" ], "families": [ "kimi-k2" ], "releaseDate": "2025-07-11", "lastUpdated": "2025-07-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "baseten/Kimi-K2-Instruct-FP4", "modelKey": "baseten/Kimi-K2-Instruct-FP4", "displayName": "Kimi K2 0711 Instruct FP4", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-07-11", "openWeights": false, "releaseDate": "2025-07-11" } } ] }, { "id": "moonshotai/kimi-k2-thinking", "provider": "moonshotai", "model": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "alibaba-cn", "azure", "azure-cognitive-services", "baseten", "cortecs", "crusoe", "fireworks_ai", "gmi", "helicone", "huggingface", "io-net", "kilo", "kimi-for-coding", "llmgateway", "meganova", "moonshot", "moonshotai", "moonshotai-cn", "nano-gpt", "novita", "novita-ai", "ollama-cloud", "opencode", "openrouter", "poe", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "vercel", "zenmux" ], "aliases": [ "302ai/kimi-k2-thinking", "alibaba-cn/kimi-k2-thinking", "azure-cognitive-services/kimi-k2-thinking", "azure/kimi-k2-thinking", "baseten/moonshotai/Kimi-K2-Thinking", "cortecs/kimi-k2-thinking", "crusoe/moonshotai/Kimi-K2-Thinking", "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "gmi/moonshotai/Kimi-K2-Thinking", "helicone/kimi-k2-thinking", "huggingface/moonshotai/Kimi-K2-Thinking", "io-net/moonshotai/Kimi-K2-Thinking", "kilo/moonshotai/kimi-k2-thinking", "kimi-for-coding/kimi-k2-thinking", "llmgateway/kimi-k2-thinking", "meganova/moonshotai/Kimi-K2-Thinking", "moonshot/kimi-k2-thinking", "moonshotai-cn/kimi-k2-thinking", "moonshotai/kimi-k2-thinking", "nano-gpt/moonshotai/kimi-k2-thinking", "novita-ai/moonshotai/kimi-k2-thinking", "novita/moonshotai/kimi-k2-thinking", "ollama-cloud/kimi-k2-thinking", "opencode/kimi-k2-thinking", "openrouter/moonshotai/kimi-k2-thinking", "poe/novita/kimi-k2-thinking", "qiniu-ai/moonshotai/kimi-k2-thinking", "siliconflow-cn/Pro/moonshotai/Kimi-K2-Thinking", "siliconflow-cn/moonshotai/Kimi-K2-Thinking", "siliconflow/moonshotai/Kimi-K2-Thinking", "synthetic/hf:moonshotai/Kimi-K2-Thinking", "vercel/moonshotai/kimi-k2-thinking", "zenmux/moonshotai/kimi-k2-thinking" ], "mergedProviderModelRecords": 33, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "interleaved": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.575, "output": 2.3 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 2.294 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "azure", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "cortecs", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.656, "output": 2.731 } }, { "source": "models.dev", "provider": "helicone", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.48, "output": 2 } }, { "source": "models.dev", "provider": "huggingface", "model": "moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "io-net", "model": "moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "cacheWrite": 1.1, "input": 0.55, "output": 2.25 } }, { "source": "models.dev", "provider": "kilo", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.47, "output": 2 } }, { "source": "models.dev", "provider": "kimi-for-coding", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "meganova", "model": "moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.6 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "opencode", "model": "kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 0.4, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.5 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.5 } }, { "source": "models.dev", "provider": "siliconflow", "model": "moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.5 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 2.5 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/moonshotai/Kimi-K2-Thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 1.2 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "novita", "model": "novita/moonshotai/kimi-k2-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking", "Kimi-K2-Thinking", "Moonshot Kimi K2 Thinking", "MoonshotAI: Kimi K2 Thinking", "Pro/moonshotai/Kimi-K2-Thinking", "kimi-k2-thinking", "moonshotai/Kimi-K2-Thinking" ], "families": [ "kimi-thinking" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-09-05", "lastUpdated": "2025-09-05", "deprecationDate": "2026-05-25", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 33 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "kimi-k2-thinking", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Moonshot Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-12-02", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "moonshotai/Kimi-K2-Thinking", "modelKey": "moonshotai/Kimi-K2-Thinking", "displayName": "Kimi-K2-Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "moonshotai/Kimi-K2-Thinking", "modelKey": "moonshotai/Kimi-K2-Thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2024-11-01", "openWeights": false, "releaseDate": "2024-11-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "MoonshotAI: Kimi K2 Thinking", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-11-06", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kimi-for-coding", "providerName": "Kimi For Coding", "providerApi": "https://api.kimi.com/coding/v1", "providerDoc": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-12", "openWeights": true, "releaseDate": "2025-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "moonshotai/Kimi-K2-Thinking", "modelKey": "moonshotai/Kimi-K2-Thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-07", "openWeights": true, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "kimi-k2-thinking", "family": "kimi-thinking", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2-thinking", "modelKey": "kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/kimi-k2-thinking", "modelKey": "novita/kimi-k2-thinking", "displayName": "kimi-k2-thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-07", "openWeights": false, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "metadata": { "lastUpdated": "2025-11-07", "openWeights": false, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2-Thinking", "modelKey": "moonshotai/Kimi-K2-Thinking", "displayName": "moonshotai/Kimi-K2-Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/moonshotai/Kimi-K2-Thinking", "modelKey": "Pro/moonshotai/Kimi-K2-Thinking", "displayName": "Pro/moonshotai/Kimi-K2-Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2-Thinking", "modelKey": "moonshotai/Kimi-K2-Thinking", "displayName": "moonshotai/Kimi-K2-Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:moonshotai/Kimi-K2-Thinking", "modelKey": "hf:moonshotai/Kimi-K2-Thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-07", "openWeights": true, "releaseDate": "2025-11-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2-thinking", "modelKey": "moonshotai/kimi-k2-thinking", "displayName": "Kimi K2 Thinking", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2-Thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/moonshotai/Kimi-K2-Thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/moonshotai/Kimi-K2-Thinking", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2-thinking", "mode": "chat", "metadata": { "deprecationDate": "2026-05-25", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/moonshotai/kimi-k2-thinking", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2-thinking", "displayName": "MoonshotAI: Kimi K2 Thinking", "metadata": { "canonicalSlug": "moonshotai/kimi-k2-thinking-20251106", "createdAt": "2025-11-06T14:50:22.000Z", "huggingFaceId": "moonshotai/Kimi-K2-Thinking", "links": { "details": "/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2-thinking-251104", "provider": "moonshotai", "model": "kimi-k2-thinking-251104", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/kimi-k2-thinking-251104" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 229376, "inputTokens": 229376, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "kimi-k2-thinking-251104", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "kimi-k2-thinking-251104", "mode": "chat" } ] }, { "id": "moonshotai/kimi-k2-thinking-maas", "provider": "moonshotai", "model": "kimi-k2-thinking-maas", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-moonshot_models" ], "aliases": [ "google-vertex/moonshotai/kimi-k2-thinking-maas", "vertex_ai-moonshot_models/vertex_ai/moonshotai/kimi-k2-thinking-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "moonshotai/kimi-k2-thinking-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } }, { "source": "litellm", "provider": "vertex_ai-moonshot_models", "model": "vertex_ai/moonshotai/kimi-k2-thinking-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking" ], "families": [ "kimi-thinking" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "moonshotai/kimi-k2-thinking-maas", "modelKey": "moonshotai/kimi-k2-thinking-maas", "displayName": "Kimi K2 Thinking", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-13", "openWeights": true, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-moonshot_models", "model": "vertex_ai/moonshotai/kimi-k2-thinking-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" } } ] }, { "id": "moonshotai/kimi-k2-thinking-original", "provider": "moonshotai", "model": "kimi-k2-thinking-original", "displayName": "Kimi K2 Thinking Original", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/moonshotai/kimi-k2-thinking-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2-thinking-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking Original" ], "families": [ "kimi-thinking" ], "releaseDate": "2025-11-06", "lastUpdated": "2025-11-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2-thinking-original", "modelKey": "moonshotai/kimi-k2-thinking-original", "displayName": "Kimi K2 Thinking Original", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } } ] }, { "id": "moonshotai/kimi-k2-thinking-turbo", "provider": "moonshotai", "model": "kimi-k2-thinking-turbo", "displayName": "Kimi K2 Thinking Turbo", "family": "kimi-thinking", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "llmgateway", "moonshot", "moonshotai", "moonshotai-cn", "zenmux" ], "aliases": [ "302ai/kimi-k2-thinking-turbo", "llmgateway/kimi-k2-thinking-turbo", "moonshot/kimi-k2-thinking-turbo", "moonshotai-cn/kimi-k2-thinking-turbo", "moonshotai/kimi-k2-thinking-turbo", "zenmux/moonshotai/kimi-k2-thinking-turbo" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "kimi-k2-thinking-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.265, "output": 9.119 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2-thinking-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2-thinking-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2-thinking-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2-thinking-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2-thinking-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking Turbo", "kimi-k2-thinking-turbo" ], "families": [ "kimi-thinking" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-09-05", "lastUpdated": "2025-09-05", "deprecationDate": "2026-05-25", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "kimi-k2-thinking-turbo", "modelKey": "kimi-k2-thinking-turbo", "displayName": "kimi-k2-thinking-turbo", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2-thinking-turbo", "modelKey": "kimi-k2-thinking-turbo", "displayName": "Kimi K2 Thinking Turbo", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2-thinking-turbo", "modelKey": "kimi-k2-thinking-turbo", "displayName": "Kimi K2 Thinking Turbo", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2-thinking-turbo", "modelKey": "kimi-k2-thinking-turbo", "displayName": "Kimi K2 Thinking Turbo", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "openWeights": true, "releaseDate": "2025-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2-thinking-turbo", "modelKey": "moonshotai/kimi-k2-thinking-turbo", "displayName": "Kimi K2 Thinking Turbo", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2-thinking-turbo", "mode": "chat", "metadata": { "deprecationDate": "2026-05-25", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } } ] }, { "id": "moonshotai/kimi-k2-thinking-turbo-original", "provider": "moonshotai", "model": "kimi-k2-thinking-turbo-original", "displayName": "Kimi K2 Thinking Turbo Original", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/moonshotai/kimi-k2-thinking-turbo-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2-thinking-turbo-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.15, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Thinking Turbo Original" ], "families": [ "kimi-thinking" ], "releaseDate": "2025-11-06", "lastUpdated": "2025-11-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2-thinking-turbo-original", "modelKey": "moonshotai/kimi-k2-thinking-turbo-original", "displayName": "Kimi K2 Thinking Turbo Original", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-11-06", "openWeights": false, "releaseDate": "2025-11-06" } } ] }, { "id": "moonshotai/kimi-k2-turbo-preview", "provider": "moonshotai", "model": "kimi-k2-turbo-preview", "displayName": "Kimi K2 Turbo", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "moonshot", "moonshotai", "moonshotai-cn" ], "aliases": [ "abacus/kimi-k2-turbo-preview", "moonshot/kimi-k2-turbo-preview", "moonshotai-cn/kimi-k2-turbo-preview", "moonshotai/kimi-k2-turbo-preview" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "kimi-k2-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 8 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "input": 2.4, "output": 10 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.6, "input": 2.4, "output": 10 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2-turbo-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1.15, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2 Turbo", "Kimi K2 Turbo Preview" ], "families": [ "kimi-k2" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-07-08", "lastUpdated": "2025-07-08", "deprecationDate": "2026-05-25", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "kimi-k2-turbo-preview", "modelKey": "kimi-k2-turbo-preview", "displayName": "Kimi K2 Turbo Preview", "family": "kimi-k2", "metadata": { "lastUpdated": "2025-07-08", "openWeights": false, "releaseDate": "2025-07-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2-turbo-preview", "modelKey": "kimi-k2-turbo-preview", "displayName": "Kimi K2 Turbo", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2-turbo-preview", "modelKey": "kimi-k2-turbo-preview", "displayName": "Kimi K2 Turbo", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2025-09-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2-turbo-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-05-25", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } } ] }, { "id": "moonshotai/kimi-k2:1t", "provider": "moonshotai", "model": "kimi-k2:1t", "displayName": "kimi-k2:1t", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/kimi-k2:1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "kimi-k2:1t" ], "families": [ "kimi-k2" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-07-11", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "kimi-k2:1t", "modelKey": "kimi-k2:1t", "displayName": "kimi-k2:1t", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-07-11" } } ] }, { "id": "moonshotai/kimi-k2.5", "provider": "moonshotai", "model": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "aihubmix", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "auriko", "azure", "azure-cognitive-services", "azure_ai", "baseten", "cloudflare-ai-gateway", "cortecs", "crof", "deepinfra", "digitalocean", "evroc", "frogbot", "hpc-ai", "huggingface", "jiekou", "kilo", "llmgateway", "meganova", "moonshot", "moonshotai", "moonshotai-cn", "nano-gpt", "nebius", "neuralwatt", "novita-ai", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "poe", "qiniu-ai", "routing-run", "siliconflow", "siliconflow-cn", "synthetic", "tencent-coding-plan", "together_ai", "togetherai", "vercel", "wandb", "zenmux" ], "aliases": [ "abacus/kimi-k2.5", "aihubmix/kimi-k2.5", "alibaba-cn/kimi-k2.5", "alibaba-cn/kimi/kimi-k2.5", "alibaba-coding-plan-cn/kimi-k2.5", "alibaba-coding-plan/kimi-k2.5", "alibaba-token-plan-cn/kimi-k2.5", "alibaba-token-plan/kimi-k2.5", "auriko/kimi-k2.5", "azure-cognitive-services/kimi-k2.5", "azure/kimi-k2.5", "azure_ai/kimi-k2.5", "baseten/moonshotai/Kimi-K2.5", "cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.5", "cortecs/kimi-k2.5", "crof/kimi-k2.5", "deepinfra/moonshotai/Kimi-K2.5", "digitalocean/kimi-k2.5", "evroc/moonshotai/Kimi-K2.5", "frogbot/kimi-k2.5", "hpc-ai/moonshotai/kimi-k2.5", "huggingface/moonshotai/Kimi-K2.5", "jiekou/moonshotai/kimi-k2.5", "kilo/moonshotai/kimi-k2.5", "llmgateway/kimi-k2.5", "meganova/moonshotai/Kimi-K2.5", "moonshot/kimi-k2.5", "moonshotai-cn/kimi-k2.5", "moonshotai/kimi-k2.5", "nano-gpt/TEE/kimi-k2.5", "nano-gpt/moonshotai/kimi-k2.5", "nebius/moonshotai/Kimi-K2.5", "neuralwatt/moonshotai/Kimi-K2.5", "novita-ai/moonshotai/kimi-k2.5", "ollama-cloud/kimi-k2.5", "opencode-go/kimi-k2.5", "opencode/kimi-k2.5", "openrouter/moonshotai/kimi-k2.5", "orcarouter/kimi/kimi-k2.5", "poe/novita/kimi-k2.5", "qiniu-ai/moonshotai/kimi-k2.5", "routing-run/route/kimi-k2.5", "siliconflow-cn/Pro/moonshotai/Kimi-K2.5", "siliconflow/moonshotai/Kimi-K2.5", "synthetic/hf:moonshotai/Kimi-K2.5", "tencent-coding-plan/kimi-k2.5", "together_ai/moonshotai/Kimi-K2.5", "togetherai/moonshotai/Kimi-K2.5", "vercel/moonshotai/kimi-k2.5", "wandb/moonshotai/Kimi-K2.5", "zenmux/moonshotai/kimi-k2.5" ], "mergedProviderModelRecords": 51, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "functionCalling": true, "toolChoice": true, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "aihubmix", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.574, "output": 2.411 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "kimi/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "auriko", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.8 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "azure", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "baseten", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "cortecs", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.76 } }, { "source": "models.dev", "provider": "crof", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.35, "output": 1.7 } }, { "source": "models.dev", "provider": "deepinfra", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.45, "output": 2.25 } }, { "source": "models.dev", "provider": "digitalocean", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.7 } }, { "source": "models.dev", "provider": "evroc", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.47, "output": 5.9 } }, { "source": "models.dev", "provider": "frogbot", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "hpc-ai", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.3, "output": 1.5 } }, { "source": "models.dev", "provider": "huggingface", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "jiekou", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "kilo", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "meganova", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.8 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.9 } }, { "source": "models.dev", "provider": "nebius", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 2.5, "reasoningOutput": 2.5 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.52, "output": 2.59 } }, { "source": "models.dev", "provider": "novita-ai", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "opencode-go", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "opencode", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.375, "output": 2.025 } }, { "source": "models.dev", "provider": "orcarouter", "model": "kimi/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "poe", "model": "novita/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.462, "output": 2.42 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.25 } }, { "source": "models.dev", "provider": "siliconflow", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.25 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "tencent-coding-plan", "model": "kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "togetherai", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.8 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "models.dev", "provider": "wandb", "model": "moonshotai/Kimi-K2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2.85 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.58, "output": 3.02 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/moonshotai/kimi-k2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 2.8 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/moonshotai/Kimi-K2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.375, "output": 2.025 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5", "Kimi K2.5 TEE", "Kimi-K2.5", "Moonshot Kimi K2.5", "MoonshotAI: Kimi K2.5", "Moonshotai/Kimi-K2.5", "Pro/moonshotai/Kimi-K2.5", "kimi-k2.5", "kimi/kimi-k2.5", "moonshotai/Kimi-K2.5" ], "families": [ "kimi-k2", "kimi-thinking" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01", "lastUpdated": "2026-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 51 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Moonshot Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "kimi/kimi-k2.5", "modelKey": "kimi/kimi-k2.5", "displayName": "kimi/kimi-k2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-06", "openWeights": true, "releaseDate": "2026-02-06", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-01-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/moonshotai/kimi-k2.5", "modelKey": "workers-ai/@cf/moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-thinking", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi-K2.5", "metadata": { "lastUpdated": "1970-01-01", "openWeights": false, "releaseDate": "1970-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "hpc-ai", "providerName": "HPC-AI", "providerApi": "https://api.hpc-ai.com/inference/v1", "providerDoc": "https://www.hpc-ai.com/doc/docs/quickstart/", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-01-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi-K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-01", "openWeights": true, "releaseDate": "2026-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "budget_tokens", "min": 1024, "max": 262143 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "MoonshotAI: Kimi K2.5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-26", "openWeights": false, "releaseDate": "2026-01-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/kimi-k2.5", "modelKey": "TEE/kimi-k2.5", "displayName": "Kimi K2.5 TEE", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-29", "openWeights": false, "releaseDate": "2026-01-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi-K2.5", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "kimi-k2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "kimi/kimi-k2.5", "modelKey": "kimi/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/kimi-k2.5", "modelKey": "novita/kimi-k2.5", "displayName": "Kimi-K2.5", "metadata": { "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Moonshotai/Kimi-K2.5", "metadata": { "lastUpdated": "2026-01-28", "openWeights": false, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/kimi-k2.5", "modelKey": "route/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/moonshotai/Kimi-K2.5", "modelKey": "Pro/moonshotai/Kimi-K2.5", "displayName": "Pro/moonshotai/Kimi-K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "moonshotai/Kimi-K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:moonshotai/Kimi-K2.5", "modelKey": "hf:moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "kimi-k2.5", "modelKey": "kimi-k2.5", "displayName": "Kimi-K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "moonshotai/Kimi-K2.5", "modelKey": "moonshotai/Kimi-K2.5", "displayName": "Kimi K2.5", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2.5", "modelKey": "moonshotai/kimi-k2.5", "displayName": "Kimi K2.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/kimi-k2.5", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/moonshotai/Kimi-K2.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2.5", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/moonshotai/kimi-k2.5", "mode": "chat", "metadata": { "source": "https://openrouter.ai/moonshotai/kimi-k2.5" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/moonshotai/Kimi-K2.5", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/kimi-k2-5" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/moonshotai/Kimi-K2.5", "mode": "chat", "metadata": { "source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2.5", "displayName": "MoonshotAI: Kimi K2.5", "metadata": { "canonicalSlug": "moonshotai/kimi-k2.5-0127", "createdAt": "2026-01-27T04:11:16.000Z", "huggingFaceId": "moonshotai/Kimi-K2.5", "links": { "details": "/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2.5-fast", "provider": "moonshotai", "model": "kimi-k2.5-fast", "displayName": "Kimi-K2.5-fast", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "nebius", "neuralwatt" ], "aliases": [ "nebius/moonshotai/Kimi-K2.5-fast", "neuralwatt/kimi-k2.5-fast" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262128, "inputTokens": 256000, "outputTokens": 262128, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "moonshotai/Kimi-K2.5-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.625, "input": 0.5, "output": 2.5 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "kimi-k2.5-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.52, "output": 2.59 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 Fast", "Kimi-K2.5-fast" ], "families": [ "kimi-k2" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-12-15", "lastUpdated": "2026-02-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "moonshotai/Kimi-K2.5-fast", "modelKey": "moonshotai/Kimi-K2.5-fast", "displayName": "Kimi-K2.5-fast", "family": "kimi-k2", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "kimi-k2.5-fast", "modelKey": "kimi-k2.5-fast", "displayName": "Kimi K2.5 Fast", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } } ] }, { "id": "moonshotai/kimi-k2.5-free", "provider": "moonshotai", "model": "kimi-k2.5-free", "displayName": "Kimi K2.5 Free", "family": "kimi-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/kimi-k2.5-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "kimi-k2.5-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 Free" ], "families": [ "kimi-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-10", "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.5-free", "modelKey": "kimi-k2.5-free", "displayName": "Kimi K2.5 Free", "family": "kimi-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "openWeights": true, "releaseDate": "2026-01-27" } } ] }, { "id": "moonshotai/kimi-k2.5-fw", "provider": "moonshotai", "model": "kimi-k2.5-fw", "displayName": "Kimi-K2.5-FW", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/fireworks-ai/kimi-k2.5-fw" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 245760, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "fireworks-ai/kimi-k2.5-fw", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi-K2.5-FW" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "fireworks-ai/kimi-k2.5-fw", "modelKey": "fireworks-ai/kimi-k2.5-fw", "displayName": "Kimi-K2.5-FW", "metadata": { "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27" } } ] }, { "id": "moonshotai/kimi-k2.5-lightning", "provider": "moonshotai", "model": "kimi-k2.5-lightning", "displayName": "Kimi K2.5 (Lightning)", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "crof" ], "aliases": [ "crof/kimi-k2.5-lightning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "crof", "model": "kimi-k2.5-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 (Lightning)" ], "families": [ "kimi-k2" ], "releaseDate": "2026-02-06", "lastUpdated": "2026-02-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "kimi-k2.5-lightning", "modelKey": "kimi-k2.5-lightning", "displayName": "Kimi K2.5 (Lightning)", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-02-06", "openWeights": true, "releaseDate": "2026-02-06", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "moonshotai/kimi-k2.5-nvfp4", "provider": "moonshotai", "model": "kimi-k2.5-nvfp4", "displayName": "Kimi K2.5 (NVFP4)", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "synthetic" ], "aliases": [ "synthetic/hf:nvidia/Kimi-K2.5-NVFP4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "synthetic", "model": "hf:nvidia/Kimi-K2.5-NVFP4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 (NVFP4)" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:nvidia/Kimi-K2.5-NVFP4", "modelKey": "hf:nvidia/Kimi-K2.5-NVFP4", "displayName": "Kimi K2.5 (NVFP4)", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } } ] }, { "id": "moonshotai/kimi-k2.5-tee", "provider": "moonshotai", "model": "kimi-k2.5-tee", "displayName": "Kimi K2.5 TEE", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/moonshotai/Kimi-K2.5-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "moonshotai/Kimi-K2.5-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 0.44, "output": 2 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 TEE" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2024-10", "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "moonshotai/Kimi-K2.5-TEE", "modelKey": "moonshotai/Kimi-K2.5-TEE", "displayName": "Kimi K2.5 TEE", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2.5-thinking", "provider": "moonshotai", "model": "kimi-k2.5-thinking", "displayName": "Kimi K2.5 Thinking TEE", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/kimi-k2.5-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/kimi-k2.5-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 Thinking TEE" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-01-29", "lastUpdated": "2026-01-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/kimi-k2.5-thinking", "modelKey": "TEE/kimi-k2.5-thinking", "displayName": "Kimi K2.5 Thinking TEE", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-01-29", "openWeights": false, "releaseDate": "2026-01-29" } } ] }, { "id": "moonshotai/kimi-k2.5:thinking", "provider": "moonshotai", "model": "kimi-k2.5:thinking", "displayName": "Kimi K2.5 Thinking", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/moonshotai/kimi-k2.5:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2.5:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Kimi K2.5 Thinking" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-01-26", "lastUpdated": "2026-01-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2.5:thinking", "modelKey": "moonshotai/kimi-k2.5:thinking", "displayName": "Kimi K2.5 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-01-26", "openWeights": false, "releaseDate": "2026-01-26" } } ] }, { "id": "moonshotai/kimi-k2.6", "provider": "moonshotai", "model": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "alibaba-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "ambient", "auriko", "azure", "azure-cognitive-services", "azure_ai", "baseten", "berget", "cloudflare-ai-gateway", "cloudflare-workers-ai", "cortecs", "crof", "deepinfra", "digitalocean", "fastrouter", "gmicloud", "huggingface", "inceptron", "kilo", "lilac", "llmgateway", "moonshot", "moonshotai", "moonshotai-cn", "nano-gpt", "neuralwatt", "novita-ai", "nvidia", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "poe", "routing-run", "siliconflow", "siliconflow-cn", "synthetic", "togetherai", "vercel", "vultr", "wafer.ai", "zenmux" ], "aliases": [ "aihubmix/kimi-k2.6", "alibaba-cn/kimi-k2.6", "alibaba-token-plan-cn/kimi-k2.6", "alibaba-token-plan/kimi-k2.6", "ambient/moonshotai/kimi-k2.6", "auriko/kimi-k2.6", "azure-cognitive-services/kimi-k2.6", "azure/kimi-k2.6", "azure_ai/kimi-k2.6", "baseten/moonshotai/Kimi-K2.6", "berget/moonshotai/Kimi-K2.6", "cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.6", "cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6", "cortecs/kimi-k2.6", "crof/kimi-k2.6", "deepinfra/moonshotai/Kimi-K2.6", "digitalocean/kimi-k2.6", "fastrouter/moonshotai/kimi-k2.6", "gmicloud/moonshotai/Kimi-K2.6", "huggingface/moonshotai/Kimi-K2.6", "inceptron/moonshotai/Kimi-K2.6", "kilo/moonshotai/kimi-k2.6", "lilac/moonshotai/kimi-k2.6", "llmgateway/kimi-k2.6", "moonshot/kimi-k2.6", "moonshotai-cn/kimi-k2.6", "moonshotai/kimi-k2.6", "nano-gpt/TEE/kimi-k2.6", "nano-gpt/moonshotai/kimi-k2.6", "neuralwatt/moonshotai/Kimi-K2.6", "novita-ai/moonshotai/kimi-k2.6", "nvidia/moonshotai/kimi-k2.6", "ollama-cloud/kimi-k2.6", "opencode-go/kimi-k2.6", "opencode/kimi-k2.6", "openrouter/moonshotai/kimi-k2.6", "orcarouter/kimi/kimi-k2.6", "poe/novita/kimi-k2.6", "routing-run/route/kimi-k2.6", "siliconflow-cn/Pro/moonshotai/Kimi-K2.6", "siliconflow/moonshotai/Kimi-K2.6", "synthetic/hf:moonshotai/Kimi-K2.6", "togetherai/moonshotai/Kimi-K2.6", "vercel/moonshotai/kimi-k2.6", "vultr/moonshotai/Kimi-K2.6", "wafer.ai/Kimi-K2.6", "zenmux/moonshotai/kimi-k2.6" ], "mergedProviderModelRecords": 47, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "interleaved": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.929, "output": 3.858 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "ambient", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "auriko", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "azure", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "baseten", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "berget", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.83, "output": 3.85 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "cortecs", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.81, "output": 3.54 } }, { "source": "models.dev", "provider": "crof", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.5, "output": 1.99 } }, { "source": "models.dev", "provider": "deepinfra", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.75, "output": 3.5 } }, { "source": "models.dev", "provider": "digitalocean", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "fastrouter", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 3.5 } }, { "source": "models.dev", "provider": "gmicloud", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.144, "input": 0.855, "output": 3.6 } }, { "source": "models.dev", "provider": "huggingface", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "inceptron", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 0.78, "output": 3.5 } }, { "source": "models.dev", "provider": "kilo", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.375, "input": 0.75, "output": 3.5 } }, { "source": "models.dev", "provider": "lilac", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.7, "output": 3.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.53, "output": 2.73 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.375, "input": 1.5, "output": 5.25 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69, "output": 3.22 } }, { "source": "models.dev", "provider": "novita-ai", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "nvidia", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "opencode-go", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "opencode", "model": "kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.67, "output": 3.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "kimi/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "poe", "model": "novita/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.96, "output": 4.04 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.462, "output": 2.42 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.77, "output": 4 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.95, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "togetherai", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.2, "output": 4.5 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "vultr", "model": "moonshotai/Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "Kimi-K2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "cacheWrite": 0, "input": 0.68, "output": 3.15 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/kimi-k2.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-k2.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2.6", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 0.67, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6", "Kimi K2.6 TEE", "Kimi-K2.6", "Moonshot Kimi K2.6", "MoonshotAI: Kimi K2.6", "Pro/moonshotai/Kimi-K2.6", "kimi-k2.6", "moonshotai/Kimi-K2.6" ], "families": [ "kimi-k2", "kimi-thinking" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 47 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Moonshot Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ambient", "providerName": "Ambient", "providerApi": "https://api.ambient.xyz/v1", "providerDoc": "https://ambient.xyz", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2026-05-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/moonshotai/kimi-k2.6", "modelKey": "workers-ai/@cf/moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/moonshotai/kimi-k2.6", "modelKey": "@cf/moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi-K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inceptron", "providerName": "Inceptron", "providerApi": "https://api.inceptron.io/v1", "providerDoc": "https://docs.inceptron.io", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "MoonshotAI: Kimi K2.6", "metadata": { "lastUpdated": "2026-05-12", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lilac", "providerName": "Lilac", "providerApi": "https://api.getlilac.com/v1", "providerDoc": "https://docs.getlilac.com/inference/models", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/kimi-k2.6", "modelKey": "TEE/kimi-k2.6", "displayName": "Kimi K2.6 TEE", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "kimi-k2.6", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.6", "modelKey": "kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "kimi/kimi-k2.6", "modelKey": "kimi/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/kimi-k2.6", "modelKey": "novita/kimi-k2.6", "displayName": "Kimi-K2.6", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-02", "openWeights": true, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/kimi-k2.6", "modelKey": "route/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/moonshotai/Kimi-K2.6", "modelKey": "Pro/moonshotai/Kimi-K2.6", "displayName": "Pro/moonshotai/Kimi-K2.6", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "moonshotai/Kimi-K2.6", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-06-15", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:moonshotai/Kimi-K2.6", "modelKey": "hf:moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "moonshotai/Kimi-K2.6", "modelKey": "moonshotai/Kimi-K2.6", "displayName": "Kimi K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "Kimi-K2.6", "modelKey": "Kimi-K2.6", "displayName": "Kimi-K2.6", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-05-13", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2.6", "modelKey": "moonshotai/kimi-k2.6", "displayName": "Kimi K2.6", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/kimi-k2.6", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-k2.6", "mode": "chat", "metadata": { "source": "https://platform.kimi.ai/docs/pricing/chat-k26" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2.6", "displayName": "MoonshotAI: Kimi K2.6", "metadata": { "canonicalSlug": "moonshotai/kimi-k2.6-20260420", "createdAt": "2026-04-20T15:36:42.000Z", "huggingFaceId": "moonshotai/Kimi-K2.6", "links": { "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2.6-6bit", "provider": "moonshotai", "model": "kimi-k2.6-6bit", "displayName": "Kimi K2.6 6bit", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/kimi-k2.6-6bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/kimi-k2.6-6bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.462, "output": 2.42 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 6bit" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/kimi-k2.6-6bit", "modelKey": "route/kimi-k2.6-6bit", "displayName": "Kimi K2.6 6bit", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } } ] }, { "id": "moonshotai/kimi-k2.6-fast", "provider": "moonshotai", "model": "kimi-k2.6-fast", "displayName": "Kimi K2.6 Fast", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/kimi-k2.6-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262128, "outputTokens": 262128, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "kimi-k2.6-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69, "output": 3.22 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 Fast" ], "families": [ "kimi-k2" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "kimi-k2.6-fast", "modelKey": "kimi-k2.6-fast", "displayName": "Kimi K2.6 Fast", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } } ] }, { "id": "moonshotai/kimi-k2.6-tee", "provider": "moonshotai", "model": "kimi-k2.6-tee", "displayName": "Kimi K2.6 TEE", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/moonshotai/Kimi-K2.6-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "moonshotai/Kimi-K2.6-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.475, "input": 0.95, "output": 4 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 TEE" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-12", "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "moonshotai/Kimi-K2.6-TEE", "modelKey": "moonshotai/Kimi-K2.6-TEE", "displayName": "Kimi K2.6 TEE", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2.6:thinking", "provider": "moonshotai", "model": "kimi-k2.6:thinking", "displayName": "Kimi K2.6 Thinking", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/moonshotai/kimi-k2.6:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-k2.6:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.53, "output": 2.73 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 Thinking" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-k2.6:thinking", "modelKey": "moonshotai/kimi-k2.6:thinking", "displayName": "Kimi K2.6 Thinking", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-16" } } ] }, { "id": "moonshotai/kimi-k2.7-code", "provider": "moonshotai", "model": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba-token-plan", "alibaba-token-plan-cn", "ambient", "baseten", "cloudflare-workers-ai", "cortecs", "crof", "llmgateway", "moonshotai", "moonshotai-cn", "neuralwatt", "ollama-cloud", "opencode-go", "openrouter", "togetherai", "vercel", "zenmux" ], "aliases": [ "alibaba-token-plan-cn/kimi-k2.7-code", "alibaba-token-plan/kimi-k2.7-code", "ambient/moonshotai/kimi-k2.7-code", "baseten/moonshotai/Kimi-K2.7-Code", "cloudflare-workers-ai/@cf/moonshotai/kimi-k2.7-code", "cortecs/kimi-k2.7-code", "crof/kimi-k2.7-code", "llmgateway/kimi-k2.7-code", "moonshotai-cn/kimi-k2.7-code", "moonshotai/kimi-k2.7-code", "neuralwatt/moonshotai/Kimi-K2.7-Code", "ollama-cloud/kimi-k2.7-code", "opencode-go/kimi-k2.7-code", "openrouter/moonshotai/kimi-k2.7-code", "togetherai/moonshotai/Kimi-K2.7-Code", "vercel/moonshotai/kimi-k2.7-code", "zenmux/moonshotai/kimi-k2.7-code" ], "mergedProviderModelRecords": 17, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "ambient", "model": "moonshotai/kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "cacheWrite": 0, "input": 0.75, "output": 3.5 } }, { "source": "models.dev", "provider": "baseten", "model": "moonshotai/Kimi-K2.7-Code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/moonshotai/kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "cortecs", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.32, "input": 1.28, "output": 4.63 } }, { "source": "models.dev", "provider": "crof", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.55, "output": 2.25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "moonshotai/Kimi-K2.7-Code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "opencode-go", "model": "kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "openrouter", "model": "moonshotai/kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.144, "input": 0.68, "output": 3.41 } }, { "source": "models.dev", "provider": "togetherai", "model": "moonshotai/Kimi-K2.7-Code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } }, { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2.7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } }, { "source": "openrouter", "provider": "openrouter", "model": "moonshotai/kimi-k2.7-code", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1296, "input": 0.612, "output": 3.069 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code", "MoonshotAI: Kimi K2.7 Code", "kimi-k2.7-code" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ambient", "providerName": "Ambient", "providerApi": "https://api.ambient.xyz/v1", "providerDoc": "https://ambient.xyz", "model": "moonshotai/kimi-k2.7-code", "modelKey": "moonshotai/kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "moonshotai/Kimi-K2.7-Code", "modelKey": "moonshotai/Kimi-K2.7-Code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/moonshotai/kimi-k2.7-code", "modelKey": "@cf/moonshotai/kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "moonshotai/Kimi-K2.7-Code", "modelKey": "moonshotai/Kimi-K2.7-Code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "kimi-k2.7-code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "kimi-k2.7-code", "modelKey": "kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "moonshotai/kimi-k2.7-code", "modelKey": "moonshotai/kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "moonshotai/Kimi-K2.7-Code", "modelKey": "moonshotai/Kimi-K2.7-Code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-06-14", "openWeights": true, "releaseDate": "2026-06-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2.7-code", "modelKey": "moonshotai/kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": false, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2.7-code", "modelKey": "moonshotai/kimi-k2.7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "moonshotai/kimi-k2.7-code", "displayName": "MoonshotAI: Kimi K2.7 Code", "metadata": { "canonicalSlug": "moonshotai/kimi-k2.7-code-20260612", "createdAt": "2026-06-12T12:12:41.000Z", "huggingFaceId": "moonshotai/Kimi-K2.7-Code", "links": { "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints" }, "reasoning": { "mandatory": true, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-k2.7-code-free", "provider": "moonshotai", "model": "kimi-k2.7-code-free", "displayName": "Kimi K2.7 Code (Free)", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/moonshotai/kimi-k2.7-code-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "moonshotai/kimi-k2.7-code-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code (Free)" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "moonshotai/kimi-k2.7-code-free", "modelKey": "moonshotai/kimi-k2.7-code-free", "displayName": "Kimi K2.7 Code (Free)", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "moonshotai/kimi-k2.7-code-highspeed", "provider": "moonshotai", "model": "kimi-k2.7-code-highspeed", "displayName": "Kimi K2.7 Code HighSpeed", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "moonshotai", "moonshotai-cn", "vercel" ], "aliases": [ "moonshotai-cn/kimi-k2.7-code-highspeed", "moonshotai/kimi-k2.7-code-highspeed", "vercel/moonshotai/kimi-k2.7-code-highspeed" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "moonshotai-cn", "model": "kimi-k2.7-code-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.38, "input": 1.9, "output": 8 } }, { "source": "models.dev", "provider": "moonshotai", "model": "kimi-k2.7-code-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.38, "input": 1.9, "output": 8 } }, { "source": "models.dev", "provider": "vercel", "model": "moonshotai/kimi-k2.7-code-highspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.38, "input": 1.9, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code High Speed", "Kimi K2.7 Code HighSpeed" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai-cn", "providerName": "Moonshot AI (China)", "providerApi": "https://api.moonshot.cn/v1", "providerDoc": "https://platform.moonshot.cn/docs/api/chat", "model": "kimi-k2.7-code-highspeed", "modelKey": "kimi-k2.7-code-highspeed", "displayName": "Kimi K2.7 Code HighSpeed", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moonshotai", "providerName": "Moonshot AI", "providerApi": "https://api.moonshot.ai/v1", "providerDoc": "https://platform.moonshot.ai/docs/api/chat", "model": "kimi-k2.7-code-highspeed", "modelKey": "kimi-k2.7-code-highspeed", "displayName": "Kimi K2.7 Code HighSpeed", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "moonshotai/kimi-k2.7-code-highspeed", "modelKey": "moonshotai/kimi-k2.7-code-highspeed", "displayName": "Kimi K2.7 Code High Speed", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-06-15", "openWeights": false, "releaseDate": "2026-06-15" } } ] }, { "id": "moonshotai/kimi-k2p5", "provider": "moonshotai", "model": "kimi-k2p5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/kimi-k2p5", "fireworks_ai/kimi-k2p5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/kimi-k2p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/kimi-k2p5", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/kimi-k2p5", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "moonshotai/kimi-k2p6", "provider": "moonshotai", "model": "kimi-k2p6", "displayName": "Kimi K2.6", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/kimi-k2p6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/kimi-k2p6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 0.95, "output": 4 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/kimi-k2p6", "modelKey": "accounts/fireworks/models/kimi-k2p6", "displayName": "Kimi K2.6", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2p6-fast", "provider": "moonshotai", "model": "kimi-k2p6-fast", "displayName": "Kimi K2.6 Fast", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/routers/kimi-k2p6-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/routers/kimi-k2p6-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 Fast" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/routers/kimi-k2p6-fast", "modelKey": "accounts/fireworks/routers/kimi-k2p6-fast", "displayName": "Kimi K2.6 Fast", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-06-05", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2p6-turbo", "provider": "moonshotai", "model": "kimi-k2p6-turbo", "displayName": "Kimi K2.6 Turbo", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "firepass", "fireworks-ai" ], "aliases": [ "firepass/accounts/fireworks/routers/kimi-k2p6-turbo", "fireworks-ai/accounts/fireworks/routers/kimi-k2p6-turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "firepass", "model": "accounts/fireworks/routers/kimi-k2p6-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/routers/kimi-k2p6-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 2, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2.6 Turbo" ], "families": [ "kimi-thinking" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "firepass", "providerName": "Fireworks (Firepass)", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://docs.fireworks.ai/firepass", "model": "accounts/fireworks/routers/kimi-k2p6-turbo", "modelKey": "accounts/fireworks/routers/kimi-k2p6-turbo", "displayName": "Kimi K2.6 Turbo", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/routers/kimi-k2p6-turbo", "modelKey": "accounts/fireworks/routers/kimi-k2p6-turbo", "displayName": "Kimi K2.6 Turbo", "family": "kimi-thinking", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2p7-code", "provider": "moonshotai", "model": "kimi-k2p7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/kimi-k2p7-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/kimi-k2p7-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code" ], "families": [ "kimi-k2" ], "releaseDate": "2026-06-12", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/kimi-k2p7-code", "modelKey": "accounts/fireworks/models/kimi-k2p7-code", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-k2p7-code-fast", "provider": "moonshotai", "model": "kimi-k2p7-code-fast", "displayName": "Kimi K2.7 Code Fast", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/routers/kimi-k2p7-code-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/routers/kimi-k2p7-code-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.38, "input": 1.9, "output": 8 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code Fast" ], "families": [ "kimi-k2" ], "releaseDate": "2026-06-12", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/routers/kimi-k2p7-code-fast", "modelKey": "accounts/fireworks/routers/kimi-k2p7-code-fast", "displayName": "Kimi K2.7 Code Fast", "family": "kimi-k2", "metadata": { "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-06-12", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "moonshotai/kimi-latest", "provider": "moonshotai", "model": "kimi-latest", "displayName": "MoonshotAI: Kimi Latest", "family": "kimi", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "moonshot", "nano-gpt", "openrouter" ], "aliases": [ "kilo/~moonshotai/kimi-latest", "moonshot/kimi-latest", "nano-gpt/moonshotai/kimi-latest", "openrouter/~moonshotai/kimi-latest" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 262144, "inputTokens": 256000, "maxTokens": 131072, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~moonshotai/kimi-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14, "input": 0.74, "output": 3.49 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "moonshotai/kimi-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 0.5, "output": 2.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "~moonshotai/kimi-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.67, "output": 3.5 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 2, "output": 5 } }, { "source": "openrouter", "provider": "openrouter", "model": "~moonshotai/kimi-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 0.67, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Kimi Latest", "MoonshotAI Kimi Latest", "MoonshotAI: Kimi Latest" ], "families": [ "kimi" ], "modes": [ "chat" ], "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "deprecationDate": "2026-01-28", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~moonshotai/kimi-latest", "modelKey": "~moonshotai/kimi-latest", "displayName": "MoonshotAI: Kimi Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "moonshotai/kimi-latest", "modelKey": "moonshotai/kimi-latest", "displayName": "Kimi Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~moonshotai/kimi-latest", "modelKey": "~moonshotai/kimi-latest", "displayName": "MoonshotAI Kimi Latest", "family": "kimi", "metadata": { "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-latest", "mode": "chat", "metadata": { "deprecationDate": "2026-01-28", "source": "https://platform.moonshot.ai/docs/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~moonshotai/kimi-latest", "displayName": "MoonshotAI Kimi Latest", "metadata": { "canonicalSlug": "~moonshotai/kimi-latest", "createdAt": "2026-04-27T19:33:48.000Z", "links": { "details": "/api/v1/models/~moonshotai/kimi-latest/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Router", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "moonshotai/kimi-latest-128k", "provider": "moonshotai", "model": "kimi-latest-128k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/kimi-latest-128k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-latest-128k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-latest-128k", "mode": "chat", "metadata": { "deprecationDate": "2026-01-28", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/kimi-latest-32k", "provider": "moonshotai", "model": "kimi-latest-32k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/kimi-latest-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-latest-32k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-latest-32k", "mode": "chat", "metadata": { "deprecationDate": "2026-01-28", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/kimi-latest-8k", "provider": "moonshotai", "model": "kimi-latest-8k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/kimi-latest-8k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-latest-8k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-latest-8k", "mode": "chat", "metadata": { "deprecationDate": "2026-01-28", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/kimi-thinking-preview", "provider": "moonshotai", "model": "kimi-thinking-preview", "displayName": "Kimi Thinking Preview", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "moonshot", "nano-gpt" ], "aliases": [ "moonshot/kimi-thinking-preview", "nano-gpt/kimi-thinking-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "kimi-thinking-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 31.46, "output": 31.46 } }, { "source": "litellm", "provider": "moonshot", "model": "moonshot/kimi-thinking-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Kimi Thinking Preview" ], "modes": [ "chat" ], "releaseDate": "2025-05-07", "lastUpdated": "2025-05-07", "deprecationDate": "2025-11-11", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "kimi-thinking-preview", "modelKey": "kimi-thinking-preview", "displayName": "Kimi Thinking Preview", "metadata": { "lastUpdated": "2025-05-07", "openWeights": false, "releaseDate": "2025-05-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/kimi-thinking-preview", "mode": "chat", "metadata": { "deprecationDate": "2025-11-11", "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" } } ] }, { "id": "moonshotai/moonshot-v1-128k", "provider": "moonshotai", "model": "moonshot-v1-128k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-128k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-128k-0430", "provider": "moonshotai", "model": "moonshot-v1-128k-0430", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-128k-0430" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k-0430", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2024-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k-0430", "mode": "chat", "metadata": { "deprecationDate": "2024-04-30", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-128k-vision-preview", "provider": "moonshotai", "model": "moonshot-v1-128k-vision-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-128k-vision-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k-vision-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-128k-vision-preview", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-32k", "provider": "moonshotai", "model": "moonshot-v1-32k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-32k-0430", "provider": "moonshotai", "model": "moonshot-v1-32k-0430", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-32k-0430" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k-0430", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2024-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k-0430", "mode": "chat", "metadata": { "deprecationDate": "2024-04-30", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-32k-vision-preview", "provider": "moonshotai", "model": "moonshot-v1-32k-vision-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-32k-vision-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k-vision-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-32k-vision-preview", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-8k", "provider": "moonshotai", "model": "moonshot-v1-8k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-8k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-8k-0430", "provider": "moonshotai", "model": "moonshot-v1-8k-0430", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-8k-0430" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k-0430", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2024-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k-0430", "mode": "chat", "metadata": { "deprecationDate": "2024-04-30", "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-8k-vision-preview", "provider": "moonshotai", "model": "moonshot-v1-8k-vision-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-8k-vision-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k-vision-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-8k-vision-preview", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "moonshotai/moonshot-v1-auto", "provider": "moonshotai", "model": "moonshot-v1-auto", "mode": "chat", "sources": [ "litellm" ], "providers": [ "moonshot" ], "aliases": [ "moonshot/moonshot-v1-auto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "moonshot", "model": "moonshot/moonshot-v1-auto", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "moonshot", "model": "moonshot/moonshot-v1-auto", "mode": "chat", "metadata": { "source": "https://platform.moonshot.ai/docs/pricing" } } ] }, { "id": "morph/auto", "provider": "morph", "model": "auto", "displayName": "Auto", "family": "auto", "sources": [ "models.dev" ], "providers": [ "morph" ], "aliases": [ "morph/auto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "morph", "model": "auto", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 1.55 } } ] }, "metadata": { "displayNames": [ "Auto" ], "families": [ "auto" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "morph", "providerName": "Morph", "providerApi": "https://api.morphllm.com/v1", "providerDoc": "https://docs.morphllm.com/api-reference/introduction", "model": "auto", "modelKey": "auto", "displayName": "Auto", "family": "auto", "metadata": { "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "morph/morph-v3-fast", "provider": "morph", "model": "morph-v3-fast", "displayName": "Morph v3 Fast", "family": "morph", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "morph" ], "aliases": [ "morph/morph-v3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": false, "transcription": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "morph", "model": "morph-v3-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.2 } }, { "source": "litellm", "provider": "morph", "model": "morph/morph-v3-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Morph v3 Fast" ], "families": [ "morph" ], "modes": [ "chat" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "morph", "providerName": "Morph", "providerApi": "https://api.morphllm.com/v1", "providerDoc": "https://docs.morphllm.com/api-reference/introduction", "model": "morph-v3-fast", "modelKey": "morph-v3-fast", "displayName": "Morph v3 Fast", "family": "morph", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "morph", "model": "morph/morph-v3-fast", "mode": "chat" } ] }, { "id": "morph/morph-v3-large", "provider": "morph", "model": "morph-v3-large", "displayName": "Morph v3 Large", "family": "morph", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "morph" ], "aliases": [ "morph/morph-v3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 16000, "maxTokens": 16000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": false, "transcription": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "morph", "model": "morph-v3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 1.9 } }, { "source": "litellm", "provider": "morph", "model": "morph/morph-v3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Morph v3 Large" ], "families": [ "morph" ], "modes": [ "chat" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "morph", "providerName": "Morph", "providerApi": "https://api.morphllm.com/v1", "providerDoc": "https://docs.morphllm.com/api-reference/introduction", "model": "morph-v3-large", "modelKey": "morph-v3-large", "displayName": "Morph v3 Large", "family": "morph", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "morph", "model": "morph/morph-v3-large", "mode": "chat" } ] }, { "id": "nano-gpt/aion-1.0", "provider": "nano-gpt", "model": "aion-1.0", "displayName": "Aion 1.0", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/aion-labs/aion-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "aion-labs/aion-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.995, "output": 7.99 } } ] }, "metadata": { "displayNames": [ "Aion 1.0" ], "families": [ "llama" ], "releaseDate": "2025-02-01", "lastUpdated": "2025-02-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "aion-labs/aion-1.0", "modelKey": "aion-labs/aion-1.0", "displayName": "Aion 1.0", "family": "llama", "metadata": { "lastUpdated": "2025-02-01", "openWeights": false, "releaseDate": "2025-02-01" } } ] }, { "id": "nano-gpt/aion-1.0-mini", "provider": "nano-gpt", "model": "aion-1.0-mini", "displayName": "Aion 1.0 mini (DeepSeek)", "family": "deepseek", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/aion-labs/aion-1.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "aion-labs/aion-1.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7989999999999999, "output": 1.394 } } ] }, "metadata": { "displayNames": [ "Aion 1.0 mini (DeepSeek)" ], "families": [ "deepseek" ], "releaseDate": "2025-02-20", "lastUpdated": "2025-02-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "aion-labs/aion-1.0-mini", "modelKey": "aion-labs/aion-1.0-mini", "displayName": "Aion 1.0 mini (DeepSeek)", "family": "deepseek", "metadata": { "lastUpdated": "2025-02-20", "openWeights": false, "releaseDate": "2025-02-20" } } ] }, { "id": "nano-gpt/aion-2.0", "provider": "nano-gpt", "model": "aion-2.0", "displayName": "AionLabs: Aion-2.0", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/aion-labs/aion-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "aion-labs/aion-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-2.0" ], "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "aion-labs/aion-2.0", "modelKey": "aion-labs/aion-2.0", "displayName": "AionLabs: Aion-2.0", "metadata": { "lastUpdated": "2026-02-23", "openWeights": false, "releaseDate": "2026-02-23" } } ] }, { "id": "nano-gpt/aion-2.5", "provider": "nano-gpt", "model": "aion-2.5", "displayName": "AionLabs: Aion-2.5", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/aion-labs/aion-2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "aion-labs/aion-2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.35, "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "AionLabs: Aion-2.5" ], "releaseDate": "2026-03-20", "lastUpdated": "2026-03-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "aion-labs/aion-2.5", "modelKey": "aion-labs/aion-2.5", "displayName": "AionLabs: Aion-2.5", "metadata": { "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "nano-gpt/aion-rp-llama-3.1-8b", "provider": "nano-gpt", "model": "aion-rp-llama-3.1-8b", "displayName": "Llama 3.1 8b (uncensored)", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/aion-labs/aion-rp-llama-3.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "aion-labs/aion-rp-llama-3.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 8b (uncensored)" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "aion-labs/aion-rp-llama-3.1-8b", "modelKey": "aion-labs/aion-rp-llama-3.1-8b", "displayName": "Llama 3.1 8b (uncensored)", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "nano-gpt/amoral-gemma3-27b-v2", "provider": "nano-gpt", "model": "amoral-gemma3-27b-v2", "displayName": "Amoral Gemma3 27B v2", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/soob3123/amoral-gemma3-27B-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "soob3123/amoral-gemma3-27B-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Amoral Gemma3 27B v2" ], "families": [ "gemma" ], "releaseDate": "2025-05-23", "lastUpdated": "2025-05-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "soob3123/amoral-gemma3-27B-v2", "modelKey": "soob3123/amoral-gemma3-27B-v2", "displayName": "Amoral Gemma3 27B v2", "family": "gemma", "metadata": { "lastUpdated": "2025-05-23", "openWeights": false, "releaseDate": "2025-05-23" } } ] }, { "id": "nano-gpt/anubis-70b-v1", "provider": "nano-gpt", "model": "anubis-70b-v1", "displayName": "Anubis 70B v1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Anubis-70B-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Anubis-70B-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.31, "output": 0.31 } } ] }, "metadata": { "displayNames": [ "Anubis 70B v1" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Anubis-70B-v1", "modelKey": "TheDrummer/Anubis-70B-v1", "displayName": "Anubis 70B v1", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/anubis-70b-v1.1", "provider": "nano-gpt", "model": "anubis-70b-v1.1", "displayName": "Anubis 70B v1.1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Anubis-70B-v1.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Anubis-70B-v1.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.31, "output": 0.31 } } ] }, "metadata": { "displayNames": [ "Anubis 70B v1.1" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Anubis-70B-v1.1", "modelKey": "TheDrummer/Anubis-70B-v1.1", "displayName": "Anubis 70B v1.1", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/asi1-mini", "provider": "nano-gpt", "model": "asi1-mini", "displayName": "ASI1 Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/asi1-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "asi1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "ASI1 Mini" ], "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "asi1-mini", "modelKey": "asi1-mini", "displayName": "ASI1 Mini", "metadata": { "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "nano-gpt/auto-model", "provider": "nano-gpt", "model": "auto-model", "displayName": "Auto model", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/auto-model" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "auto-model", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Auto model" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "auto-model", "modelKey": "auto-model", "displayName": "Auto model", "metadata": { "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "nano-gpt/auto-model-basic", "provider": "nano-gpt", "model": "auto-model-basic", "displayName": "Auto model (Basic)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/auto-model-basic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "auto-model-basic", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } } ] }, "metadata": { "displayNames": [ "Auto model (Basic)" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "auto-model-basic", "modelKey": "auto-model-basic", "displayName": "Auto model (Basic)", "metadata": { "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "nano-gpt/auto-model-premium", "provider": "nano-gpt", "model": "auto-model-premium", "displayName": "Auto model (Premium)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/auto-model-premium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "auto-model-premium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } } ] }, "metadata": { "displayNames": [ "Auto model (Premium)" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "auto-model-premium", "modelKey": "auto-model-premium", "displayName": "Auto model (Premium)", "metadata": { "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "nano-gpt/auto-model-standard", "provider": "nano-gpt", "model": "auto-model-standard", "displayName": "Auto model (Standard)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/auto-model-standard" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "auto-model-standard", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } } ] }, "metadata": { "displayNames": [ "Auto model (Standard)" ], "releaseDate": "2024-06-01", "lastUpdated": "2024-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "auto-model-standard", "modelKey": "auto-model-standard", "displayName": "Auto model (Standard)", "metadata": { "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } } ] }, { "id": "nano-gpt/azure-gpt-4-turbo", "provider": "nano-gpt", "model": "azure-gpt-4-turbo", "displayName": "Azure gpt-4-turbo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/azure-gpt-4-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "azure-gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 30.005 } } ] }, "metadata": { "displayNames": [ "Azure gpt-4-turbo" ], "releaseDate": "2023-11-06", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "azure-gpt-4-turbo", "modelKey": "azure-gpt-4-turbo", "displayName": "Azure gpt-4-turbo", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-11-06" } } ] }, { "id": "nano-gpt/azure-gpt-4o", "provider": "nano-gpt", "model": "azure-gpt-4o", "displayName": "Azure gpt-4o", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/azure-gpt-4o" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "azure-gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 9.996 } } ] }, "metadata": { "displayNames": [ "Azure gpt-4o" ], "releaseDate": "2024-05-13", "lastUpdated": "2024-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "azure-gpt-4o", "modelKey": "azure-gpt-4o", "displayName": "Azure gpt-4o", "metadata": { "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } } ] }, { "id": "nano-gpt/azure-gpt-4o-mini", "provider": "nano-gpt", "model": "azure-gpt-4o-mini", "displayName": "Azure gpt-4o-mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/azure-gpt-4o-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "azure-gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1496, "output": 0.595 } } ] }, "metadata": { "displayNames": [ "Azure gpt-4o-mini" ], "releaseDate": "2024-07-18", "lastUpdated": "2024-07-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "azure-gpt-4o-mini", "modelKey": "azure-gpt-4o-mini", "displayName": "Azure gpt-4o-mini", "metadata": { "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } } ] }, { "id": "nano-gpt/azure-o1", "provider": "nano-gpt", "model": "azure-o1", "displayName": "Azure o1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/azure-o1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "azure-o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 59.993 } } ] }, "metadata": { "displayNames": [ "Azure o1" ], "releaseDate": "2024-12-17", "lastUpdated": "2024-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "azure-o1", "modelKey": "azure-o1", "displayName": "Azure o1", "metadata": { "lastUpdated": "2024-12-17", "openWeights": false, "releaseDate": "2024-12-17" } } ] }, { "id": "nano-gpt/azure-o3-mini", "provider": "nano-gpt", "model": "azure-o3-mini", "displayName": "Azure o3-mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/azure-o3-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "azure-o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.088, "output": 4.3996 } } ] }, "metadata": { "displayNames": [ "Azure o3-mini" ], "releaseDate": "2025-01-31", "lastUpdated": "2025-01-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "azure-o3-mini", "modelKey": "azure-o3-mini", "displayName": "Azure o3-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } } ] }, { "id": "nano-gpt/baichuan-m2", "provider": "nano-gpt", "model": "baichuan-m2", "displayName": "Baichuan M2 32B Medical", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Baichuan-M2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Baichuan-M2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15.73, "output": 15.73 } } ] }, "metadata": { "displayNames": [ "Baichuan M2 32B Medical" ], "releaseDate": "2025-08-19", "lastUpdated": "2025-08-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Baichuan-M2", "modelKey": "Baichuan-M2", "displayName": "Baichuan M2 32B Medical", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } } ] }, { "id": "nano-gpt/baichuan4-air", "provider": "nano-gpt", "model": "baichuan4-air", "displayName": "Baichuan 4 Air", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Baichuan4-Air" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Baichuan4-Air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.157, "output": 0.157 } } ] }, "metadata": { "displayNames": [ "Baichuan 4 Air" ], "releaseDate": "2025-08-19", "lastUpdated": "2025-08-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Baichuan4-Air", "modelKey": "Baichuan4-Air", "displayName": "Baichuan 4 Air", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } } ] }, { "id": "nano-gpt/baichuan4-turbo", "provider": "nano-gpt", "model": "baichuan4-turbo", "displayName": "Baichuan 4 Turbo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Baichuan4-Turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Baichuan4-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.42, "output": 2.42 } } ] }, "metadata": { "displayNames": [ "Baichuan 4 Turbo" ], "releaseDate": "2025-08-19", "lastUpdated": "2025-08-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Baichuan4-Turbo", "modelKey": "Baichuan4-Turbo", "displayName": "Baichuan 4 Turbo", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } } ] }, { "id": "nano-gpt/brave", "provider": "nano-gpt", "model": "brave", "displayName": "Brave (Answers)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/brave" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "brave", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 5 } } ] }, "metadata": { "displayNames": [ "Brave (Answers)" ], "releaseDate": "2023-03-02", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "brave", "modelKey": "brave", "displayName": "Brave (Answers)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-03-02" } } ] }, { "id": "nano-gpt/brave-pro", "provider": "nano-gpt", "model": "brave-pro", "displayName": "Brave (Pro)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/brave-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "brave-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 5 } } ] }, "metadata": { "displayNames": [ "Brave (Pro)" ], "releaseDate": "2023-03-02", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "brave-pro", "modelKey": "brave-pro", "displayName": "Brave (Pro)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-03-02" } } ] }, { "id": "nano-gpt/brave-research", "provider": "nano-gpt", "model": "brave-research", "displayName": "Brave (Research)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/brave-research" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "brave-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 5 } } ] }, "metadata": { "displayNames": [ "Brave (Research)" ], "releaseDate": "2023-03-02", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "brave-research", "modelKey": "brave-research", "displayName": "Brave (Research)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-03-02" } } ] }, { "id": "nano-gpt/claw-high", "provider": "nano-gpt", "model": "claw-high", "displayName": "Claw High", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claw-high" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claw-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Claw High" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claw-high", "modelKey": "claw-high", "displayName": "Claw High", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/claw-low", "provider": "nano-gpt", "model": "claw-low", "displayName": "Claw Low", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claw-low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claw-low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Claw Low" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claw-low", "modelKey": "claw-low", "displayName": "Claw Low", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/claw-medium", "provider": "nano-gpt", "model": "claw-medium", "displayName": "Claw Medium", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/claw-medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "inputTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "claw-medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Claw Medium" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "claw-medium", "modelKey": "claw-medium", "displayName": "Claw Medium", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/coding-router", "provider": "nano-gpt", "model": "coding-router", "displayName": "Coding Router", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nanogpt/coding-router" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nanogpt/coding-router", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "Coding Router" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nanogpt/coding-router", "modelKey": "nanogpt/coding-router", "displayName": "Coding Router", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/coding-router:high", "provider": "nano-gpt", "model": "coding-router:high", "displayName": "Coding Router High", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nanogpt/coding-router:high" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nanogpt/coding-router:high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "Coding Router High" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nanogpt/coding-router:high", "modelKey": "nanogpt/coding-router:high", "displayName": "Coding Router High", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/coding-router:low", "provider": "nano-gpt", "model": "coding-router:low", "displayName": "Coding Router Low", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nanogpt/coding-router:low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nanogpt/coding-router:low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Coding Router Low" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nanogpt/coding-router:low", "modelKey": "nanogpt/coding-router:low", "displayName": "Coding Router Low", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/coding-router:max", "provider": "nano-gpt", "model": "coding-router:max", "displayName": "Coding Router Max", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nanogpt/coding-router:max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nanogpt/coding-router:max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } } ] }, "metadata": { "displayNames": [ "Coding Router Max" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nanogpt/coding-router:max", "modelKey": "nanogpt/coding-router:max", "displayName": "Coding Router Max", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/coding-router:medium", "provider": "nano-gpt", "model": "coding-router:medium", "displayName": "Coding Router Medium", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nanogpt/coding-router:medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nanogpt/coding-router:medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Coding Router Medium" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nanogpt/coding-router:medium", "modelKey": "nanogpt/coding-router:medium", "displayName": "Coding Router Medium", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/cogito-v1-preview-qwen-32b", "provider": "nano-gpt", "model": "cogito-v1-preview-qwen-32b", "displayName": "Cogito v1 Preview Qwen 32B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepcogito/cogito-v1-preview-qwen-32B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepcogito/cogito-v1-preview-qwen-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.7999999999999998, "output": 1.7999999999999998 } } ] }, "metadata": { "displayNames": [ "Cogito v1 Preview Qwen 32B" ], "families": [ "qwen" ], "releaseDate": "2025-05-10", "lastUpdated": "2025-05-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepcogito/cogito-v1-preview-qwen-32B", "modelKey": "deepcogito/cogito-v1-preview-qwen-32B", "displayName": "Cogito v1 Preview Qwen 32B", "family": "qwen", "metadata": { "lastUpdated": "2025-05-10", "openWeights": false, "releaseDate": "2025-05-10" } } ] }, { "id": "nano-gpt/cydonia-24b-v2", "provider": "nano-gpt", "model": "cydonia-24b-v2", "displayName": "The Drummer Cydonia 24B v2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Cydonia-24B-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Cydonia-24B-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1207 } } ] }, "metadata": { "displayNames": [ "The Drummer Cydonia 24B v2" ], "releaseDate": "2025-02-17", "lastUpdated": "2025-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Cydonia-24B-v2", "modelKey": "TheDrummer/Cydonia-24B-v2", "displayName": "The Drummer Cydonia 24B v2", "metadata": { "lastUpdated": "2025-02-17", "openWeights": false, "releaseDate": "2025-02-17" } } ] }, { "id": "nano-gpt/cydonia-24b-v4", "provider": "nano-gpt", "model": "cydonia-24b-v4", "displayName": "The Drummer Cydonia 24B v4", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Cydonia-24B-v4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Cydonia-24B-v4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2414 } } ] }, "metadata": { "displayNames": [ "The Drummer Cydonia 24B v4" ], "releaseDate": "2025-07-22", "lastUpdated": "2025-07-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Cydonia-24B-v4", "modelKey": "TheDrummer/Cydonia-24B-v4", "displayName": "The Drummer Cydonia 24B v4", "metadata": { "lastUpdated": "2025-07-22", "openWeights": false, "releaseDate": "2025-07-22" } } ] }, { "id": "nano-gpt/cydonia-24b-v4.1", "provider": "nano-gpt", "model": "cydonia-24b-v4.1", "displayName": "The Drummer Cydonia 24B v4.1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Cydonia-24B-v4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Cydonia-24B-v4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1207 } } ] }, "metadata": { "displayNames": [ "The Drummer Cydonia 24B v4.1" ], "releaseDate": "2025-08-19", "lastUpdated": "2025-08-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Cydonia-24B-v4.1", "modelKey": "TheDrummer/Cydonia-24B-v4.1", "displayName": "The Drummer Cydonia 24B v4.1", "metadata": { "lastUpdated": "2025-08-19", "openWeights": false, "releaseDate": "2025-08-19" } } ] }, { "id": "nano-gpt/cydonia-24b-v4.3", "provider": "nano-gpt", "model": "cydonia-24b-v4.3", "displayName": "The Drummer Cydonia 24B v4.3", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Cydonia-24B-v4.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Cydonia-24B-v4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1207 } } ] }, "metadata": { "displayNames": [ "The Drummer Cydonia 24B v4.3" ], "releaseDate": "2025-12-25", "lastUpdated": "2025-12-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Cydonia-24B-v4.3", "modelKey": "TheDrummer/Cydonia-24B-v4.3", "displayName": "The Drummer Cydonia 24B v4.3", "metadata": { "lastUpdated": "2025-12-25", "openWeights": false, "releaseDate": "2025-12-25" } } ] }, { "id": "nano-gpt/deepclaude", "provider": "nano-gpt", "model": "deepclaude", "displayName": "DeepClaude", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/deepclaude" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "deepclaude", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "DeepClaude" ], "releaseDate": "2025-02-01", "lastUpdated": "2025-02-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "deepclaude", "modelKey": "deepclaude", "displayName": "DeepClaude", "metadata": { "lastUpdated": "2025-02-01", "openWeights": false, "releaseDate": "2025-02-01" } } ] }, { "id": "nano-gpt/deephermes-3-mistral-24b-preview", "provider": "nano-gpt", "model": "deephermes-3-mistral-24b-preview", "displayName": "DeepHermes-3 Mistral 24B (Preview)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/DeepHermes-3-Mistral-24B-Preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "DeepHermes-3 Mistral 24B (Preview)" ], "releaseDate": "2025-05-10", "lastUpdated": "2025-05-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "modelKey": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "displayName": "DeepHermes-3 Mistral 24B (Preview)", "metadata": { "lastUpdated": "2025-05-10", "openWeights": false, "releaseDate": "2025-05-10" } } ] }, { "id": "nano-gpt/dmind-1", "provider": "nano-gpt", "model": "dmind-1", "displayName": "DMind-1", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/dmind/dmind-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "dmind/dmind-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "DMind-1" ], "families": [ "gpt" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "dmind/dmind-1", "modelKey": "dmind/dmind-1", "displayName": "DMind-1", "family": "gpt", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "nano-gpt/dmind-1-mini", "provider": "nano-gpt", "model": "dmind-1-mini", "displayName": "DMind-1-Mini", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/dmind/dmind-1-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "dmind/dmind-1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "DMind-1-Mini" ], "families": [ "gpt" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "dmind/dmind-1-mini", "modelKey": "dmind/dmind-1-mini", "displayName": "DMind-1-Mini", "family": "gpt", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "nano-gpt/dolphin-2.9.2-qwen2-72b", "provider": "nano-gpt", "model": "dolphin-2.9.2-qwen2-72b", "displayName": "Dolphin 72b", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/cognitivecomputations/dolphin-2.9.2-qwen2-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "cognitivecomputations/dolphin-2.9.2-qwen2-72b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Dolphin 72b" ], "families": [ "qwen" ], "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "cognitivecomputations/dolphin-2.9.2-qwen2-72b", "modelKey": "cognitivecomputations/dolphin-2.9.2-qwen2-72b", "displayName": "Dolphin 72b", "family": "qwen", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } } ] }, { "id": "nano-gpt/doubao-1-5-thinking-pro-250415", "provider": "nano-gpt", "model": "doubao-1-5-thinking-pro-250415", "displayName": "Doubao 1.5 Thinking Pro", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1-5-thinking-pro-250415" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1-5-thinking-pro-250415", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Thinking Pro" ], "releaseDate": "2025-04-17", "lastUpdated": "2025-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1-5-thinking-pro-250415", "modelKey": "doubao-1-5-thinking-pro-250415", "displayName": "Doubao 1.5 Thinking Pro", "metadata": { "lastUpdated": "2025-04-17", "openWeights": false, "releaseDate": "2025-04-17" } } ] }, { "id": "nano-gpt/doubao-1-5-thinking-pro-vision-250415", "provider": "nano-gpt", "model": "doubao-1-5-thinking-pro-vision-250415", "displayName": "Doubao 1.5 Thinking Pro Vision", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1-5-thinking-pro-vision-250415" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1-5-thinking-pro-vision-250415", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Thinking Pro Vision" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1-5-thinking-pro-vision-250415", "modelKey": "doubao-1-5-thinking-pro-vision-250415", "displayName": "Doubao 1.5 Thinking Pro Vision", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "nano-gpt/doubao-1-5-thinking-vision-pro-250428", "provider": "nano-gpt", "model": "doubao-1-5-thinking-vision-pro-250428", "displayName": "Doubao 1.5 Thinking Vision Pro", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1-5-thinking-vision-pro-250428" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1-5-thinking-vision-pro-250428", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 1.43 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Thinking Vision Pro" ], "releaseDate": "2025-05-15", "lastUpdated": "2025-05-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1-5-thinking-vision-pro-250428", "modelKey": "doubao-1-5-thinking-vision-pro-250428", "displayName": "Doubao 1.5 Thinking Vision Pro", "metadata": { "lastUpdated": "2025-05-15", "openWeights": false, "releaseDate": "2025-05-15" } } ] }, { "id": "nano-gpt/doubao-1.5-pro-256k", "provider": "nano-gpt", "model": "doubao-1.5-pro-256k", "displayName": "Doubao 1.5 Pro 256k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1.5-pro-256k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1.5-pro-256k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.799, "output": 1.445 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Pro 256k" ], "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1.5-pro-256k", "modelKey": "doubao-1.5-pro-256k", "displayName": "Doubao 1.5 Pro 256k", "metadata": { "lastUpdated": "2025-03-12", "openWeights": false, "releaseDate": "2025-03-12" } } ] }, { "id": "nano-gpt/doubao-1.5-pro-32k", "provider": "nano-gpt", "model": "doubao-1.5-pro-32k", "displayName": "Doubao 1.5 Pro 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1.5-pro-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1.5-pro-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1343, "output": 0.3349 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Pro 32k" ], "releaseDate": "2025-01-22", "lastUpdated": "2025-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1.5-pro-32k", "modelKey": "doubao-1.5-pro-32k", "displayName": "Doubao 1.5 Pro 32k", "metadata": { "lastUpdated": "2025-01-22", "openWeights": false, "releaseDate": "2025-01-22" } } ] }, { "id": "nano-gpt/doubao-1.5-vision-pro-32k", "provider": "nano-gpt", "model": "doubao-1.5-vision-pro-32k", "displayName": "Doubao 1.5 Vision Pro 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-1.5-vision-pro-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-1.5-vision-pro-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.459, "output": 1.377 } } ] }, "metadata": { "displayNames": [ "Doubao 1.5 Vision Pro 32k" ], "releaseDate": "2025-01-22", "lastUpdated": "2025-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-1.5-vision-pro-32k", "modelKey": "doubao-1.5-vision-pro-32k", "displayName": "Doubao 1.5 Vision Pro 32k", "metadata": { "lastUpdated": "2025-01-22", "openWeights": false, "releaseDate": "2025-01-22" } } ] }, { "id": "nano-gpt/doubao-seed-1-6-250615", "provider": "nano-gpt", "model": "doubao-seed-1-6-250615", "displayName": "Doubao Seed 1.6", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-1-6-250615" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-1-6-250615", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.204, "output": 0.51 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 1.6" ], "releaseDate": "2025-06-15", "lastUpdated": "2025-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-1-6-250615", "modelKey": "doubao-seed-1-6-250615", "displayName": "Doubao Seed 1.6", "metadata": { "lastUpdated": "2025-06-15", "openWeights": false, "releaseDate": "2025-06-15" } } ] }, { "id": "nano-gpt/doubao-seed-1-6-flash-250615", "provider": "nano-gpt", "model": "doubao-seed-1-6-flash-250615", "displayName": "Doubao Seed 1.6 Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-1-6-flash-250615" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-1-6-flash-250615", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0374, "output": 0.374 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 1.6 Flash" ], "releaseDate": "2025-06-15", "lastUpdated": "2025-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-1-6-flash-250615", "modelKey": "doubao-seed-1-6-flash-250615", "displayName": "Doubao Seed 1.6 Flash", "metadata": { "lastUpdated": "2025-06-15", "openWeights": false, "releaseDate": "2025-06-15" } } ] }, { "id": "nano-gpt/doubao-seed-1-6-thinking-250615", "provider": "nano-gpt", "model": "doubao-seed-1-6-thinking-250615", "displayName": "Doubao Seed 1.6 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-1-6-thinking-250615" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-1-6-thinking-250615", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.204, "output": 2.04 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 1.6 Thinking" ], "releaseDate": "2025-06-15", "lastUpdated": "2025-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-1-6-thinking-250615", "modelKey": "doubao-seed-1-6-thinking-250615", "displayName": "Doubao Seed 1.6 Thinking", "metadata": { "lastUpdated": "2025-06-15", "openWeights": false, "releaseDate": "2025-06-15" } } ] }, { "id": "nano-gpt/doubao-seed-1-8-251215", "provider": "nano-gpt", "model": "doubao-seed-1-8-251215", "displayName": "Doubao Seed 1.8", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-1-8-251215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-1-8-251215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.612, "output": 6.12 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 1.8" ], "releaseDate": "2025-12-15", "lastUpdated": "2025-12-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-1-8-251215", "modelKey": "doubao-seed-1-8-251215", "displayName": "Doubao Seed 1.8", "metadata": { "lastUpdated": "2025-12-15", "openWeights": false, "releaseDate": "2025-12-15" } } ] }, { "id": "nano-gpt/doubao-seed-2-0-code-preview-260215", "provider": "nano-gpt", "model": "doubao-seed-2-0-code-preview-260215", "displayName": "Doubao Seed 2.0 Code Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-2-0-code-preview-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-2-0-code-preview-260215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.782, "output": 3.893 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Code Preview" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-2-0-code-preview-260215", "modelKey": "doubao-seed-2-0-code-preview-260215", "displayName": "Doubao Seed 2.0 Code Preview", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "nano-gpt/doubao-seed-2-0-lite-260215", "provider": "nano-gpt", "model": "doubao-seed-2-0-lite-260215", "displayName": "Doubao Seed 2.0 Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-2-0-lite-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-2-0-lite-260215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1462, "output": 0.8738 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Lite" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-2-0-lite-260215", "modelKey": "doubao-seed-2-0-lite-260215", "displayName": "Doubao Seed 2.0 Lite", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "nano-gpt/doubao-seed-2-0-mini-260215", "provider": "nano-gpt", "model": "doubao-seed-2-0-mini-260215", "displayName": "Doubao Seed 2.0 Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-2-0-mini-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-2-0-mini-260215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0493, "output": 0.4845 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Mini" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-2-0-mini-260215", "modelKey": "doubao-seed-2-0-mini-260215", "displayName": "Doubao Seed 2.0 Mini", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "nano-gpt/doubao-seed-2-0-pro-260215", "provider": "nano-gpt", "model": "doubao-seed-2-0-pro-260215", "displayName": "Doubao Seed 2.0 Pro", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/doubao-seed-2-0-pro-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "doubao-seed-2-0-pro-260215", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.782, "output": 3.876 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Pro" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "doubao-seed-2-0-pro-260215", "modelKey": "doubao-seed-2-0-pro-260215", "displayName": "Doubao Seed 2.0 Pro", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "nano-gpt/dracarys-72b-instruct", "provider": "nano-gpt", "model": "dracarys-72b-instruct", "displayName": "Llama 3.1 70B Dracarys 2", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/abacusai/Dracarys-72B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "abacusai/Dracarys-72B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Dracarys 2" ], "families": [ "llama" ], "releaseDate": "2025-08-02", "lastUpdated": "2025-08-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "abacusai/Dracarys-72B-Instruct", "modelKey": "abacusai/Dracarys-72B-Instruct", "displayName": "Llama 3.1 70B Dracarys 2", "family": "llama", "metadata": { "lastUpdated": "2025-08-02", "openWeights": false, "releaseDate": "2025-08-02" } } ] }, { "id": "nano-gpt/ernie-4.5-8k-preview", "provider": "nano-gpt", "model": "ernie-4.5-8k-preview", "displayName": "Ernie 4.5 8k Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-4.5-8k-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-4.5-8k-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.66, "output": 2.6 } } ] }, "metadata": { "displayNames": [ "Ernie 4.5 8k Preview" ], "releaseDate": "2025-03-25", "lastUpdated": "2025-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-4.5-8k-preview", "modelKey": "ernie-4.5-8k-preview", "displayName": "Ernie 4.5 8k Preview", "metadata": { "lastUpdated": "2025-03-25", "openWeights": false, "releaseDate": "2025-03-25" } } ] }, { "id": "nano-gpt/ernie-4.5-turbo-128k", "provider": "nano-gpt", "model": "ernie-4.5-turbo-128k", "displayName": "Ernie 4.5 Turbo 128k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-4.5-turbo-128k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-4.5-turbo-128k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.132, "output": 0.55 } } ] }, "metadata": { "displayNames": [ "Ernie 4.5 Turbo 128k" ], "releaseDate": "2025-05-08", "lastUpdated": "2025-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-4.5-turbo-128k", "modelKey": "ernie-4.5-turbo-128k", "displayName": "Ernie 4.5 Turbo 128k", "metadata": { "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } } ] }, { "id": "nano-gpt/ernie-4.5-turbo-vl-32k", "provider": "nano-gpt", "model": "ernie-4.5-turbo-vl-32k", "displayName": "Ernie 4.5 Turbo VL 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-4.5-turbo-vl-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-4.5-turbo-vl-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.495, "output": 1.43 } } ] }, "metadata": { "displayNames": [ "Ernie 4.5 Turbo VL 32k" ], "releaseDate": "2025-05-08", "lastUpdated": "2025-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-4.5-turbo-vl-32k", "modelKey": "ernie-4.5-turbo-vl-32k", "displayName": "Ernie 4.5 Turbo VL 32k", "metadata": { "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } } ] }, { "id": "nano-gpt/ernie-4.5-vl-28b-a3b", "provider": "nano-gpt", "model": "ernie-4.5-vl-28b-a3b", "displayName": "ERNIE 4.5 VL 28B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/baidu/ernie-4.5-vl-28b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "baidu/ernie-4.5-vl-28b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13999999999999999, "output": 0.5599999999999999 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 VL 28B" ], "families": [ "ernie" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "baidu/ernie-4.5-vl-28b-a3b", "modelKey": "baidu/ernie-4.5-vl-28b-a3b", "displayName": "ERNIE 4.5 VL 28B", "family": "ernie", "metadata": { "lastUpdated": "2025-06-30", "openWeights": false, "releaseDate": "2025-06-30" } } ] }, { "id": "nano-gpt/ernie-5.0-thinking-preview", "provider": "nano-gpt", "model": "ernie-5.0-thinking-preview", "displayName": "Ernie 5.0 Thinking Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-5.0-thinking-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-5.0-thinking-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 2 } } ] }, "metadata": { "displayNames": [ "Ernie 5.0 Thinking Preview" ], "releaseDate": "2025-11-18", "lastUpdated": "2025-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-5.0-thinking-preview", "modelKey": "ernie-5.0-thinking-preview", "displayName": "Ernie 5.0 Thinking Preview", "metadata": { "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } } ] }, { "id": "nano-gpt/ernie-5.1", "provider": "nano-gpt", "model": "ernie-5.1", "displayName": "ERNIE 5.1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 119000, "inputTokens": 119000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 0.75, "output": 3 } } ] }, "metadata": { "displayNames": [ "ERNIE 5.1" ], "releaseDate": "2026-05-10", "lastUpdated": "2026-05-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-5.1", "modelKey": "ernie-5.1", "displayName": "ERNIE 5.1", "metadata": { "lastUpdated": "2026-05-10", "openWeights": false, "releaseDate": "2026-05-10" } } ] }, { "id": "nano-gpt/ernie-5.1:thinking", "provider": "nano-gpt", "model": "ernie-5.1:thinking", "displayName": "ERNIE 5.1 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-5.1:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 119000, "inputTokens": 119000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-5.1:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 0.75, "output": 3 } } ] }, "metadata": { "displayNames": [ "ERNIE 5.1 Thinking" ], "releaseDate": "2026-05-10", "lastUpdated": "2026-05-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-5.1:thinking", "modelKey": "ernie-5.1:thinking", "displayName": "ERNIE 5.1 Thinking", "metadata": { "lastUpdated": "2026-05-10", "openWeights": false, "releaseDate": "2026-05-10" } } ] }, { "id": "nano-gpt/ernie-x1-32k", "provider": "nano-gpt", "model": "ernie-x1-32k", "displayName": "Ernie X1 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-x1-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-x1-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 1.32 } } ] }, "metadata": { "displayNames": [ "Ernie X1 32k" ], "releaseDate": "2025-05-08", "lastUpdated": "2025-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-x1-32k", "modelKey": "ernie-x1-32k", "displayName": "Ernie X1 32k", "metadata": { "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } } ] }, { "id": "nano-gpt/ernie-x1-32k-preview", "provider": "nano-gpt", "model": "ernie-x1-32k-preview", "displayName": "Ernie X1 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-x1-32k-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-x1-32k-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.33, "output": 1.32 } } ] }, "metadata": { "displayNames": [ "Ernie X1 32k" ], "releaseDate": "2025-04-03", "lastUpdated": "2025-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-x1-32k-preview", "modelKey": "ernie-x1-32k-preview", "displayName": "Ernie X1 32k", "metadata": { "lastUpdated": "2025-04-03", "openWeights": false, "releaseDate": "2025-04-03" } } ] }, { "id": "nano-gpt/ernie-x1-turbo-32k", "provider": "nano-gpt", "model": "ernie-x1-turbo-32k", "displayName": "Ernie X1 Turbo 32k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-x1-turbo-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-x1-turbo-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.165, "output": 0.66 } } ] }, "metadata": { "displayNames": [ "Ernie X1 Turbo 32k" ], "releaseDate": "2025-05-08", "lastUpdated": "2025-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-x1-turbo-32k", "modelKey": "ernie-x1-turbo-32k", "displayName": "Ernie X1 Turbo 32k", "metadata": { "lastUpdated": "2025-05-08", "openWeights": false, "releaseDate": "2025-05-08" } } ] }, { "id": "nano-gpt/ernie-x1.1-preview", "provider": "nano-gpt", "model": "ernie-x1.1-preview", "displayName": "ERNIE X1.1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ernie-x1.1-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ernie-x1.1-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "ERNIE X1.1" ], "releaseDate": "2025-09-10", "lastUpdated": "2025-09-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ernie-x1.1-preview", "modelKey": "ernie-x1.1-preview", "displayName": "ERNIE X1.1", "metadata": { "lastUpdated": "2025-09-10", "openWeights": false, "releaseDate": "2025-09-10" } } ] }, { "id": "nano-gpt/eva-llama-3.33-70b-v0.0", "provider": "nano-gpt", "model": "eva-llama-3.33-70b-v0.0", "displayName": "EVA Llama 3.33 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 2.006 } } ] }, "metadata": { "displayNames": [ "EVA Llama 3.33 70B" ], "families": [ "llama" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0", "modelKey": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0", "displayName": "EVA Llama 3.33 70B", "family": "llama", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/eva-llama-3.33-70b-v0.1", "provider": "nano-gpt", "model": "eva-llama-3.33-70b-v0.1", "displayName": "EVA-LLaMA-3.33-70B-v0.1", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 2.006 } } ] }, "metadata": { "displayNames": [ "EVA-LLaMA-3.33-70B-v0.1" ], "families": [ "llama" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1", "modelKey": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1", "displayName": "EVA-LLaMA-3.33-70B-v0.1", "family": "llama", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "nano-gpt/eva-qwen2.5-32b-v0.2", "provider": "nano-gpt", "model": "eva-qwen2.5-32b-v0.2", "displayName": "EVA-Qwen2.5-32B-v0.2", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7989999999999999, "output": 0.7989999999999999 } } ] }, "metadata": { "displayNames": [ "EVA-Qwen2.5-32B-v0.2" ], "families": [ "qwen" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "modelKey": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "displayName": "EVA-Qwen2.5-32B-v0.2", "family": "qwen", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/eva-qwen2.5-72b-v0.2", "provider": "nano-gpt", "model": "eva-qwen2.5-72b-v0.2", "displayName": "EVA-Qwen2.5-72B-v0.2", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7989999999999999, "output": 0.7989999999999999 } } ] }, "metadata": { "displayNames": [ "EVA-Qwen2.5-72B-v0.2" ], "families": [ "qwen" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2", "modelKey": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2", "displayName": "EVA-Qwen2.5-72B-v0.2", "family": "qwen", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "nano-gpt/exa-answer", "provider": "nano-gpt", "model": "exa-answer", "displayName": "Exa (Answer)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/exa-answer" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "exa-answer", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Exa (Answer)" ], "releaseDate": "2025-06-04", "lastUpdated": "2025-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "exa-answer", "modelKey": "exa-answer", "displayName": "Exa (Answer)", "metadata": { "lastUpdated": "2025-06-04", "openWeights": false, "releaseDate": "2025-06-04" } } ] }, { "id": "nano-gpt/exa-research", "provider": "nano-gpt", "model": "exa-research", "displayName": "Exa (Research)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/exa-research" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "exa-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Exa (Research)" ], "releaseDate": "2025-06-04", "lastUpdated": "2025-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "exa-research", "modelKey": "exa-research", "displayName": "Exa (Research)", "metadata": { "lastUpdated": "2025-06-04", "openWeights": false, "releaseDate": "2025-06-04" } } ] }, { "id": "nano-gpt/exa-research-pro", "provider": "nano-gpt", "model": "exa-research-pro", "displayName": "Exa (Research Pro)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/exa-research-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "exa-research-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Exa (Research Pro)" ], "releaseDate": "2025-06-04", "lastUpdated": "2025-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "exa-research-pro", "modelKey": "exa-research-pro", "displayName": "Exa (Research Pro)", "metadata": { "lastUpdated": "2025-06-04", "openWeights": false, "releaseDate": "2025-06-04" } } ] }, { "id": "nano-gpt/fastgpt", "provider": "nano-gpt", "model": "fastgpt", "displayName": "Web Answer", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/fastgpt" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "fastgpt", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 7.5, "output": 7.5 } } ] }, "metadata": { "displayNames": [ "Web Answer" ], "releaseDate": "2023-08-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "fastgpt", "modelKey": "fastgpt", "displayName": "Web Answer", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-08-01" } } ] }, { "id": "nano-gpt/gemma-3-12b-it", "provider": "nano-gpt", "model": "gemma-3-12b-it", "displayName": "Gemma 3 12B IT", "family": "unsloth", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/unsloth/gemma-3-12b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "unsloth/gemma-3-12b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.272, "output": 0.272 } } ] }, "metadata": { "displayNames": [ "Gemma 3 12B IT" ], "families": [ "unsloth" ], "releaseDate": "2025-03-10", "lastUpdated": "2025-03-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "unsloth/gemma-3-12b-it", "modelKey": "unsloth/gemma-3-12b-it", "displayName": "Gemma 3 12B IT", "family": "unsloth", "metadata": { "lastUpdated": "2025-03-10", "openWeights": false, "releaseDate": "2025-03-10" } } ] }, { "id": "nano-gpt/gemma-3-27b-it", "provider": "nano-gpt", "model": "gemma-3-27b-it", "displayName": "Gemma 3 27B TEE", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/gemma-3-27b-it", "nano-gpt/unsloth/gemma-3-27b-it" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "unsloth/gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2992, "output": 0.2992 } } ] }, "metadata": { "displayNames": [ "Gemma 3 27B IT", "Gemma 3 27B TEE" ], "families": [ "gemma", "unsloth" ], "releaseDate": "2025-03-10", "lastUpdated": "2025-03-10", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gemma-3-27b-it", "modelKey": "TEE/gemma-3-27b-it", "displayName": "Gemma 3 27B TEE", "family": "gemma", "metadata": { "lastUpdated": "2025-03-10", "openWeights": false, "releaseDate": "2025-03-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "unsloth/gemma-3-27b-it", "modelKey": "unsloth/gemma-3-27b-it", "displayName": "Gemma 3 27B IT", "family": "unsloth", "metadata": { "lastUpdated": "2025-03-10", "openWeights": false, "releaseDate": "2025-03-10" } } ] }, { "id": "nano-gpt/gemma-3-4b-it", "provider": "nano-gpt", "model": "gemma-3-4b-it", "displayName": "Gemma 3 4B IT", "family": "unsloth", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/unsloth/gemma-3-4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "unsloth/gemma-3-4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "Gemma 3 4B IT" ], "families": [ "unsloth" ], "releaseDate": "2025-03-10", "lastUpdated": "2025-03-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "unsloth/gemma-3-4b-it", "modelKey": "unsloth/gemma-3-4b-it", "displayName": "Gemma 3 4B IT", "family": "unsloth", "metadata": { "lastUpdated": "2025-03-10", "openWeights": false, "releaseDate": "2025-03-10" } } ] }, { "id": "nano-gpt/gemma-4-26b-a4b-uncensored", "provider": "nano-gpt", "model": "gemma-4-26b-a4b-uncensored", "displayName": "Gemma 4 26B A4B Uncensored TEE", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/gemma-4-26b-a4b-uncensored" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gemma-4-26b-a4b-uncensored", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Gemma 4 26B A4B Uncensored TEE" ], "releaseDate": "2026-05-23", "lastUpdated": "2026-05-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gemma-4-26b-a4b-uncensored", "modelKey": "TEE/gemma-4-26b-a4b-uncensored", "displayName": "Gemma 4 26B A4B Uncensored TEE", "metadata": { "lastUpdated": "2026-05-23", "openWeights": false, "releaseDate": "2026-05-23" } } ] }, { "id": "nano-gpt/gemma-4-31b-claude-4.6-opus-reasoning-distilled", "provider": "nano-gpt", "model": "gemma-4-31b-claude-4.6-opus-reasoning-distilled", "displayName": "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0306, "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled", "modelKey": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled", "displayName": "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-cognitive-unshackled", "provider": "nano-gpt", "model": "gemma-4-31b-cognitive-unshackled", "displayName": "Gemma 4 31B Cognitive Unshackled", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-Cognitive-Unshackled" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-Cognitive-Unshackled", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Cognitive Unshackled" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-Cognitive-Unshackled", "modelKey": "Gemma-4-31B-Cognitive-Unshackled", "displayName": "Gemma 4 31B Cognitive Unshackled", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-darkidol", "provider": "nano-gpt", "model": "gemma-4-31b-darkidol", "displayName": "Gemma 4 31B DarkIdol", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-DarkIdol" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-DarkIdol", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B DarkIdol" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-DarkIdol", "modelKey": "Gemma-4-31B-DarkIdol", "displayName": "Gemma 4 31B DarkIdol", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-fabled", "provider": "nano-gpt", "model": "gemma-4-31b-fabled", "displayName": "Gemma 4 31B Fabled", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemma-4-31B-Fabled" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemma-4-31B-Fabled", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Fabled" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemma-4-31B-Fabled", "modelKey": "gemma-4-31B-Fabled", "displayName": "Gemma 4 31B Fabled", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/gemma-4-31b-garnet", "provider": "nano-gpt", "model": "gemma-4-31b-garnet", "displayName": "Gemma 4 31B Garnet", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemma-4-31B-Garnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemma-4-31B-Garnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Garnet" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemma-4-31B-Garnet", "modelKey": "gemma-4-31B-Garnet", "displayName": "Gemma 4 31B Garnet", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/gemma-4-31b-garnetv2", "provider": "nano-gpt", "model": "gemma-4-31b-garnetv2", "displayName": "Gemma 4 31B Garnet V2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-GarnetV2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-GarnetV2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Garnet V2" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-GarnetV2", "modelKey": "Gemma-4-31B-GarnetV2", "displayName": "Gemma 4 31B Garnet V2", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-gemopus", "provider": "nano-gpt", "model": "gemma-4-31b-gemopus", "displayName": "Gemma 4 31B Gemopus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-Gemopus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-Gemopus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Gemopus" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-Gemopus", "modelKey": "Gemma-4-31B-Gemopus", "displayName": "Gemma 4 31B Gemopus", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-it", "provider": "nano-gpt", "model": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-it", "nano-gpt/TEE/gemma-4-31b-it" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.46 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B IT", "Gemma 4 31B IT TEE" ], "releaseDate": "2026-04-09", "lastUpdated": "2026-04-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-it", "modelKey": "Gemma-4-31B-it", "displayName": "Gemma 4 31B IT", "metadata": { "lastUpdated": "2026-04-09", "openWeights": false, "releaseDate": "2026-04-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gemma-4-31b-it", "modelKey": "TEE/gemma-4-31b-it", "displayName": "Gemma 4 31B IT TEE", "metadata": { "lastUpdated": "2026-05-26", "openWeights": false, "releaseDate": "2026-05-26" } } ] }, { "id": "nano-gpt/gemma-4-31b-k1-v5", "provider": "nano-gpt", "model": "gemma-4-31b-k1-v5", "displayName": "Gemma 4 31B K1 v5", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemma-4-31B-K1-v5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemma-4-31B-K1-v5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B K1 v5" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemma-4-31B-K1-v5", "modelKey": "gemma-4-31B-K1-v5", "displayName": "Gemma 4 31B K1 v5", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/gemma-4-31b-larkspur-v0.5", "provider": "nano-gpt", "model": "gemma-4-31b-larkspur-v0.5", "displayName": "Gemma 4 31B Larkspur v0.5", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemma-4-31B-Larkspur-v0.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemma-4-31B-Larkspur-v0.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Larkspur v0.5" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemma-4-31B-Larkspur-v0.5", "modelKey": "gemma-4-31B-Larkspur-v0.5", "displayName": "Gemma 4 31B Larkspur v0.5", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/gemma-4-31b-meromero", "provider": "nano-gpt", "model": "gemma-4-31b-meromero", "displayName": "Gemma 4 31B MeroMero", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/gemma-4-31B-MeroMero" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "gemma-4-31B-MeroMero", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B MeroMero" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "gemma-4-31B-MeroMero", "modelKey": "gemma-4-31B-MeroMero", "displayName": "Gemma 4 31B MeroMero", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/gemma-4-31b-musica-v1", "provider": "nano-gpt", "model": "gemma-4-31b-musica-v1", "displayName": "Gemma 4 31B Musica v1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-Musica-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-Musica-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Musica v1" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-Musica-v1", "modelKey": "Gemma-4-31B-Musica-v1", "displayName": "Gemma 4 31B Musica v1", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma-4-31b-queen", "provider": "nano-gpt", "model": "gemma-4-31b-queen", "displayName": "Gemma 4 31B Queen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gemma-4-31B-Queen" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gemma-4-31B-Queen", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Queen" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gemma-4-31B-Queen", "modelKey": "Gemma-4-31B-Queen", "displayName": "Gemma 4 31B Queen", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/gemma4-31b", "provider": "nano-gpt", "model": "gemma4-31b", "displayName": "Gemma 4 31B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/gemma4-31b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gemma4-31b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B" ], "releaseDate": "2026-04-04", "lastUpdated": "2026-04-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gemma4-31b", "modelKey": "TEE/gemma4-31b", "displayName": "Gemma 4 31B", "metadata": { "lastUpdated": "2026-04-04", "openWeights": false, "releaseDate": "2026-04-04" } } ] }, { "id": "nano-gpt/gemma4-31b:thinking", "provider": "nano-gpt", "model": "gemma4-31b:thinking", "displayName": "Gemma 4 31B Thinking TEE", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/gemma4-31b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gemma4-31b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B Thinking TEE" ], "releaseDate": "2026-05-02", "lastUpdated": "2026-05-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gemma4-31b:thinking", "modelKey": "TEE/gemma4-31b:thinking", "displayName": "Gemma 4 31B Thinking TEE", "metadata": { "lastUpdated": "2026-05-02", "openWeights": false, "releaseDate": "2026-05-02" } } ] }, { "id": "nano-gpt/granite-4.1-8b", "provider": "nano-gpt", "model": "granite-4.1-8b", "displayName": "Granite 4.1 8B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ibm-granite/granite-4.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ibm-granite/granite-4.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Granite 4.1 8B" ], "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ibm-granite/granite-4.1-8b", "modelKey": "ibm-granite/granite-4.1-8b", "displayName": "Granite 4.1 8B", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2026-04-29" } } ] }, { "id": "nano-gpt/grayline-qwen3-8b", "provider": "nano-gpt", "model": "grayline-qwen3-8b", "displayName": "Grayline Qwen3 8B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/soob3123/GrayLine-Qwen3-8B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "soob3123/GrayLine-Qwen3-8B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Grayline Qwen3 8B" ], "families": [ "qwen" ], "releaseDate": "2025-09-25", "lastUpdated": "2025-09-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "soob3123/GrayLine-Qwen3-8B", "modelKey": "soob3123/GrayLine-Qwen3-8B", "displayName": "Grayline Qwen3 8B", "family": "qwen", "metadata": { "lastUpdated": "2025-09-25", "openWeights": false, "releaseDate": "2025-09-25" } } ] }, { "id": "nano-gpt/hermes-3-llama-3.1-70b", "provider": "nano-gpt", "model": "hermes-3-llama-3.1-70b", "displayName": "Hermes 3 70B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/hermes-3-llama-3.1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/hermes-3-llama-3.1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.408, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Hermes 3 70B" ], "releaseDate": "2026-01-07", "lastUpdated": "2026-01-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/hermes-3-llama-3.1-70b", "modelKey": "NousResearch/hermes-3-llama-3.1-70b", "displayName": "Hermes 3 70B", "metadata": { "lastUpdated": "2026-01-07", "openWeights": false, "releaseDate": "2026-01-07" } } ] }, { "id": "nano-gpt/hermes-4-405b", "provider": "nano-gpt", "model": "hermes-4-405b", "displayName": "Hermes 4 Large", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/hermes-4-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/hermes-4-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Hermes 4 Large" ], "releaseDate": "2025-08-26", "lastUpdated": "2025-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/hermes-4-405b", "modelKey": "NousResearch/hermes-4-405b", "displayName": "Hermes 4 Large", "metadata": { "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } } ] }, { "id": "nano-gpt/hermes-4-405b:thinking", "provider": "nano-gpt", "model": "hermes-4-405b:thinking", "displayName": "Hermes 4 Large (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/hermes-4-405b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/hermes-4-405b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Hermes 4 Large (Thinking)" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/hermes-4-405b:thinking", "modelKey": "NousResearch/hermes-4-405b:thinking", "displayName": "Hermes 4 Large (Thinking)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/hermes-4-70b", "provider": "nano-gpt", "model": "hermes-4-70b", "displayName": "Hermes 4 Medium", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/hermes-4-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/hermes-4-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.3995 } } ] }, "metadata": { "displayNames": [ "Hermes 4 Medium" ], "releaseDate": "2025-07-03", "lastUpdated": "2025-07-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/hermes-4-70b", "modelKey": "NousResearch/hermes-4-70b", "displayName": "Hermes 4 Medium", "metadata": { "lastUpdated": "2025-07-03", "openWeights": false, "releaseDate": "2025-07-03" } } ] }, { "id": "nano-gpt/hermes-4-70b:thinking", "provider": "nano-gpt", "model": "hermes-4-70b:thinking", "displayName": "Hermes 4 (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NousResearch/Hermes-4-70B:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NousResearch/Hermes-4-70B:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.3995 } } ] }, "metadata": { "displayNames": [ "Hermes 4 (Thinking)" ], "releaseDate": "2025-09-17", "lastUpdated": "2025-09-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NousResearch/Hermes-4-70B:thinking", "modelKey": "NousResearch/Hermes-4-70B:thinking", "displayName": "Hermes 4 (Thinking)", "metadata": { "lastUpdated": "2025-09-17", "openWeights": false, "releaseDate": "2025-09-17" } } ] }, { "id": "nano-gpt/hermes-high", "provider": "nano-gpt", "model": "hermes-high", "displayName": "Hermes High", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/hermes-high" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "hermes-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.998, "output": 25.007 } } ] }, "metadata": { "displayNames": [ "Hermes High" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "hermes-high", "modelKey": "hermes-high", "displayName": "Hermes High", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/hermes-low", "provider": "nano-gpt", "model": "hermes-low", "displayName": "Hermes Low", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/hermes-low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "hermes-low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Hermes Low" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "hermes-low", "modelKey": "hermes-low", "displayName": "Hermes Low", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/hermes-medium", "provider": "nano-gpt", "model": "hermes-medium", "displayName": "Hermes Medium", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/hermes-medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "inputTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "hermes-medium", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Hermes Medium" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "hermes-medium", "modelKey": "hermes-medium", "displayName": "Hermes Medium", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/holo3-35b-a3b", "provider": "nano-gpt", "model": "holo3-35b-a3b", "displayName": "Holo3-35B-A3B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/holo3-35b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "holo3-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Holo3-35B-A3B" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "holo3-35b-a3b", "modelKey": "holo3-35b-a3b", "displayName": "Holo3-35B-A3B", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/holo3-35b-a3b:thinking", "provider": "nano-gpt", "model": "holo3-35b-a3b:thinking", "displayName": "Holo3-35B-A3B Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/holo3-35b-a3b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "holo3-35b-a3b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "Holo3-35B-A3B Thinking" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "holo3-35b-a3b:thinking", "modelKey": "holo3-35b-a3b:thinking", "displayName": "Holo3-35B-A3B Thinking", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/hunyuan-mt-7b", "provider": "nano-gpt", "model": "hunyuan-mt-7b", "displayName": "Hunyuan MT 7B", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/tencent/Hunyuan-MT-7B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "tencent/Hunyuan-MT-7B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 20 } } ] }, "metadata": { "displayNames": [ "Hunyuan MT 7B" ], "families": [ "hunyuan" ], "releaseDate": "2025-09-18", "lastUpdated": "2025-09-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "tencent/Hunyuan-MT-7B", "modelKey": "tencent/Hunyuan-MT-7B", "displayName": "Hunyuan MT 7B", "family": "hunyuan", "metadata": { "lastUpdated": "2025-09-18", "openWeights": false, "releaseDate": "2025-09-18" } } ] }, { "id": "nano-gpt/hunyuan-turbos-20250226", "provider": "nano-gpt", "model": "hunyuan-turbos-20250226", "displayName": "Hunyuan Turbo S", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/hunyuan-turbos-20250226" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 24000, "inputTokens": 24000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "hunyuan-turbos-20250226", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.187, "output": 0.374 } } ] }, "metadata": { "displayNames": [ "Hunyuan Turbo S" ], "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "hunyuan-turbos-20250226", "modelKey": "hunyuan-turbos-20250226", "displayName": "Hunyuan Turbo S", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } } ] }, { "id": "nano-gpt/hy3-preview", "provider": "nano-gpt", "model": "hy3-preview", "displayName": "Tencent: Hy3 preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/tencent/hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "tencent/hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.029, "input": 0.066, "output": 0.26 } } ] }, "metadata": { "displayNames": [ "Tencent: Hy3 preview" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "tencent/hy3-preview", "modelKey": "tencent/hy3-preview", "displayName": "Tencent: Hy3 preview", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "nano-gpt/inflection-3-pi", "provider": "nano-gpt", "model": "inflection-3-pi", "displayName": "Inflection 3 Pi", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inflection/inflection-3-pi" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inflection/inflection-3-pi", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 9.996 } } ] }, "metadata": { "displayNames": [ "Inflection 3 Pi" ], "families": [ "gpt" ], "releaseDate": "2024-10-11", "lastUpdated": "2024-10-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inflection/inflection-3-pi", "modelKey": "inflection/inflection-3-pi", "displayName": "Inflection 3 Pi", "family": "gpt", "metadata": { "lastUpdated": "2024-10-11", "openWeights": false, "releaseDate": "2024-10-11" } } ] }, { "id": "nano-gpt/inflection-3-productivity", "provider": "nano-gpt", "model": "inflection-3-productivity", "displayName": "Inflection 3 Productivity", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inflection/inflection-3-productivity" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inflection/inflection-3-productivity", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 9.996 } } ] }, "metadata": { "displayNames": [ "Inflection 3 Productivity" ], "families": [ "gpt" ], "releaseDate": "2024-10-11", "lastUpdated": "2024-10-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inflection/inflection-3-productivity", "modelKey": "inflection/inflection-3-productivity", "displayName": "Inflection 3 Productivity", "family": "gpt", "metadata": { "lastUpdated": "2024-10-11", "openWeights": false, "releaseDate": "2024-10-11" } } ] }, { "id": "nano-gpt/jamba-large", "provider": "nano-gpt", "model": "jamba-large", "displayName": "Jamba Large", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.989, "output": 7.99 } } ] }, "metadata": { "displayNames": [ "Jamba Large" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-large", "modelKey": "jamba-large", "displayName": "Jamba Large", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "nano-gpt/jamba-large-1.6", "provider": "nano-gpt", "model": "jamba-large-1.6", "displayName": "Jamba Large 1.6", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-large-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-large-1.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.989, "output": 7.99 } } ] }, "metadata": { "displayNames": [ "Jamba Large 1.6" ], "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-large-1.6", "modelKey": "jamba-large-1.6", "displayName": "Jamba Large 1.6", "metadata": { "lastUpdated": "2025-03-12", "openWeights": false, "releaseDate": "2025-03-12" } } ] }, { "id": "nano-gpt/jamba-large-1.7", "provider": "nano-gpt", "model": "jamba-large-1.7", "displayName": "Jamba Large 1.7", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-large-1.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-large-1.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.989, "output": 7.99 } } ] }, "metadata": { "displayNames": [ "Jamba Large 1.7" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-large-1.7", "modelKey": "jamba-large-1.7", "displayName": "Jamba Large 1.7", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "nano-gpt/jamba-mini", "provider": "nano-gpt", "model": "jamba-mini", "displayName": "Jamba Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1989, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Jamba Mini" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-mini", "modelKey": "jamba-mini", "displayName": "Jamba Mini", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "nano-gpt/jamba-mini-1.6", "provider": "nano-gpt", "model": "jamba-mini-1.6", "displayName": "Jamba Mini 1.6", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-mini-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-mini-1.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1989, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Jamba Mini 1.6" ], "releaseDate": "2025-03-01", "lastUpdated": "2025-03-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-mini-1.6", "modelKey": "jamba-mini-1.6", "displayName": "Jamba Mini 1.6", "metadata": { "lastUpdated": "2025-03-01", "openWeights": false, "releaseDate": "2025-03-01" } } ] }, { "id": "nano-gpt/jamba-mini-1.7", "provider": "nano-gpt", "model": "jamba-mini-1.7", "displayName": "Jamba Mini 1.7", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/jamba-mini-1.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "jamba-mini-1.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1989, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Jamba Mini 1.7" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "jamba-mini-1.7", "modelKey": "jamba-mini-1.7", "displayName": "Jamba Mini 1.7", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "nano-gpt/k2-think", "provider": "nano-gpt", "model": "k2-think", "displayName": "K2-Think", "family": "kimi-thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/LLM360/K2-Think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "LLM360/K2-Think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "K2-Think" ], "families": [ "kimi-thinking" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "LLM360/K2-Think", "modelKey": "LLM360/K2-Think", "displayName": "K2-Think", "family": "kimi-thinking", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/kat-coder-air-v1", "provider": "nano-gpt", "model": "kat-coder-air-v1", "displayName": "KAT Coder Air V1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/KAT-Coder-Air-V1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "KAT-Coder-Air-V1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "KAT Coder Air V1" ], "releaseDate": "2025-10-28", "lastUpdated": "2025-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "KAT-Coder-Air-V1", "modelKey": "KAT-Coder-Air-V1", "displayName": "KAT Coder Air V1", "metadata": { "lastUpdated": "2025-10-28", "openWeights": false, "releaseDate": "2025-10-28" } } ] }, { "id": "nano-gpt/kat-coder-exp-72b-1010", "provider": "nano-gpt", "model": "kat-coder-exp-72b-1010", "displayName": "KAT Coder Exp 72B 1010", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/KAT-Coder-Exp-72B-1010" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "KAT-Coder-Exp-72B-1010", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "KAT Coder Exp 72B 1010" ], "releaseDate": "2025-10-28", "lastUpdated": "2025-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "KAT-Coder-Exp-72B-1010", "modelKey": "KAT-Coder-Exp-72B-1010", "displayName": "KAT Coder Exp 72B 1010", "metadata": { "lastUpdated": "2025-10-28", "openWeights": false, "releaseDate": "2025-10-28" } } ] }, { "id": "nano-gpt/kat-coder-pro-v2", "provider": "nano-gpt", "model": "kat-coder-pro-v2", "displayName": "KAT Coder Pro V2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/kwaipilot/kat-coder-pro-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "kwaipilot/kat-coder-pro-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "KAT Coder Pro V2" ], "releaseDate": "2026-03-28", "lastUpdated": "2026-03-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "kwaipilot/kat-coder-pro-v2", "modelKey": "kwaipilot/kat-coder-pro-v2", "displayName": "KAT Coder Pro V2", "metadata": { "lastUpdated": "2026-03-28", "openWeights": false, "releaseDate": "2026-03-28" } } ] }, { "id": "nano-gpt/l3-8b-stheno-v3.2", "provider": "nano-gpt", "model": "l3-8b-stheno-v3.2", "displayName": "Sao10K Stheno 8b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Sao10K/L3-8B-Stheno-v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Sao10K/L3-8B-Stheno-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "Sao10K Stheno 8b" ], "families": [ "llama" ], "releaseDate": "2024-11-29", "lastUpdated": "2024-11-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Sao10K/L3-8B-Stheno-v3.2", "modelKey": "Sao10K/L3-8B-Stheno-v3.2", "displayName": "Sao10K Stheno 8b", "family": "llama", "metadata": { "lastUpdated": "2024-11-29", "openWeights": false, "releaseDate": "2024-11-29" } } ] }, { "id": "nano-gpt/l3.1-70b-celeste-v0.1-bf16", "provider": "nano-gpt", "model": "l3.1-70b-celeste-v0.1-bf16", "displayName": "Llama 3.1 70B Celeste v0.1", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Celeste v0.1" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16", "modelKey": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16", "displayName": "Llama 3.1 70B Celeste v0.1", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "nano-gpt/l3.1-70b-euryale-v2.2", "provider": "nano-gpt", "model": "l3.1-70b-euryale-v2.2", "displayName": "Llama 3.1 70B Euryale", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Sao10K/L3.1-70B-Euryale-v2.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 20480, "inputTokens": 20480, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Sao10K/L3.1-70B-Euryale-v2.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.306, "output": 0.357 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Euryale" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Sao10K/L3.1-70B-Euryale-v2.2", "modelKey": "Sao10K/L3.1-70B-Euryale-v2.2", "displayName": "Llama 3.1 70B Euryale", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "nano-gpt/l3.1-70b-hanami-x1", "provider": "nano-gpt", "model": "l3.1-70b-hanami-x1", "displayName": "Llama 3.1 70B Hanami", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Sao10K/L3.1-70B-Hanami-x1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Sao10K/L3.1-70B-Hanami-x1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Hanami" ], "families": [ "llama" ], "releaseDate": "2024-07-23", "lastUpdated": "2024-07-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Sao10K/L3.1-70B-Hanami-x1", "modelKey": "Sao10K/L3.1-70B-Hanami-x1", "displayName": "Llama 3.1 70B Hanami", "family": "llama", "metadata": { "lastUpdated": "2024-07-23", "openWeights": false, "releaseDate": "2024-07-23" } } ] }, { "id": "nano-gpt/l3.3-70b-euryale-v2.3", "provider": "nano-gpt", "model": "l3.3-70b-euryale-v2.3", "displayName": "Llama 3.3 70B Euryale", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Sao10K/L3.3-70B-Euryale-v2.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 20480, "inputTokens": 20480, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Sao10K/L3.3-70B-Euryale-v2.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Euryale" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Sao10K/L3.3-70B-Euryale-v2.3", "modelKey": "Sao10K/L3.3-70B-Euryale-v2.3", "displayName": "Llama 3.3 70B Euryale", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-cu-mai-r1-70b", "provider": "nano-gpt", "model": "l3.3-cu-mai-r1-70b", "displayName": "Llama 3.3 70B Cu Mai", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-Cu-Mai-R1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-Cu-Mai-R1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Cu Mai" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-Cu-Mai-R1-70b", "modelKey": "Steelskull/L3.3-Cu-Mai-R1-70b", "displayName": "Llama 3.3 70B Cu Mai", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-electra-r1-70b", "provider": "nano-gpt", "model": "l3.3-electra-r1-70b", "displayName": "Steelskull Electra R1 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-Electra-R1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-Electra-R1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.69989, "output": 0.69989 } } ] }, "metadata": { "displayNames": [ "Steelskull Electra R1 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-Electra-R1-70b", "modelKey": "Steelskull/L3.3-Electra-R1-70b", "displayName": "Steelskull Electra R1 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-ms-evalebis-70b", "provider": "nano-gpt", "model": "l3.3-ms-evalebis-70b", "displayName": "MS Evalebis 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-MS-Evalebis-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-MS-Evalebis-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "MS Evalebis 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-MS-Evalebis-70b", "modelKey": "Steelskull/L3.3-MS-Evalebis-70b", "displayName": "MS Evalebis 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-ms-evayale-70b", "provider": "nano-gpt", "model": "l3.3-ms-evayale-70b", "displayName": "Evayale 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-MS-Evayale-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-MS-Evayale-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Evayale 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-MS-Evayale-70B", "modelKey": "Steelskull/L3.3-MS-Evayale-70B", "displayName": "Evayale 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-ms-nevoria-70b", "provider": "nano-gpt", "model": "l3.3-ms-nevoria-70b", "displayName": "Steelskull Nevoria 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-MS-Nevoria-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-MS-Nevoria-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Steelskull Nevoria 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-MS-Nevoria-70b", "modelKey": "Steelskull/L3.3-MS-Nevoria-70b", "displayName": "Steelskull Nevoria 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/l3.3-nevoria-r1-70b", "provider": "nano-gpt", "model": "l3.3-nevoria-r1-70b", "displayName": "Steelskull Nevoria R1 70b", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Steelskull/L3.3-Nevoria-R1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Steelskull/L3.3-Nevoria-R1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Steelskull Nevoria R1 70b" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Steelskull/L3.3-Nevoria-R1-70b", "modelKey": "Steelskull/L3.3-Nevoria-R1-70b", "displayName": "Steelskull Nevoria R1 70b", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/laguna-m.1", "provider": "nano-gpt", "model": "laguna-m.1", "displayName": "Laguna M.1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/poolside/laguna-m.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "poolside/laguna-m.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Laguna M.1" ], "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "poolside/laguna-m.1", "modelKey": "poolside/laguna-m.1", "displayName": "Laguna M.1", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2026-04-29" } } ] }, { "id": "nano-gpt/laguna-xs.2", "provider": "nano-gpt", "model": "laguna-xs.2", "displayName": "Laguna XS.2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/poolside/laguna-xs.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "poolside/laguna-xs.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Laguna XS.2" ], "releaseDate": "2026-04-29", "lastUpdated": "2026-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "poolside/laguna-xs.2", "modelKey": "poolside/laguna-xs.2", "displayName": "Laguna XS.2", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2026-04-29" } } ] }, { "id": "nano-gpt/learnlm-1.5-pro-experimental", "provider": "nano-gpt", "model": "learnlm-1.5-pro-experimental", "displayName": "Gemini LearnLM Experimental", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/learnlm-1.5-pro-experimental" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32767, "inputTokens": 32767, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "learnlm-1.5-pro-experimental", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.502, "output": 10.506 } } ] }, "metadata": { "displayNames": [ "Gemini LearnLM Experimental" ], "releaseDate": "2024-05-14", "lastUpdated": "2024-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "learnlm-1.5-pro-experimental", "modelKey": "learnlm-1.5-pro-experimental", "displayName": "Gemini LearnLM Experimental", "metadata": { "lastUpdated": "2024-05-14", "openWeights": false, "releaseDate": "2024-05-14" } } ] }, { "id": "nano-gpt/lfm-2-24b-a2b", "provider": "nano-gpt", "model": "lfm-2-24b-a2b", "displayName": "LFM2 24B A2B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/liquid/lfm-2-24b-a2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "liquid/lfm-2-24b-a2b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "LFM2 24B A2B" ], "releaseDate": "2025-12-20", "lastUpdated": "2025-12-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "liquid/lfm-2-24b-a2b", "modelKey": "liquid/lfm-2-24b-a2b", "displayName": "LFM2 24B A2B", "metadata": { "lastUpdated": "2025-12-20", "openWeights": false, "releaseDate": "2025-12-20" } } ] }, { "id": "nano-gpt/ling-2.6-1t", "provider": "nano-gpt", "model": "ling-2.6-1t", "displayName": "Ling 2.6 1T", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inclusionai/ling-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inclusionai/ling-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Ling 2.6 1T" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inclusionai/ling-2.6-1t", "modelKey": "inclusionai/ling-2.6-1t", "displayName": "Ling 2.6 1T", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "nano-gpt/ling-2.6-flash", "provider": "nano-gpt", "model": "ling-2.6-flash", "displayName": "Ling 2.6 Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inclusionai/ling-2.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inclusionai/ling-2.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Ling 2.6 Flash" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inclusionai/ling-2.6-flash", "modelKey": "inclusionai/ling-2.6-flash", "displayName": "Ling 2.6 Flash", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } } ] }, { "id": "nano-gpt/llama3-3-70b", "provider": "nano-gpt", "model": "llama3-3-70b", "displayName": "Llama 3.3 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/llama3-3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/llama3-3-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B" ], "families": [ "llama" ], "releaseDate": "2025-07-03", "lastUpdated": "2025-07-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/llama3-3-70b", "modelKey": "TEE/llama3-3-70b", "displayName": "Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2025-07-03", "openWeights": false, "releaseDate": "2025-07-03" } } ] }, { "id": "nano-gpt/lumimaid-v0.2-70b", "provider": "nano-gpt", "model": "lumimaid-v0.2-70b", "displayName": "Lumimaid v0.2", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/NeverSleep/Lumimaid-v0.2-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "NeverSleep/Lumimaid-v0.2-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Lumimaid v0.2" ], "families": [ "llama" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "NeverSleep/Lumimaid-v0.2-70B", "modelKey": "NeverSleep/Lumimaid-v0.2-70B", "displayName": "Lumimaid v0.2", "family": "llama", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/m-prometheus-14b", "provider": "nano-gpt", "model": "m-prometheus-14b", "displayName": "M-Prometheus 14B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Unbabel/M-Prometheus-14B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Unbabel/M-Prometheus-14B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "M-Prometheus 14B" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Unbabel/M-Prometheus-14B", "modelKey": "Unbabel/M-Prometheus-14B", "displayName": "M-Prometheus 14B", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "nano-gpt/magidonia-24b-v4.3", "provider": "nano-gpt", "model": "magidonia-24b-v4.3", "displayName": "The Drummer Magidonia 24B v4.3", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Magidonia-24B-v4.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Magidonia-24B-v4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1207 } } ] }, "metadata": { "displayNames": [ "The Drummer Magidonia 24B v4.3" ], "releaseDate": "2025-12-25", "lastUpdated": "2025-12-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Magidonia-24B-v4.3", "modelKey": "TheDrummer/Magidonia-24B-v4.3", "displayName": "The Drummer Magidonia 24B v4.3", "metadata": { "lastUpdated": "2025-12-25", "openWeights": false, "releaseDate": "2025-12-25" } } ] }, { "id": "nano-gpt/magnum-v2-72b", "provider": "nano-gpt", "model": "magnum-v2-72b", "displayName": "Magnum V2 72B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthracite-org/magnum-v2-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthracite-org/magnum-v2-72b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 2.992 } } ] }, "metadata": { "displayNames": [ "Magnum V2 72B" ], "families": [ "llama" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthracite-org/magnum-v2-72b", "modelKey": "anthracite-org/magnum-v2-72b", "displayName": "Magnum V2 72B", "family": "llama", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/magnum-v4-72b", "provider": "nano-gpt", "model": "magnum-v4-72b", "displayName": "Magnum v4 72B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/anthracite-org/magnum-v4-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "anthracite-org/magnum-v4-72b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 2.992 } } ] }, "metadata": { "displayNames": [ "Magnum v4 72B" ], "families": [ "llama" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "anthracite-org/magnum-v4-72b", "modelKey": "anthracite-org/magnum-v4-72b", "displayName": "Magnum v4 72B", "family": "llama", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "nano-gpt/manta-flash-1.0", "provider": "nano-gpt", "model": "manta-flash-1.0", "displayName": "Manta Flash 1.0", "family": "nova", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/meganova-ai/manta-flash-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "meganova-ai/manta-flash-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "Manta Flash 1.0" ], "families": [ "nova" ], "releaseDate": "2025-12-20", "lastUpdated": "2025-12-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meganova-ai/manta-flash-1.0", "modelKey": "meganova-ai/manta-flash-1.0", "displayName": "Manta Flash 1.0", "family": "nova", "metadata": { "lastUpdated": "2025-12-20", "openWeights": false, "releaseDate": "2025-12-20" } } ] }, { "id": "nano-gpt/manta-mini-1.0", "provider": "nano-gpt", "model": "manta-mini-1.0", "displayName": "Manta Mini 1.0", "family": "nova", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/meganova-ai/manta-mini-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "meganova-ai/manta-mini-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.16 } } ] }, "metadata": { "displayNames": [ "Manta Mini 1.0" ], "families": [ "nova" ], "releaseDate": "2025-12-20", "lastUpdated": "2025-12-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meganova-ai/manta-mini-1.0", "modelKey": "meganova-ai/manta-mini-1.0", "displayName": "Manta Mini 1.0", "family": "nova", "metadata": { "lastUpdated": "2025-12-20", "openWeights": false, "releaseDate": "2025-12-20" } } ] }, { "id": "nano-gpt/manta-pro-1.0", "provider": "nano-gpt", "model": "manta-pro-1.0", "displayName": "Manta Pro 1.0", "family": "nova", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/meganova-ai/manta-pro-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "meganova-ai/manta-pro-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.060000000000000005, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Manta Pro 1.0" ], "families": [ "nova" ], "releaseDate": "2025-12-20", "lastUpdated": "2025-12-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "meganova-ai/manta-pro-1.0", "modelKey": "meganova-ai/manta-pro-1.0", "displayName": "Manta Pro 1.0", "family": "nova", "metadata": { "lastUpdated": "2025-12-20", "openWeights": false, "releaseDate": "2025-12-20" } } ] }, { "id": "nano-gpt/mercury-2", "provider": "nano-gpt", "model": "mercury-2", "displayName": "Mercury 2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Mercury 2" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mercury-2", "modelKey": "mercury-2", "displayName": "Mercury 2", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/mimo-v2-flash", "provider": "nano-gpt", "model": "mimo-v2-flash", "displayName": "MiMo V2 Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.102, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash" ], "families": [ "mimo" ], "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-flash", "modelKey": "xiaomi/mimo-v2-flash", "displayName": "MiMo V2 Flash", "family": "mimo", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2-flash-original", "provider": "nano-gpt", "model": "mimo-v2-flash-original", "displayName": "MiMo V2 Flash Original", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-flash-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-flash-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.102, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash Original" ], "families": [ "mimo" ], "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-flash-original", "modelKey": "xiaomi/mimo-v2-flash-original", "displayName": "MiMo V2 Flash Original", "family": "mimo", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2-flash-thinking", "provider": "nano-gpt", "model": "mimo-v2-flash-thinking", "displayName": "MiMo V2 Flash (Thinking)", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-flash-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-flash-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.102, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash (Thinking)" ], "families": [ "mimo" ], "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-flash-thinking", "modelKey": "xiaomi/mimo-v2-flash-thinking", "displayName": "MiMo V2 Flash (Thinking)", "family": "mimo", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2-flash-thinking-original", "provider": "nano-gpt", "model": "mimo-v2-flash-thinking-original", "displayName": "MiMo V2 Flash (Thinking) Original", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-flash-thinking-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-flash-thinking-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.102, "output": 0.306 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash (Thinking) Original" ], "families": [ "mimo" ], "releaseDate": "2025-12-17", "lastUpdated": "2025-12-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-flash-thinking-original", "modelKey": "xiaomi/mimo-v2-flash-thinking-original", "displayName": "MiMo V2 Flash (Thinking) Original", "family": "mimo", "metadata": { "lastUpdated": "2025-12-17", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2-omni", "provider": "nano-gpt", "model": "mimo-v2-omni", "displayName": "MiMo V2 Omni", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Omni" ], "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-omni", "modelKey": "xiaomi/mimo-v2-omni", "displayName": "MiMo V2 Omni", "metadata": { "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2-pro", "provider": "nano-gpt", "model": "mimo-v2-pro", "displayName": "MiMo V2 Pro", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Pro" ], "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2-pro", "modelKey": "xiaomi/mimo-v2-pro", "displayName": "MiMo V2 Pro", "metadata": { "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2.5", "provider": "nano-gpt", "model": "mimo-v2.5", "displayName": "MiMo V2.5", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2.5", "modelKey": "xiaomi/mimo-v2.5", "displayName": "MiMo V2.5", "metadata": { "lastUpdated": "2026-04-22", "openWeights": false, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mimo-v2.5-pro", "provider": "nano-gpt", "model": "mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0036, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Pro" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "xiaomi/mimo-v2.5-pro", "modelKey": "xiaomi/mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "metadata": { "lastUpdated": "2026-04-22", "openWeights": false, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/mirothinker-1-7-deepresearch", "provider": "nano-gpt", "model": "mirothinker-1-7-deepresearch", "displayName": "MiroThinker 1.7 Deep Research", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mirothinker-1-7-deepresearch" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mirothinker-1-7-deepresearch", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4, "output": 25 } } ] }, "metadata": { "displayNames": [ "MiroThinker 1.7 Deep Research" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mirothinker-1-7-deepresearch", "modelKey": "mirothinker-1-7-deepresearch", "displayName": "MiroThinker 1.7 Deep Research", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/mirothinker-1-7-deepresearch-mini", "provider": "nano-gpt", "model": "mirothinker-1-7-deepresearch-mini", "displayName": "MiroThinker 1.7 Deep Research Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mirothinker-1-7-deepresearch-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mirothinker-1-7-deepresearch-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "MiroThinker 1.7 Deep Research Mini" ], "releaseDate": "2026-05-11", "lastUpdated": "2026-05-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mirothinker-1-7-deepresearch-mini", "modelKey": "mirothinker-1-7-deepresearch-mini", "displayName": "MiroThinker 1.7 Deep Research Mini", "metadata": { "lastUpdated": "2026-05-11", "openWeights": false, "releaseDate": "2026-05-11" } } ] }, { "id": "nano-gpt/mn-12b-inferor-v0.0", "provider": "nano-gpt", "model": "mn-12b-inferor-v0.0", "displayName": "Mistral Nemo Inferor 12B", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Infermatic/MN-12B-Inferor-v0.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Infermatic/MN-12B-Inferor-v0.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25499999999999995, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo Inferor 12B" ], "families": [ "mistral-nemo" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Infermatic/MN-12B-Inferor-v0.0", "modelKey": "Infermatic/MN-12B-Inferor-v0.0", "displayName": "Mistral Nemo Inferor 12B", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/mn-12b-mag-mell-r1", "provider": "nano-gpt", "model": "mn-12b-mag-mell-r1", "displayName": "Mag Mell R1", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inflatebot/MN-12B-Mag-Mell-R1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inflatebot/MN-12B-Mag-Mell-R1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Mag Mell R1" ], "families": [ "mistral-nemo" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inflatebot/MN-12B-Mag-Mell-R1", "modelKey": "inflatebot/MN-12B-Mag-Mell-R1", "displayName": "Mag Mell R1", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/mn-loosecannon-12b-v1", "provider": "nano-gpt", "model": "mn-loosecannon-12b-v1", "displayName": "MN-LooseCannon-12B-v1", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/GalrionSoftworks/MN-LooseCannon-12B-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "GalrionSoftworks/MN-LooseCannon-12B-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "MN-LooseCannon-12B-v1" ], "families": [ "mistral-nemo" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "GalrionSoftworks/MN-LooseCannon-12B-v1", "modelKey": "GalrionSoftworks/MN-LooseCannon-12B-v1", "displayName": "MN-LooseCannon-12B-v1", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/ms3.2-24b-magnum-diamond", "provider": "nano-gpt", "model": "ms3.2-24b-magnum-diamond", "displayName": "MS3.2 24B Magnum Diamond", "family": "mistral", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "MS3.2 24B Magnum Diamond" ], "families": [ "mistral" ], "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond", "modelKey": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond", "displayName": "MS3.2 24B Magnum Diamond", "family": "mistral", "metadata": { "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } } ] }, { "id": "nano-gpt/ms3.2-the-omega-directive-24b-unslop-v2.0", "provider": "nano-gpt", "model": "ms3.2-the-omega-directive-24b-unslop-v2.0", "displayName": "Omega Directive 24B Unslop v2.0", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Omega Directive 24B Unslop v2.0" ], "families": [ "llama" ], "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0", "modelKey": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0", "displayName": "Omega Directive 24B Unslop v2.0", "family": "llama", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "nano-gpt/mythomax-l2-13b", "provider": "nano-gpt", "model": "mythomax-l2-13b", "displayName": "MythoMax 13B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Gryphe/MythoMax-L2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "inputTokens": 4000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Gryphe/MythoMax-L2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1003 } } ] }, "metadata": { "displayNames": [ "MythoMax 13B" ], "families": [ "llama" ], "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Gryphe/MythoMax-L2-13b", "modelKey": "Gryphe/MythoMax-L2-13b", "displayName": "MythoMax 13B", "family": "llama", "metadata": { "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } } ] }, { "id": "nano-gpt/nemomix-unleashed-12b", "provider": "nano-gpt", "model": "nemomix-unleashed-12b", "displayName": "NemoMix 12B Unleashed", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/MarinaraSpaghetti/NemoMix-Unleashed-12B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "MarinaraSpaghetti/NemoMix-Unleashed-12B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "NemoMix 12B Unleashed" ], "families": [ "mistral-nemo" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "MarinaraSpaghetti/NemoMix-Unleashed-12B", "modelKey": "MarinaraSpaghetti/NemoMix-Unleashed-12B", "displayName": "NemoMix 12B Unleashed", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/nemotron-3-nano-30b-a3b", "provider": "nano-gpt", "model": "nemotron-3-nano-30b-a3b", "displayName": "Nvidia Nemotron 3 Nano 30B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron 3 Nano 30B" ], "families": [ "nemotron" ], "releaseDate": "2025-12-15", "lastUpdated": "2025-12-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/nemotron-3-nano-30b-a3b", "modelKey": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "Nvidia Nemotron 3 Nano 30B", "family": "nemotron", "metadata": { "lastUpdated": "2025-12-15", "openWeights": false, "releaseDate": "2025-12-15" } } ] }, { "id": "nano-gpt/nemotron-3-nano-omni-30b-a3b-reasoning", "provider": "nano-gpt", "model": "nemotron-3-nano-omni-30b-a3b-reasoning", "displayName": "Nvidia Nemotron 3 Nano Omni", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.105, "output": 0.42 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron 3 Nano Omni" ], "families": [ "nemotron" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "modelKey": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "displayName": "Nvidia Nemotron 3 Nano Omni", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-28", "openWeights": false, "releaseDate": "2026-04-28" } } ] }, { "id": "nano-gpt/nemotron-3-super-120b-a12b", "provider": "nano-gpt", "model": "nemotron-3-super-120b-a12b", "displayName": "Nvidia Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-01", "lastUpdated": "2026-03-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "Nvidia Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nano-gpt/nemotron-3-super-120b-a12b:thinking", "provider": "nano-gpt", "model": "nemotron-3-super-120b-a12b:thinking", "displayName": "Nvidia Nemotron 3 Super 120B Thinking", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/nemotron-3-super-120b-a12b:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/nemotron-3-super-120b-a12b:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron 3 Super 120B Thinking" ], "families": [ "nemotron" ], "releaseDate": "2026-03-01", "lastUpdated": "2026-03-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/nemotron-3-super-120b-a12b:thinking", "modelKey": "nvidia/nemotron-3-super-120b-a12b:thinking", "displayName": "Nvidia Nemotron 3 Super 120B Thinking", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01" } } ] }, { "id": "nano-gpt/neuraldaredevil-8b-abliterated", "provider": "nano-gpt", "model": "neuraldaredevil-8b-abliterated", "displayName": "Neural Daredevil 8B abliterated", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/mlabonne/NeuralDaredevil-8B-abliterated" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "mlabonne/NeuralDaredevil-8B-abliterated", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.44, "output": 0.44 } } ] }, "metadata": { "displayNames": [ "Neural Daredevil 8B abliterated" ], "families": [ "llama" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "mlabonne/NeuralDaredevil-8B-abliterated", "modelKey": "mlabonne/NeuralDaredevil-8B-abliterated", "displayName": "Neural Daredevil 8B abliterated", "family": "llama", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "nano-gpt/nvidia-nemotron-nano-9b-v2", "provider": "nano-gpt", "model": "nvidia-nemotron-nano-9b-v2", "displayName": "Nvidia Nemotron Nano 9B v2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/nvidia/nvidia-nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "nvidia/nvidia-nemotron-nano-9b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron Nano 9B v2" ], "families": [ "nemotron" ], "releaseDate": "2025-08-18", "lastUpdated": "2025-08-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "nvidia/nvidia-nemotron-nano-9b-v2", "modelKey": "nvidia/nvidia-nemotron-nano-9b-v2", "displayName": "Nvidia Nemotron Nano 9B v2", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-18", "openWeights": false, "releaseDate": "2025-08-18" } } ] }, { "id": "nano-gpt/olmo-3-32b-think", "provider": "nano-gpt", "model": "olmo-3-32b-think", "displayName": "Olmo 3 32B Think", "family": "allenai", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/allenai/olmo-3-32b-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "allenai/olmo-3-32b-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.44999999999999996 } } ] }, "metadata": { "displayNames": [ "Olmo 3 32B Think" ], "families": [ "allenai" ], "releaseDate": "2025-11-01", "lastUpdated": "2025-11-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "allenai/olmo-3-32b-think", "modelKey": "allenai/olmo-3-32b-think", "displayName": "Olmo 3 32B Think", "family": "allenai", "metadata": { "lastUpdated": "2025-11-01", "openWeights": false, "releaseDate": "2025-11-01" } } ] }, { "id": "nano-gpt/openreasoning-nemotron-32b", "provider": "nano-gpt", "model": "openreasoning-nemotron-32b", "displayName": "OpenReasoning Nemotron 32B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/pamanseau/OpenReasoning-Nemotron-32B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "pamanseau/OpenReasoning-Nemotron-32B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "OpenReasoning Nemotron 32B" ], "families": [ "nemotron" ], "releaseDate": "2025-08-21", "lastUpdated": "2025-08-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "pamanseau/OpenReasoning-Nemotron-32B", "modelKey": "pamanseau/OpenReasoning-Nemotron-32B", "displayName": "OpenReasoning Nemotron 32B", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-21", "openWeights": false, "releaseDate": "2025-08-21" } } ] }, { "id": "nano-gpt/owl", "provider": "nano-gpt", "model": "owl", "displayName": "OWL", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/owl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "inputTokens": 1048756, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "owl", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "OWL" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "owl", "modelKey": "owl", "displayName": "OWL", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "nano-gpt/perceptron-mk1", "provider": "nano-gpt", "model": "perceptron-mk1", "displayName": "Perceptron Mk1", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/perceptron/perceptron-mk1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "perceptron/perceptron-mk1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Perceptron Mk1" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "perceptron/perceptron-mk1", "modelKey": "perceptron/perceptron-mk1", "displayName": "Perceptron Mk1", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/phi-4-mini-instruct", "provider": "nano-gpt", "model": "phi-4-mini-instruct", "displayName": "Phi 4 Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.68 } } ] }, "metadata": { "displayNames": [ "Phi 4 Mini" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "phi-4-mini-instruct", "modelKey": "phi-4-mini-instruct", "displayName": "Phi 4 Mini", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/phi-4-multimodal-instruct", "provider": "nano-gpt", "model": "phi-4-multimodal-instruct", "displayName": "Phi 4 Multimodal", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/phi-4-multimodal-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "phi-4-multimodal-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.11 } } ] }, "metadata": { "displayNames": [ "Phi 4 Multimodal" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "phi-4-multimodal-instruct", "modelKey": "phi-4-multimodal-instruct", "displayName": "Phi 4 Multimodal", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/qvq-max", "provider": "nano-gpt", "model": "qvq-max", "displayName": "Qwen: QvQ Max", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/qvq-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "qvq-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 5.3 } } ] }, "metadata": { "displayNames": [ "Qwen: QvQ Max" ], "releaseDate": "2025-03-28", "lastUpdated": "2025-03-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "qvq-max", "modelKey": "qvq-max", "displayName": "Qwen: QvQ Max", "metadata": { "lastUpdated": "2025-03-28", "openWeights": false, "releaseDate": "2025-03-28" } } ] }, { "id": "nano-gpt/qwerky-72b", "provider": "nano-gpt", "model": "qwerky-72b", "displayName": "Qwerky 72B", "family": "qwerky", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/featherless-ai/Qwerky-72B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "featherless-ai/Qwerky-72B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Qwerky 72B" ], "families": [ "qwerky" ], "releaseDate": "2025-03-20", "lastUpdated": "2025-03-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "featherless-ai/Qwerky-72B", "modelKey": "featherless-ai/Qwerky-72B", "displayName": "Qwerky 72B", "family": "qwerky", "metadata": { "lastUpdated": "2025-03-20", "openWeights": false, "releaseDate": "2025-03-20" } } ] }, { "id": "nano-gpt/remm-slerp-l2-13b", "provider": "nano-gpt", "model": "remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/undi95/remm-slerp-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 6144, "inputTokens": 6144, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "undi95/remm-slerp-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7989999999999999, "output": 1.2069999999999999 } } ] }, "metadata": { "displayNames": [ "ReMM SLERP 13B" ], "families": [ "llama" ], "releaseDate": "2025-01-01", "lastUpdated": "2025-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "undi95/remm-slerp-l2-13b", "modelKey": "undi95/remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "family": "llama", "metadata": { "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "nano-gpt/ring-2.6-1t", "provider": "nano-gpt", "model": "ring-2.6-1t", "displayName": "Ring 2.6 1T", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/inclusionai/ring-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Ring 2.6 1T" ], "releaseDate": "2026-05-08", "lastUpdated": "2026-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "inclusionai/ring-2.6-1t", "modelKey": "inclusionai/ring-2.6-1t", "displayName": "Ring 2.6 1T", "metadata": { "lastUpdated": "2026-05-08", "openWeights": false, "releaseDate": "2026-05-08" } } ] }, { "id": "nano-gpt/rnj-1-instruct", "provider": "nano-gpt", "model": "rnj-1-instruct", "displayName": "RNJ-1 Instruct 8B", "family": "rnj", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/essentialai/rnj-1-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "essentialai/rnj-1-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "RNJ-1 Instruct 8B" ], "families": [ "rnj" ], "releaseDate": "2025-12-13", "lastUpdated": "2025-12-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "essentialai/rnj-1-instruct", "modelKey": "essentialai/rnj-1-instruct", "displayName": "RNJ-1 Instruct 8B", "family": "rnj", "metadata": { "lastUpdated": "2025-12-13", "openWeights": false, "releaseDate": "2025-12-13" } } ] }, { "id": "nano-gpt/rocinante-12b-v1.1", "provider": "nano-gpt", "model": "rocinante-12b-v1.1", "displayName": "Rocinante 12b", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Rocinante-12B-v1.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Rocinante-12B-v1.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.408, "output": 0.595 } } ] }, "metadata": { "displayNames": [ "Rocinante 12b" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Rocinante-12B-v1.1", "modelKey": "TheDrummer/Rocinante-12B-v1.1", "displayName": "Rocinante 12b", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/sarvam-105b", "provider": "nano-gpt", "model": "sarvam-105b", "displayName": "Sarvam 105B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/sarvam-105b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "sarvam-105b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.028, "input": 0.045, "output": 0.177 } } ] }, "metadata": { "displayNames": [ "Sarvam 105B" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sarvam-105b", "modelKey": "sarvam-105b", "displayName": "Sarvam 105B", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/sarvam-30b", "provider": "nano-gpt", "model": "sarvam-30b", "displayName": "Sarvam 30B", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/sarvam-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "sarvam-30b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.017, "input": 0.028, "output": 0.111 } } ] }, "metadata": { "displayNames": [ "Sarvam 30B" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sarvam-30b", "modelKey": "sarvam-30b", "displayName": "Sarvam 30B", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } } ] }, { "id": "nano-gpt/seed-2.0-lite", "provider": "nano-gpt", "model": "seed-2.0-lite", "displayName": "ByteDance Seed 2.0 Lite", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/bytedance-seed/seed-2.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "bytedance-seed/seed-2.0-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed 2.0 Lite" ], "releaseDate": "2026-03-10", "lastUpdated": "2026-03-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "bytedance-seed/seed-2.0-lite", "modelKey": "bytedance-seed/seed-2.0-lite", "displayName": "ByteDance Seed 2.0 Lite", "metadata": { "lastUpdated": "2026-03-10", "openWeights": false, "releaseDate": "2026-03-10" } } ] }, { "id": "nano-gpt/shisa-v2-llama3.3-70b", "provider": "nano-gpt", "model": "shisa-v2-llama3.3-70b", "displayName": "Shisa V2 Llama 3.3 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/shisa-ai/shisa-v2-llama3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "shisa-ai/shisa-v2-llama3.3-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Shisa V2 Llama 3.3 70B" ], "families": [ "llama" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "shisa-ai/shisa-v2-llama3.3-70b", "modelKey": "shisa-ai/shisa-v2-llama3.3-70b", "displayName": "Shisa V2 Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nano-gpt/shisa-v2.1-llama3.3-70b", "provider": "nano-gpt", "model": "shisa-v2.1-llama3.3-70b", "displayName": "Shisa V2.1 Llama 3.3 70B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/shisa-ai/shisa-v2.1-llama3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "shisa-ai/shisa-v2.1-llama3.3-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Shisa V2.1 Llama 3.3 70B" ], "families": [ "llama" ], "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "shisa-ai/shisa-v2.1-llama3.3-70b", "modelKey": "shisa-ai/shisa-v2.1-llama3.3-70b", "displayName": "Shisa V2.1 Llama 3.3 70B", "family": "llama", "metadata": { "lastUpdated": "2024-12-06", "openWeights": false, "releaseDate": "2024-12-06" } } ] }, { "id": "nano-gpt/skyfall-31b-v4.2", "provider": "nano-gpt", "model": "skyfall-31b-v4.2", "displayName": "TheDrummer Skyfall 31B v4.2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/Skyfall-31B-v4.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/Skyfall-31B-v4.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "TheDrummer Skyfall 31B v4.2" ], "releaseDate": "2026-03-26", "lastUpdated": "2026-03-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/Skyfall-31B-v4.2", "modelKey": "TheDrummer/Skyfall-31B-v4.2", "displayName": "TheDrummer Skyfall 31B v4.2", "metadata": { "lastUpdated": "2026-03-26", "openWeights": false, "releaseDate": "2026-03-26" } } ] }, { "id": "nano-gpt/skyfall-36b-v2", "provider": "nano-gpt", "model": "skyfall-36b-v2", "displayName": "TheDrummer Skyfall 36B V2", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/skyfall-36b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/skyfall-36b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.493, "output": 0.493 } } ] }, "metadata": { "displayNames": [ "TheDrummer Skyfall 36B V2" ], "releaseDate": "2025-03-10", "lastUpdated": "2025-03-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/skyfall-36b-v2", "modelKey": "TheDrummer/skyfall-36b-v2", "displayName": "TheDrummer Skyfall 36B V2", "metadata": { "lastUpdated": "2025-03-10", "openWeights": false, "releaseDate": "2025-03-10" } } ] }, { "id": "nano-gpt/solar-pro-3", "provider": "nano-gpt", "model": "solar-pro-3", "displayName": "Solar Pro 3", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/upstage/solar-pro-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "upstage/solar-pro-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Solar Pro 3" ], "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "upstage/solar-pro-3", "modelKey": "upstage/solar-pro-3", "displayName": "Solar Pro 3", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } } ] }, { "id": "nano-gpt/sonar", "provider": "nano-gpt", "model": "sonar", "displayName": "Perplexity Simple", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/sonar" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 127000, "inputTokens": 127000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.003, "output": 1.003 } } ] }, "metadata": { "displayNames": [ "Perplexity Simple" ], "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sonar", "modelKey": "sonar", "displayName": "Perplexity Simple", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } } ] }, { "id": "nano-gpt/starcannon-unleashed-12b-v1.0", "provider": "nano-gpt", "model": "starcannon-unleashed-12b-v1.0", "displayName": "Mistral Nemo Starcannon 12b v1", "family": "mistral-nemo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/VongolaChouko/Starcannon-Unleashed-12B-v1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "VongolaChouko/Starcannon-Unleashed-12B-v1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "Mistral Nemo Starcannon 12b v1" ], "families": [ "mistral-nemo" ], "releaseDate": "2024-07-01", "lastUpdated": "2024-07-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "VongolaChouko/Starcannon-Unleashed-12B-v1.0", "modelKey": "VongolaChouko/Starcannon-Unleashed-12B-v1.0", "displayName": "Mistral Nemo Starcannon 12b v1", "family": "mistral-nemo", "metadata": { "lastUpdated": "2024-07-01", "openWeights": false, "releaseDate": "2024-07-01" } } ] }, { "id": "nano-gpt/step-2-16k-exp", "provider": "nano-gpt", "model": "step-2-16k-exp", "displayName": "Step-2 16k Exp", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/step-2-16k-exp" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "step-2-16k-exp", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 7.004, "output": 19.992 } } ] }, "metadata": { "displayNames": [ "Step-2 16k Exp" ], "releaseDate": "2024-07-05", "lastUpdated": "2024-07-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "step-2-16k-exp", "modelKey": "step-2-16k-exp", "displayName": "Step-2 16k Exp", "metadata": { "lastUpdated": "2024-07-05", "openWeights": false, "releaseDate": "2024-07-05" } } ] }, { "id": "nano-gpt/step-2-mini", "provider": "nano-gpt", "model": "step-2-mini", "displayName": "Step-2 Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/step-2-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "step-2-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.408 } } ] }, "metadata": { "displayNames": [ "Step-2 Mini" ], "releaseDate": "2024-07-05", "lastUpdated": "2024-07-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "step-2-mini", "modelKey": "step-2-mini", "displayName": "Step-2 Mini", "metadata": { "lastUpdated": "2024-07-05", "openWeights": false, "releaseDate": "2024-07-05" } } ] }, { "id": "nano-gpt/step-3", "provider": "nano-gpt", "model": "step-3", "displayName": "Step-3", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/step-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "step-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2499, "output": 0.6494 } } ] }, "metadata": { "displayNames": [ "Step-3" ], "releaseDate": "2025-07-31", "lastUpdated": "2025-07-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "step-3", "modelKey": "step-3", "displayName": "Step-3", "metadata": { "lastUpdated": "2025-07-31", "openWeights": false, "releaseDate": "2025-07-31" } } ] }, { "id": "nano-gpt/step-3.5-flash", "provider": "nano-gpt", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "family": "step", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/stepfun-ai/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "stepfun-ai/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "families": [ "step" ], "releaseDate": "2026-02-02", "lastUpdated": "2026-02-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "stepfun-ai/step-3.5-flash", "modelKey": "stepfun-ai/step-3.5-flash", "displayName": "Step 3.5 Flash", "family": "step", "metadata": { "lastUpdated": "2026-02-02", "openWeights": false, "releaseDate": "2026-02-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "nano-gpt/step-3.5-flash-2603", "provider": "nano-gpt", "model": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/stepfun-ai/step-3.5-flash-2603" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "stepfun-ai/step-3.5-flash-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash 2603" ], "releaseDate": "2026-04-14", "lastUpdated": "2026-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "stepfun-ai/step-3.5-flash-2603", "modelKey": "stepfun-ai/step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "metadata": { "lastUpdated": "2026-04-14", "openWeights": false, "releaseDate": "2026-04-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "nano-gpt/step-3.7-flash:thinking", "provider": "nano-gpt", "model": "step-3.7-flash:thinking", "displayName": "Step 3.7 Flash Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/stepfun/step-3.7-flash:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "stepfun/step-3.7-flash:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash Thinking" ], "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "stepfun/step-3.7-flash:thinking", "modelKey": "stepfun/step-3.7-flash:thinking", "displayName": "Step 3.7 Flash Thinking", "metadata": { "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "nano-gpt/step-r1-v-mini", "provider": "nano-gpt", "model": "step-r1-v-mini", "displayName": "Step R1 V Mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/step-r1-v-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "step-r1-v-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 11 } } ] }, "metadata": { "displayNames": [ "Step R1 V Mini" ], "releaseDate": "2025-04-08", "lastUpdated": "2025-04-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "step-r1-v-mini", "modelKey": "step-r1-v-mini", "displayName": "Step R1 V Mini", "metadata": { "lastUpdated": "2025-04-08", "openWeights": false, "releaseDate": "2025-04-08" } } ] }, { "id": "nano-gpt/tongyi-deepresearch-30b-a3b", "provider": "nano-gpt", "model": "tongyi-deepresearch-30b-a3b", "displayName": "Tongyi DeepResearch 30B A3B", "family": "yi", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.24000000000000002 } } ] }, "metadata": { "displayNames": [ "Tongyi DeepResearch 30B A3B" ], "families": [ "yi" ], "releaseDate": "2025-08-26", "lastUpdated": "2025-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B", "modelKey": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B", "displayName": "Tongyi DeepResearch 30B A3B", "family": "yi", "metadata": { "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } } ] }, { "id": "nano-gpt/trinity-large-thinking", "provider": "nano-gpt", "model": "trinity-large-thinking", "displayName": "Trinity Large Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/arcee-ai/trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "arcee-ai/trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Trinity Large Thinking" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "arcee-ai/trinity-large-thinking", "modelKey": "arcee-ai/trinity-large-thinking", "displayName": "Trinity Large Thinking", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } } ] }, { "id": "nano-gpt/trinity-mini", "provider": "nano-gpt", "model": "trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/arcee-ai/trinity-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "arcee-ai/trinity-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045000000000000005, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Trinity Mini" ], "families": [ "trinity-mini" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "arcee-ai/trinity-mini", "modelKey": "arcee-ai/trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "metadata": { "lastUpdated": "2025-12-01", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "nano-gpt/universal-summarizer", "provider": "nano-gpt", "model": "universal-summarizer", "displayName": "Universal Summarizer", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/universal-summarizer" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "universal-summarizer", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 30 } } ] }, "metadata": { "displayNames": [ "Universal Summarizer" ], "releaseDate": "2023-05-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "universal-summarizer", "modelKey": "universal-summarizer", "displayName": "Universal Summarizer", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-05-01" } } ] }, { "id": "nano-gpt/unslopnemo-12b-v4.1", "provider": "nano-gpt", "model": "unslopnemo-12b-v4.1", "displayName": "UnslopNemo 12b v4", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TheDrummer/UnslopNemo-12B-v4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TheDrummer/UnslopNemo-12B-v4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.493, "output": 0.493 } } ] }, "metadata": { "displayNames": [ "UnslopNemo 12b v4" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TheDrummer/UnslopNemo-12B-v4.1", "modelKey": "TheDrummer/UnslopNemo-12B-v4.1", "displayName": "UnslopNemo 12b v4", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "nano-gpt/v0-1.0-md", "provider": "nano-gpt", "model": "v0-1.0-md", "displayName": "v0 1.0 MD", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/v0-1.0-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "v0-1.0-md", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "v0 1.0 MD" ], "releaseDate": "2025-07-04", "lastUpdated": "2025-07-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "v0-1.0-md", "modelKey": "v0-1.0-md", "displayName": "v0 1.0 MD", "metadata": { "lastUpdated": "2025-07-04", "openWeights": false, "releaseDate": "2025-07-04" } } ] }, { "id": "nano-gpt/v0-1.5-lg", "provider": "nano-gpt", "model": "v0-1.5-lg", "displayName": "v0 1.5 LG", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/v0-1.5-lg" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "v0-1.5-lg", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "v0 1.5 LG" ], "releaseDate": "2025-07-04", "lastUpdated": "2025-07-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "v0-1.5-lg", "modelKey": "v0-1.5-lg", "displayName": "v0 1.5 LG", "metadata": { "lastUpdated": "2025-07-04", "openWeights": false, "releaseDate": "2025-07-04" } } ] }, { "id": "nano-gpt/v0-1.5-md", "provider": "nano-gpt", "model": "v0-1.5-md", "displayName": "v0 1.5 MD", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/v0-1.5-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "v0-1.5-md", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "v0 1.5 MD" ], "releaseDate": "2025-07-04", "lastUpdated": "2025-07-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "v0-1.5-md", "modelKey": "v0-1.5-md", "displayName": "v0 1.5 MD", "metadata": { "lastUpdated": "2025-07-04", "openWeights": false, "releaseDate": "2025-07-04" } } ] }, { "id": "nano-gpt/veiled-calla-12b", "provider": "nano-gpt", "model": "veiled-calla-12b", "displayName": "Veiled Calla 12B", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/soob3123/Veiled-Calla-12B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "soob3123/Veiled-Calla-12B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Veiled Calla 12B" ], "families": [ "llama" ], "releaseDate": "2025-04-13", "lastUpdated": "2025-04-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "soob3123/Veiled-Calla-12B", "modelKey": "soob3123/Veiled-Calla-12B", "displayName": "Veiled Calla 12B", "family": "llama", "metadata": { "lastUpdated": "2025-04-13", "openWeights": false, "releaseDate": "2025-04-13" } } ] }, { "id": "nano-gpt/venice-uncensored", "provider": "nano-gpt", "model": "venice-uncensored", "displayName": "Venice Uncensored", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/venice-uncensored" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "venice-uncensored", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Venice Uncensored" ], "releaseDate": "2025-02-24", "lastUpdated": "2025-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "venice-uncensored", "modelKey": "venice-uncensored", "displayName": "Venice Uncensored", "metadata": { "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24" } } ] }, { "id": "nano-gpt/venice-uncensored:web", "provider": "nano-gpt", "model": "venice-uncensored:web", "displayName": "Venice Uncensored Web", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/venice-uncensored:web" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 80000, "inputTokens": 80000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "venice-uncensored:web", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Venice Uncensored Web" ], "releaseDate": "2024-05-01", "lastUpdated": "2024-05-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "venice-uncensored:web", "modelKey": "venice-uncensored:web", "displayName": "Venice Uncensored Web", "metadata": { "lastUpdated": "2024-05-01", "openWeights": false, "releaseDate": "2024-05-01" } } ] }, { "id": "nano-gpt/wayfarer-large-70b-llama-3.3", "provider": "nano-gpt", "model": "wayfarer-large-70b-llama-3.3", "displayName": "Llama 3.3 70B Wayfarer", "family": "llama", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.700000007, "output": 0.700000007 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 70B Wayfarer" ], "families": [ "llama" ], "releaseDate": "2025-02-20", "lastUpdated": "2025-02-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3", "modelKey": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3", "displayName": "Llama 3.3 70B Wayfarer", "family": "llama", "metadata": { "lastUpdated": "2025-02-20", "openWeights": false, "releaseDate": "2025-02-20" } } ] }, { "id": "nano-gpt/wizardlm-2-8x22b", "provider": "nano-gpt", "model": "wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/microsoft/wizardlm-2-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "microsoft/wizardlm-2-8x22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49299999999999994, "output": 0.49299999999999994 } } ] }, "metadata": { "displayNames": [ "WizardLM-2 8x22B" ], "families": [ "gpt" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "microsoft/wizardlm-2-8x22b", "modelKey": "microsoft/wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "family": "gpt", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "nano-gpt/yi-large", "provider": "nano-gpt", "model": "yi-large", "displayName": "Yi Large", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/yi-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "yi-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.196, "output": 3.196 } } ] }, "metadata": { "displayNames": [ "Yi Large" ], "releaseDate": "2024-05-13", "lastUpdated": "2024-05-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "yi-large", "modelKey": "yi-large", "displayName": "Yi Large", "metadata": { "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } } ] }, { "id": "nano-gpt/yi-lightning", "provider": "nano-gpt", "model": "yi-lightning", "displayName": "Yi Lightning", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/yi-lightning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 12000, "inputTokens": 12000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "yi-lightning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "Yi Lightning" ], "releaseDate": "2024-10-16", "lastUpdated": "2024-10-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "yi-lightning", "modelKey": "yi-lightning", "displayName": "Yi Lightning", "metadata": { "lastUpdated": "2024-10-16", "openWeights": false, "releaseDate": "2024-10-16" } } ] }, { "id": "nano-gpt/yi-medium-200k", "provider": "nano-gpt", "model": "yi-medium-200k", "displayName": "Yi Medium 200k", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/yi-medium-200k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "yi-medium-200k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 2.499 } } ] }, "metadata": { "displayNames": [ "Yi Medium 200k" ], "releaseDate": "2024-03-01", "lastUpdated": "2024-03-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "yi-medium-200k", "modelKey": "yi-medium-200k", "displayName": "Yi Medium 200k", "metadata": { "lastUpdated": "2024-03-01", "openWeights": false, "releaseDate": "2024-03-01" } } ] }, { "id": "nearai/flux.2-klein-4b", "provider": "nearai", "model": "flux.2-klein-4b", "displayName": "FLUX.2 Klein 4B", "family": "flux", "sources": [ "models.dev" ], "providers": [ "nearai" ], "aliases": [ "nearai/black-forest-labs/FLUX.2-klein-4B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nearai", "model": "black-forest-labs/FLUX.2-klein-4B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "FLUX.2 Klein 4B" ], "families": [ "flux" ], "releaseDate": "2026-01-14", "lastUpdated": "2026-01-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "black-forest-labs/FLUX.2-klein-4B", "modelKey": "black-forest-labs/FLUX.2-klein-4B", "displayName": "FLUX.2 Klein 4B", "family": "flux", "metadata": { "lastUpdated": "2026-01-14", "openWeights": true, "releaseDate": "2026-01-14" } } ] }, { "id": "nebius/bge-en-icl", "provider": "nebius", "model": "bge-en-icl", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "nebius" ], "aliases": [ "nebius/BAAI/bge-en-icl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nebius", "model": "nebius/BAAI/bge-en-icl", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/BAAI/bge-en-icl", "mode": "embedding", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "nebius/bge-multilingual-gemma2", "provider": "nebius", "model": "bge-multilingual-gemma2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "nebius" ], "aliases": [ "nebius/BAAI/bge-multilingual-gemma2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nebius", "model": "nebius/BAAI/bge-multilingual-gemma2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/BAAI/bge-multilingual-gemma2", "mode": "embedding", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "nebius/e5-mistral-7b-instruct", "provider": "nebius", "model": "e5-mistral-7b-instruct", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "nebius" ], "aliases": [ "nebius/intfloat/e5-mistral-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nebius", "model": "nebius/intfloat/e5-mistral-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/intfloat/e5-mistral-7b-instruct", "mode": "embedding", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "nebius/hermes-3-llama-3.1-405b", "provider": "nebius", "model": "hermes-3-llama-3.1-405b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nebius" ], "aliases": [ "nebius/NousResearch/Hermes-3-Llama-3.1-405B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nebius", "model": "nebius/NousResearch/Hermes-3-Llama-3.1-405B", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nebius", "model": "nebius/NousResearch/Hermes-3-Llama-3.1-405B", "mode": "chat", "metadata": { "source": "https://nebius.com/prices-ai-studio" } } ] }, { "id": "nebius/hermes-4-405b", "provider": "nebius", "model": "hermes-4-405b", "displayName": "Hermes-4-405B", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/NousResearch/Hermes-4-405B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 120000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "NousResearch/Hermes-4-405B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 3, "reasoningOutput": 3 } } ] }, "metadata": { "displayNames": [ "Hermes-4-405B" ], "knowledgeCutoff": "2025-11", "releaseDate": "2026-01-30", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "NousResearch/Hermes-4-405B", "modelKey": "NousResearch/Hermes-4-405B", "displayName": "Hermes-4-405B", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-30" } } ] }, { "id": "nebius/hermes-4-70b", "provider": "nebius", "model": "hermes-4-70b", "displayName": "Hermes-4-70B", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/NousResearch/Hermes-4-70B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 120000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "NousResearch/Hermes-4-70B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.013, "cacheWrite": 0.16, "input": 0.13, "output": 0.4, "reasoningOutput": 0.4 } } ] }, "metadata": { "displayNames": [ "Hermes-4-70B" ], "knowledgeCutoff": "2025-11", "releaseDate": "2026-01-30", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "NousResearch/Hermes-4-70B", "modelKey": "NousResearch/Hermes-4-70B", "displayName": "Hermes-4-70B", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-30" } } ] }, { "id": "nebius/intellect-3", "provider": "nebius", "model": "intellect-3", "displayName": "INTELLECT-3", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/PrimeIntellect/INTELLECT-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 120000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "PrimeIntellect/INTELLECT-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.25, "input": 0.2, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "INTELLECT-3" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-10", "releaseDate": "2026-01-25", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "PrimeIntellect/INTELLECT-3", "modelKey": "PrimeIntellect/INTELLECT-3", "displayName": "INTELLECT-3", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-10", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-25" } } ] }, { "id": "nebius/nemotron-3-nano-omni", "provider": "nebius", "model": "nemotron-3-nano-omni", "displayName": "Nemotron-3-Nano-Omni", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/nvidia/Nemotron-3-Nano-Omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "inputTokens": 60000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "nvidia/Nemotron-3-Nano-Omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.006, "cacheWrite": 0.075, "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Nemotron-3-Nano-Omni" ], "families": [ "nemotron" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-20", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "nvidia/Nemotron-3-Nano-Omni", "modelKey": "nvidia/Nemotron-3-Nano-Omni", "displayName": "Nemotron-3-Nano-Omni", "family": "nemotron", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-01-20" } } ] }, { "id": "nebius/nemotron-3-super-120b-a12b", "provider": "nebius", "model": "nemotron-3-super-120b-a12b", "displayName": "Nemotron-3-Super-120B-A12B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Nemotron-3-Super-120B-A12B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "Nemotron-3-Super-120B-A12B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "nebius/nvidia-nemotron-3-nano-30b-a3b", "provider": "nebius", "model": "nvidia-nemotron-3-nano-30b-a3b", "displayName": "Nemotron-3-Nano-30B-A3B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 30000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.006, "cacheWrite": 0.075, "input": 0.06, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Nemotron-3-Nano-30B-A3B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-08-10", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "modelKey": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "displayName": "Nemotron-3-Nano-30B-A3B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-08-10" } } ] }, { "id": "nlp-cloud/chatdolphin", "provider": "nlp-cloud", "model": "chatdolphin", "mode": "chat", "sources": [ "litellm" ], "providers": [ "nlp_cloud" ], "aliases": [ "nlp_cloud/chatdolphin" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nlp_cloud", "model": "chatdolphin", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nlp_cloud", "model": "chatdolphin", "mode": "chat" } ] }, { "id": "nlp-cloud/dolphin", "provider": "nlp-cloud", "model": "dolphin", "mode": "completion", "sources": [ "litellm" ], "providers": [ "nlp_cloud" ], "aliases": [ "nlp_cloud/dolphin" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nlp_cloud", "model": "dolphin", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nlp_cloud", "model": "dolphin", "mode": "completion" } ] }, { "id": "novita-ai/baichuan-m2-32b", "provider": "novita-ai", "model": "baichuan-m2-32b", "displayName": "baichuan-m2-32b", "family": "baichuan", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baichuan/baichuan-m2-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baichuan/baichuan-m2-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.07 } } ] }, "metadata": { "displayNames": [ "baichuan-m2-32b" ], "families": [ "baichuan" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-08-13", "lastUpdated": "2025-08-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baichuan/baichuan-m2-32b", "modelKey": "baichuan/baichuan-m2-32b", "displayName": "baichuan-m2-32b", "family": "baichuan", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-08-13", "openWeights": true, "releaseDate": "2025-08-13" } } ] }, { "id": "novita-ai/ernie-4.5-21b-a3b", "provider": "novita-ai", "model": "ernie-4.5-21b-a3b", "displayName": "ERNIE 4.5 21B A3B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-21B-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-21B-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 21B A3B" ], "families": [ "ernie" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-21B-a3b", "modelKey": "baidu/ernie-4.5-21B-a3b", "displayName": "ERNIE 4.5 21B A3B", "family": "ernie", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "novita-ai/ernie-4.5-21b-a3b-thinking", "provider": "novita-ai", "model": "ernie-4.5-21b-a3b-thinking", "displayName": "ERNIE-4.5-21B-A3B-Thinking", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-21B-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-21B-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "ERNIE-4.5-21B-A3B-Thinking" ], "families": [ "ernie" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-09-19", "lastUpdated": "2025-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-21B-a3b-thinking", "modelKey": "baidu/ernie-4.5-21B-a3b-thinking", "displayName": "ERNIE-4.5-21B-A3B-Thinking", "family": "ernie", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-09-19", "openWeights": true, "releaseDate": "2025-09-19" } } ] }, { "id": "novita-ai/ernie-4.5-300b-a47b-paddle", "provider": "novita-ai", "model": "ernie-4.5-300b-a47b-paddle", "displayName": "ERNIE 4.5 300B A47B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-300b-a47b-paddle" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-300b-a47b-paddle", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 300B A47B" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-300b-a47b-paddle", "modelKey": "baidu/ernie-4.5-300b-a47b-paddle", "displayName": "ERNIE 4.5 300B A47B", "metadata": { "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "novita-ai/ernie-4.5-vl-28b-a3b", "provider": "novita-ai", "model": "ernie-4.5-vl-28b-a3b", "displayName": "ERNIE 4.5 VL 28B A3B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-vl-28b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 30000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-vl-28b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.56 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 VL 28B A3B" ], "releaseDate": "2025-06-30", "lastUpdated": "2026-06-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-vl-28b-a3b", "modelKey": "baidu/ernie-4.5-vl-28b-a3b", "displayName": "ERNIE 4.5 VL 28B A3B", "metadata": { "lastUpdated": "2026-06-14", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "novita-ai/ernie-4.5-vl-28b-a3b-thinking", "provider": "novita-ai", "model": "ernie-4.5-vl-28b-a3b-thinking", "displayName": "ERNIE-4.5-VL-28B-A3B-Thinking", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-vl-28b-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-vl-28b-a3b-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.39, "output": 0.39 } } ] }, "metadata": { "displayNames": [ "ERNIE-4.5-VL-28B-A3B-Thinking" ], "releaseDate": "2025-11-26", "lastUpdated": "2025-11-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-vl-28b-a3b-thinking", "modelKey": "baidu/ernie-4.5-vl-28b-a3b-thinking", "displayName": "ERNIE-4.5-VL-28B-A3B-Thinking", "metadata": { "lastUpdated": "2025-11-26", "openWeights": true, "releaseDate": "2025-11-26" } } ] }, { "id": "novita-ai/ernie-4.5-vl-424b-a47b", "provider": "novita-ai", "model": "ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/baidu/ernie-4.5-vl-424b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.42, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "ERNIE 4.5 VL 424B A47B" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "baidu/ernie-4.5-vl-424b-a47b", "modelKey": "baidu/ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "metadata": { "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } } ] }, { "id": "novita-ai/hermes-2-pro-llama-3-8b", "provider": "novita-ai", "model": "hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/nousresearch/hermes-2-pro-llama-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "nousresearch/hermes-2-pro-llama-3-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Hermes 2 Pro Llama 3 8B" ], "releaseDate": "2024-06-27", "lastUpdated": "2024-06-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "nousresearch/hermes-2-pro-llama-3-8b", "modelKey": "nousresearch/hermes-2-pro-llama-3-8b", "displayName": "Hermes 2 Pro Llama 3 8B", "metadata": { "lastUpdated": "2024-06-27", "openWeights": true, "releaseDate": "2024-06-27" } } ] }, { "id": "novita-ai/kat-coder-pro", "provider": "novita-ai", "model": "kat-coder-pro", "displayName": "Kat Coder Pro", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/kwaipilot/kat-coder-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "kwaipilot/kat-coder-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Kat Coder Pro" ], "releaseDate": "2026-01-05", "lastUpdated": "2026-01-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "kwaipilot/kat-coder-pro", "modelKey": "kwaipilot/kat-coder-pro", "displayName": "Kat Coder Pro", "metadata": { "lastUpdated": "2026-01-05", "openWeights": true, "releaseDate": "2026-01-05" } } ] }, { "id": "novita-ai/l3-70b-euryale-v2.1", "provider": "novita-ai", "model": "l3-70b-euryale-v2.1", "displayName": "L3 70B Euryale V2.1", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/sao10K/l3-70b-euryale-v2.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "sao10K/l3-70b-euryale-v2.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.48, "output": 1.48 } } ] }, "metadata": { "displayNames": [ "L3 70B Euryale V2.1" ], "releaseDate": "2024-06-18", "lastUpdated": "2024-06-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "sao10K/l3-70b-euryale-v2.1", "modelKey": "sao10K/l3-70b-euryale-v2.1", "displayName": "L3 70B Euryale V2.1", "metadata": { "lastUpdated": "2024-06-18", "openWeights": true, "releaseDate": "2024-06-18" } } ] }, { "id": "novita-ai/l3-8b-lunaris", "provider": "novita-ai", "model": "l3-8b-lunaris", "displayName": "Sao10k L3 8B Lunaris", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/sao10K/l3-8b-lunaris" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "sao10K/l3-8b-lunaris", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "Sao10k L3 8B Lunaris" ], "releaseDate": "2024-11-28", "lastUpdated": "2024-11-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "sao10K/l3-8b-lunaris", "modelKey": "sao10K/l3-8b-lunaris", "displayName": "Sao10k L3 8B Lunaris", "metadata": { "lastUpdated": "2024-11-28", "openWeights": true, "releaseDate": "2024-11-28" } } ] }, { "id": "novita-ai/l3-8b-stheno-v3.2", "provider": "novita-ai", "model": "l3-8b-stheno-v3.2", "displayName": "L3 8B Stheno V3.2", "family": "llama", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/sao10K/L3-8B-stheno-v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "sao10K/L3-8B-stheno-v3.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "L3 8B Stheno V3.2" ], "families": [ "llama" ], "releaseDate": "2024-11-29", "lastUpdated": "2024-11-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "sao10K/L3-8B-stheno-v3.2", "modelKey": "sao10K/L3-8B-stheno-v3.2", "displayName": "L3 8B Stheno V3.2", "family": "llama", "metadata": { "lastUpdated": "2024-11-29", "openWeights": true, "releaseDate": "2024-11-29" } } ] }, { "id": "novita-ai/l31-70b-euryale-v2.2", "provider": "novita-ai", "model": "l31-70b-euryale-v2.2", "displayName": "L31 70B Euryale V2.2", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/sao10K/l31-70b-euryale-v2.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "sao10K/l31-70b-euryale-v2.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.48, "output": 1.48 } } ] }, "metadata": { "displayNames": [ "L31 70B Euryale V2.2" ], "releaseDate": "2024-09-19", "lastUpdated": "2024-09-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "sao10K/l31-70b-euryale-v2.2", "modelKey": "sao10K/l31-70b-euryale-v2.2", "displayName": "L31 70B Euryale V2.2", "metadata": { "lastUpdated": "2024-09-19", "openWeights": true, "releaseDate": "2024-09-19" } } ] }, { "id": "novita-ai/ling-2.6-1t", "provider": "novita-ai", "model": "ling-2.6-1t", "displayName": "Ling-2.6-1T", "family": "ling", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/inclusionai/ling-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "inclusionai/ling-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Ling-2.6-1T" ], "families": [ "ling" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "inclusionai/ling-2.6-1t", "modelKey": "inclusionai/ling-2.6-1t", "displayName": "Ling-2.6-1T", "family": "ling", "metadata": { "lastUpdated": "2026-04-23", "openWeights": true, "releaseDate": "2026-04-23" } } ] }, { "id": "novita-ai/ling-2.6-flash", "provider": "novita-ai", "model": "ling-2.6-flash", "displayName": "Ling-2.6-flash", "family": "ling", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/inclusionai/ling-2.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "inclusionai/ling-2.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Ling-2.6-flash" ], "families": [ "ling" ], "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "inclusionai/ling-2.6-flash", "modelKey": "inclusionai/ling-2.6-flash", "displayName": "Ling-2.6-flash", "family": "ling", "metadata": { "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "novita-ai/mimo-v2-flash", "provider": "novita-ai", "model": "mimo-v2-flash", "displayName": "XiaomiMiMo/MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/xiaomimimo/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "xiaomimimo/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "XiaomiMiMo/MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-19", "lastUpdated": "2025-12-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "xiaomimimo/mimo-v2-flash", "modelKey": "xiaomimimo/mimo-v2-flash", "displayName": "XiaomiMiMo/MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-19", "openWeights": true, "releaseDate": "2025-12-19" } } ] }, { "id": "novita-ai/mimo-v2-pro", "provider": "novita-ai", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/xiaomimimo/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "xiaomimimo/mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 2, "output": 6 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "xiaomimimo/mimo-v2-pro", "modelKey": "xiaomimimo/mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "novita-ai/mimo-v2.5-pro", "provider": "novita-ai", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/xiaomimimo/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "xiaomimimo/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 2, "output": 6 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "xiaomimimo/mimo-v2.5-pro", "modelKey": "xiaomimimo/mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-05-27", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "novita-ai/mythomax-l2-13b", "provider": "novita-ai", "model": "mythomax-l2-13b", "displayName": "Mythomax L2 13B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/gryphe/mythomax-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 3200, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "gryphe/mythomax-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.09 } } ] }, "metadata": { "displayNames": [ "Mythomax L2 13B" ], "releaseDate": "2024-04-25", "lastUpdated": "2024-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "gryphe/mythomax-l2-13b", "modelKey": "gryphe/mythomax-l2-13b", "displayName": "Mythomax L2 13B", "metadata": { "lastUpdated": "2024-04-25", "openWeights": true, "releaseDate": "2024-04-25" } } ] }, { "id": "novita-ai/paddleocr-vl", "provider": "novita-ai", "model": "paddleocr-vl", "displayName": "PaddleOCR-VL", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/paddlepaddle/paddleocr-vl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "paddlepaddle/paddleocr-vl", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.02 } } ] }, "metadata": { "displayNames": [ "PaddleOCR-VL" ], "releaseDate": "2025-10-22", "lastUpdated": "2025-10-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "paddlepaddle/paddleocr-vl", "modelKey": "paddlepaddle/paddleocr-vl", "displayName": "PaddleOCR-VL", "metadata": { "lastUpdated": "2025-10-22", "openWeights": true, "releaseDate": "2025-10-22" } } ] }, { "id": "novita-ai/ring-2.6-1t", "provider": "novita-ai", "model": "ring-2.6-1t", "displayName": "Ring-2.6-1T", "family": "ring", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/inclusionai/ring-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Ring-2.6-1T" ], "families": [ "ring" ], "releaseDate": "2026-05-08", "lastUpdated": "2026-05-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "inclusionai/ring-2.6-1t", "modelKey": "inclusionai/ring-2.6-1t", "displayName": "Ring-2.6-1T", "family": "ring", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-05-08" } } ] }, { "id": "novita-ai/wizardlm-2-8x22b", "provider": "novita-ai", "model": "wizardlm-2-8x22b", "displayName": "Wizardlm 2 8x22B", "sources": [ "models.dev" ], "providers": [ "novita-ai" ], "aliases": [ "novita-ai/microsoft/wizardlm-2-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65535, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "microsoft/wizardlm-2-8x22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.62, "output": 0.62 } } ] }, "metadata": { "displayNames": [ "Wizardlm 2 8x22B" ], "releaseDate": "2024-04-24", "lastUpdated": "2024-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "microsoft/wizardlm-2-8x22b", "modelKey": "microsoft/wizardlm-2-8x22b", "displayName": "Wizardlm 2 8x22B", "metadata": { "lastUpdated": "2024-04-24", "openWeights": true, "releaseDate": "2024-04-24" } } ] }, { "id": "novita/baichuan-m2-32b", "provider": "novita", "model": "baichuan-m2-32b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baichuan/baichuan-m2-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baichuan/baichuan-m2-32b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.07 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baichuan/baichuan-m2-32b", "mode": "chat" } ] }, { "id": "novita/bge-m3", "provider": "novita", "model": "bge-m3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baai/bge-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 96000, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baai/bge-m3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baai/bge-m3", "mode": "embedding" } ] }, { "id": "novita/bge-reranker-v2-m3", "provider": "novita", "model": "bge-reranker-v2-m3", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baai/bge-reranker-v2-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baai/bge-reranker-v2-m3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.01, "output": 0.01 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baai/bge-reranker-v2-m3", "mode": "rerank" } ] }, { "id": "novita/ernie-4.5-21b-a3b", "provider": "novita", "model": "ernie-4.5-21b-a3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-21B-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "inputTokens": 120000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-21B-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-21B-a3b", "mode": "chat" } ] }, { "id": "novita/ernie-4.5-21b-a3b-thinking", "provider": "novita", "model": "ernie-4.5-21b-a3b-thinking", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-21B-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-21B-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-21B-a3b-thinking", "mode": "chat" } ] }, { "id": "novita/ernie-4.5-300b-a47b-paddle", "provider": "novita", "model": "ernie-4.5-300b-a47b-paddle", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-300b-a47b-paddle" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "inputTokens": 123000, "maxTokens": 12000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-300b-a47b-paddle", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-300b-a47b-paddle", "mode": "chat" } ] }, { "id": "novita/ernie-4.5-vl-28b-a3b", "provider": "novita", "model": "ernie-4.5-vl-28b-a3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-vl-28b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 30000, "inputTokens": 30000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-28b-a3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-28b-a3b", "mode": "chat" } ] }, { "id": "novita/ernie-4.5-vl-28b-a3b-thinking", "provider": "novita", "model": "ernie-4.5-vl-28b-a3b-thinking", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-vl-28b-a3b-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-28b-a3b-thinking", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.39, "output": 0.39 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-28b-a3b-thinking", "mode": "chat" } ] }, { "id": "novita/ernie-4.5-vl-424b-a47b", "provider": "novita", "model": "ernie-4.5-vl-424b-a47b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/baidu/ernie-4.5-vl-424b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 123000, "inputTokens": 123000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.42, "output": 1.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/baidu/ernie-4.5-vl-424b-a47b", "mode": "chat" } ] }, { "id": "novita/hermes-2-pro-llama-3-8b", "provider": "novita", "model": "hermes-2-pro-llama-3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/nousresearch/hermes-2-pro-llama-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/nousresearch/hermes-2-pro-llama-3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.14 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/nousresearch/hermes-2-pro-llama-3-8b", "mode": "chat" } ] }, { "id": "novita/kat-coder-pro", "provider": "novita", "model": "kat-coder-pro", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/kwaipilot/kat-coder-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/kwaipilot/kat-coder-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 }, "extra": { "input_cost_per_token_cache_hit": 6e-8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/kwaipilot/kat-coder-pro", "mode": "chat" } ] }, { "id": "novita/l3-70b-euryale-v2.1", "provider": "novita", "model": "l3-70b-euryale-v2.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/sao10k/l3-70b-euryale-v2.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/sao10k/l3-70b-euryale-v2.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.48, "output": 1.48 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/sao10k/l3-70b-euryale-v2.1", "mode": "chat" } ] }, { "id": "novita/l3-8b-lunaris", "provider": "novita", "model": "l3-8b-lunaris", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/sao10k/l3-8b-lunaris" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/sao10k/l3-8b-lunaris", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/sao10k/l3-8b-lunaris", "mode": "chat" } ] }, { "id": "novita/l3-8b-stheno-v3.2", "provider": "novita", "model": "l3-8b-stheno-v3.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/Sao10K/L3-8B-Stheno-v3.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/Sao10K/L3-8B-Stheno-v3.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/Sao10K/L3-8B-Stheno-v3.2", "mode": "chat" } ] }, { "id": "novita/l31-70b-euryale-v2.2", "provider": "novita", "model": "l31-70b-euryale-v2.2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/sao10k/l31-70b-euryale-v2.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/sao10k/l31-70b-euryale-v2.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.48, "output": 1.48 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/sao10k/l31-70b-euryale-v2.2", "mode": "chat" } ] }, { "id": "novita/mimo-v2-flash", "provider": "novita", "model": "mimo-v2-flash", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/xiaomimimo/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/xiaomimimo/mimo-v2-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 }, "extra": { "input_cost_per_token_cache_hit": 2e-8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/xiaomimimo/mimo-v2-flash", "mode": "chat" } ] }, { "id": "novita/mythomax-l2-13b", "provider": "novita", "model": "mythomax-l2-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/gryphe/mythomax-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 3200, "outputTokens": 3200, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/gryphe/mythomax-l2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.09 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/gryphe/mythomax-l2-13b", "mode": "chat" } ] }, { "id": "novita/paddleocr-vl", "provider": "novita", "model": "paddleocr-vl", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/paddlepaddle/paddleocr-vl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/paddlepaddle/paddleocr-vl", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.02 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/paddlepaddle/paddleocr-vl", "mode": "chat" } ] }, { "id": "novita/r1v4-lite", "provider": "novita", "model": "r1v4-lite", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/skywork/r1v4-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/skywork/r1v4-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/skywork/r1v4-lite", "mode": "chat" } ] }, { "id": "novita/wizardlm-2-8x22b", "provider": "novita", "model": "wizardlm-2-8x22b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "novita" ], "aliases": [ "novita/microsoft/wizardlm-2-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65535, "inputTokens": 65535, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "novita", "model": "novita/microsoft/wizardlm-2-8x22b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 0.62 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/microsoft/wizardlm-2-8x22b", "mode": "chat" } ] }, { "id": "nscale/flux.1-schnell", "provider": "nscale", "model": "flux.1-schnell", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "nscale" ], "aliases": [ "nscale/black-forest-labs/FLUX.1-schnell" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nscale", "model": "nscale/black-forest-labs/FLUX.1-schnell", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.3e-9, "output": 0 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/black-forest-labs/FLUX.1-schnell", "mode": "image_generation", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "nscale/stable-diffusion-xl-base-1.0", "provider": "nscale", "model": "stable-diffusion-xl-base-1.0", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "nscale" ], "aliases": [ "nscale/stabilityai/stable-diffusion-xl-base-1.0" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nscale", "model": "nscale/stabilityai/stable-diffusion-xl-base-1.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 3e-9, "output": 0 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nscale", "model": "nscale/stabilityai/stable-diffusion-xl-base-1.0", "mode": "image_generation", "metadata": { "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "nvidia-nim/nv-rerankqa-mistral-4b-v3", "provider": "nvidia-nim", "model": "nv-rerankqa-mistral-4b-v3", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "nvidia_nim" ], "aliases": [ "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "nvidia_nim", "model": "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 }, "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "nvidia_nim", "model": "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3", "mode": "rerank" } ] }, { "id": "nvidia/active-speaker-detection", "provider": "nvidia", "model": "active-speaker-detection", "displayName": "Active Speaker Detection", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/active-speaker-detection" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/active-speaker-detection", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Active Speaker Detection" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/active-speaker-detection", "modelKey": "nvidia/active-speaker-detection", "displayName": "Active Speaker Detection", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-04-16" } } ] }, { "id": "nvidia/bevformer", "provider": "nvidia", "model": "bevformer", "displayName": "bevformer", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/bevformer" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/bevformer", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "bevformer" ], "releaseDate": "2025-03-18", "lastUpdated": "2025-07-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/bevformer", "modelKey": "nvidia/bevformer", "displayName": "bevformer", "metadata": { "lastUpdated": "2025-07-20", "openWeights": true, "releaseDate": "2025-03-18" } } ] }, { "id": "nvidia/bge-m3", "provider": "nvidia", "model": "bge-m3", "displayName": "BGE M3", "family": "bge", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/baai/bge-m3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "baai/bge-m3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE M3" ], "families": [ "bge" ], "releaseDate": "2024-01-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "baai/bge-m3", "modelKey": "baai/bge-m3", "displayName": "BGE M3", "family": "bge", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2024-01-30" } } ] }, { "id": "nvidia/cosmos-predict1-5b", "provider": "nvidia", "model": "cosmos-predict1-5b", "displayName": "cosmos-predict1-5b", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/cosmos-predict1-5b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/cosmos-predict1-5b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "cosmos-predict1-5b" ], "releaseDate": "2025-03-18", "lastUpdated": "2025-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/cosmos-predict1-5b", "modelKey": "nvidia/cosmos-predict1-5b", "displayName": "cosmos-predict1-5b", "metadata": { "lastUpdated": "2025-03-18", "openWeights": true, "releaseDate": "2025-03-18" } } ] }, { "id": "nvidia/cosmos-transfer1-7b", "provider": "nvidia", "model": "cosmos-transfer1-7b", "displayName": "cosmos-transfer1-7b", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/cosmos-transfer1-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/cosmos-transfer1-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "cosmos-transfer1-7b" ], "releaseDate": "2025-06-13", "lastUpdated": "2025-06-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/cosmos-transfer1-7b", "modelKey": "nvidia/cosmos-transfer1-7b", "displayName": "cosmos-transfer1-7b", "metadata": { "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-13" } } ] }, { "id": "nvidia/cosmos-transfer2-5-2b", "provider": "nvidia", "model": "cosmos-transfer2-5-2b", "displayName": "cosmos-transfer2.5-2b", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/cosmos-transfer2_5-2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/cosmos-transfer2_5-2b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "cosmos-transfer2.5-2b" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-02-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/cosmos-transfer2_5-2b", "modelKey": "nvidia/cosmos-transfer2_5-2b", "displayName": "cosmos-transfer2.5-2b", "metadata": { "lastUpdated": "2026-02-26", "openWeights": true, "releaseDate": "2026-02-26" } } ] }, { "id": "nvidia/dracarys-llama-3-1-70b-instruct", "provider": "nvidia", "model": "dracarys-llama-3-1-70b-instruct", "displayName": "dracarys-llama-3.1-70b-instruct", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/abacusai/dracarys-llama-3_1-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "abacusai/dracarys-llama-3_1-70b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "dracarys-llama-3.1-70b-instruct" ], "releaseDate": "2024-09-11", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "abacusai/dracarys-llama-3_1-70b-instruct", "modelKey": "abacusai/dracarys-llama-3_1-70b-instruct", "displayName": "dracarys-llama-3.1-70b-instruct", "metadata": { "lastUpdated": "2025-05-22", "openWeights": true, "releaseDate": "2024-09-11" } } ] }, { "id": "nvidia/flux-1-kontext-dev", "provider": "nvidia", "model": "flux-1-kontext-dev", "displayName": "FLUX.1-Kontext-dev", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/black-forest-labs/flux_1-kontext-dev" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "black-forest-labs/flux_1-kontext-dev", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "FLUX.1-Kontext-dev" ], "releaseDate": "2025-08-12", "lastUpdated": "2025-08-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "black-forest-labs/flux_1-kontext-dev", "modelKey": "black-forest-labs/flux_1-kontext-dev", "displayName": "FLUX.1-Kontext-dev", "metadata": { "lastUpdated": "2025-08-12", "openWeights": true, "releaseDate": "2025-08-12" } } ] }, { "id": "nvidia/flux-1-schnell", "provider": "nvidia", "model": "flux-1-schnell", "displayName": "FLUX.1-schnell", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/black-forest-labs/flux_1-schnell" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 77, "inputTokens": 77, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "black-forest-labs/flux_1-schnell", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "FLUX.1-schnell" ], "knowledgeCutoff": "2024-07", "releaseDate": "2024-08-01", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "black-forest-labs/flux_1-schnell", "modelKey": "black-forest-labs/flux_1-schnell", "displayName": "FLUX.1-schnell", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2024-08-01" } } ] }, { "id": "nvidia/flux-2-klein-4b", "provider": "nvidia", "model": "flux-2-klein-4b", "displayName": "FLUX.2 Klein 4B", "family": "flux", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/black-forest-labs/flux_2-klein-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40960, "outputTokens": 40960, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "black-forest-labs/flux_2-klein-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "FLUX.2 Klein 4B" ], "families": [ "flux" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-01-14", "lastUpdated": "2026-01-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "black-forest-labs/flux_2-klein-4b", "modelKey": "black-forest-labs/flux_2-klein-4b", "displayName": "FLUX.2 Klein 4B", "family": "flux", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-31", "openWeights": true, "releaseDate": "2026-01-14" } } ] }, { "id": "nvidia/flux.1-dev", "provider": "nvidia", "model": "flux.1-dev", "displayName": "FLUX.1-dev", "family": "flux", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/black-forest-labs/flux.1-dev" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "black-forest-labs/flux.1-dev", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "FLUX.1-dev" ], "families": [ "flux" ], "knowledgeCutoff": "2024-08", "releaseDate": "2024-08-01", "lastUpdated": "2025-09-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "black-forest-labs/flux.1-dev", "modelKey": "black-forest-labs/flux.1-dev", "displayName": "FLUX.1-dev", "family": "flux", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-09-05", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "nvidia/gliner-pii", "provider": "nvidia", "model": "gliner-pii", "displayName": "gliner-pii", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/gliner-pii" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/gliner-pii", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "gliner-pii" ], "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/gliner-pii", "modelKey": "nvidia/gliner-pii", "displayName": "gliner-pii", "metadata": { "lastUpdated": "2026-03-03", "openWeights": true, "releaseDate": "2026-03-03" } } ] }, { "id": "nvidia/magpie-tts-zeroshot", "provider": "nvidia", "model": "magpie-tts-zeroshot", "displayName": "magpie-tts-zeroshot", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/magpie-tts-zeroshot" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/magpie-tts-zeroshot", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "magpie-tts-zeroshot" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/magpie-tts-zeroshot", "modelKey": "nvidia/magpie-tts-zeroshot", "displayName": "magpie-tts-zeroshot", "metadata": { "lastUpdated": "2025-06-12", "openWeights": true, "releaseDate": "2025-05-22" } } ] }, { "id": "nvidia/nemotron-3-content-safety", "provider": "nvidia", "model": "nemotron-3-content-safety", "displayName": "nemotron-3-content-safety", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-3-content-safety" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-3-content-safety", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nemotron-3-content-safety" ], "families": [ "nemotron" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-3-content-safety", "modelKey": "nvidia/nemotron-3-content-safety", "displayName": "nemotron-3-content-safety", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-04-16" } } ] }, { "id": "nvidia/nemotron-3-nano-30b-a3b", "provider": "nvidia", "model": "nemotron-3-nano-30b-a3b", "displayName": "nemotron-3-nano-30b-a3b", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nemotron-3-nano-30b-a3b" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-12", "lastUpdated": "2024-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-3-nano-30b-a3b", "modelKey": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "nemotron-3-nano-30b-a3b", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-12", "openWeights": true, "releaseDate": "2024-12", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "provider": "nvidia", "model": "nemotron-3-nano-omni-30b-a3b-reasoning", "displayName": "Nemotron 3 Nano Omni", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Nano Omni" ], "families": [ "nemotron" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "modelKey": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "displayName": "Nemotron 3 Nano Omni", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": -1, "max": 32768 } ] } } ] }, { "id": "nvidia/nemotron-3-super-120b-a12b", "provider": "nvidia", "model": "nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-04", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nvidia/nemotron-3-ultra-550b-a55b", "provider": "nvidia", "model": "nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-3-ultra-550b-a55b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-3-ultra-550b-a55b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.5, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Ultra 550B A55B" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-3-ultra-550b-a55b", "modelKey": "nvidia/nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nvidia/nemotron-content-safety-reasoning-4b", "provider": "nvidia", "model": "nemotron-content-safety-reasoning-4b", "displayName": "nemotron-content-safety-reasoning-4b", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-content-safety-reasoning-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-content-safety-reasoning-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nemotron-content-safety-reasoning-4b" ], "families": [ "nemotron" ], "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-content-safety-reasoning-4b", "modelKey": "nvidia/nemotron-content-safety-reasoning-4b", "displayName": "nemotron-content-safety-reasoning-4b", "family": "nemotron", "metadata": { "lastUpdated": "2026-01-22", "openWeights": true, "releaseDate": "2026-01-22" } } ] }, { "id": "nvidia/nemotron-mini-4b-instruct", "provider": "nvidia", "model": "nemotron-mini-4b-instruct", "displayName": "nemotron-mini-4b-instruct", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-mini-4b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-mini-4b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nemotron-mini-4b-instruct" ], "families": [ "nemotron" ], "releaseDate": "2024-08-21", "lastUpdated": "2024-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-mini-4b-instruct", "modelKey": "nvidia/nemotron-mini-4b-instruct", "displayName": "nemotron-mini-4b-instruct", "family": "nemotron", "metadata": { "lastUpdated": "2024-08-26", "openWeights": true, "releaseDate": "2024-08-21" } } ] }, { "id": "nvidia/nemotron-voicechat", "provider": "nvidia", "model": "nemotron-voicechat", "displayName": "nemotron-voicechat", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nemotron-voicechat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nemotron-voicechat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nemotron-voicechat" ], "families": [ "nemotron" ], "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nemotron-voicechat", "modelKey": "nvidia/nemotron-voicechat", "displayName": "nemotron-voicechat", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-16", "openWeights": true, "releaseDate": "2026-03-16" } } ] }, { "id": "nvidia/nv-embed-v1", "provider": "nvidia", "model": "nv-embed-v1", "displayName": "nv-embed-v1", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nv-embed-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nv-embed-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nv-embed-v1" ], "releaseDate": "2024-06-07", "lastUpdated": "2025-07-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nv-embed-v1", "modelKey": "nvidia/nv-embed-v1", "displayName": "nv-embed-v1", "metadata": { "lastUpdated": "2025-07-22", "openWeights": true, "releaseDate": "2024-06-07" } } ] }, { "id": "nvidia/nv-embedcode-7b-v1", "provider": "nvidia", "model": "nv-embedcode-7b-v1", "displayName": "nv-embedcode-7b-v1", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nv-embedcode-7b-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nv-embedcode-7b-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nv-embedcode-7b-v1" ], "releaseDate": "2025-03-17", "lastUpdated": "2025-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nv-embedcode-7b-v1", "modelKey": "nvidia/nv-embedcode-7b-v1", "displayName": "nv-embedcode-7b-v1", "metadata": { "lastUpdated": "2025-05-29", "openWeights": true, "releaseDate": "2025-03-17" } } ] }, { "id": "nvidia/nvidia-nemotron-nano-9b-v2", "provider": "nvidia", "model": "nvidia-nemotron-nano-9b-v2", "displayName": "nvidia-nemotron-nano-9b-v2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/nvidia-nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/nvidia-nemotron-nano-9b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "nvidia-nemotron-nano-9b-v2" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-09", "releaseDate": "2025-08-18", "lastUpdated": "2025-08-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/nvidia-nemotron-nano-9b-v2", "modelKey": "nvidia/nvidia-nemotron-nano-9b-v2", "displayName": "nvidia-nemotron-nano-9b-v2", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-08-18", "openWeights": true, "releaseDate": "2025-08-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "nvidia/phi-4-mini-instruct", "provider": "nvidia", "model": "phi-4-mini-instruct", "displayName": "Phi-4-Mini", "family": "phi", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/microsoft/phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "microsoft/phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi-4-Mini" ], "families": [ "phi" ], "knowledgeCutoff": "2024-12", "releaseDate": "2024-12-01", "lastUpdated": "2025-09-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "microsoft/phi-4-mini-instruct", "modelKey": "microsoft/phi-4-mini-instruct", "displayName": "Phi-4-Mini", "family": "phi", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "nvidia/phi-4-multimodal-instruct", "provider": "nvidia", "model": "phi-4-multimodal-instruct", "displayName": "Phi 4 Multimodal", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/microsoft/phi-4-multimodal-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "microsoft/phi-4-multimodal-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Phi 4 Multimodal" ], "releaseDate": "2025-07-26", "lastUpdated": "2025-07-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "microsoft/phi-4-multimodal-instruct", "modelKey": "microsoft/phi-4-multimodal-instruct", "displayName": "Phi 4 Multimodal", "metadata": { "lastUpdated": "2025-07-26", "openWeights": false, "releaseDate": "2025-07-26" } } ] }, { "id": "nvidia/rerank-qa-mistral-4b", "provider": "nvidia", "model": "rerank-qa-mistral-4b", "displayName": "rerank-qa-mistral-4b", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/rerank-qa-mistral-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/rerank-qa-mistral-4b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "rerank-qa-mistral-4b" ], "releaseDate": "2024-03-17", "lastUpdated": "2025-01-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/rerank-qa-mistral-4b", "modelKey": "nvidia/rerank-qa-mistral-4b", "displayName": "rerank-qa-mistral-4b", "metadata": { "lastUpdated": "2025-01-17", "openWeights": true, "releaseDate": "2024-03-17" } } ] }, { "id": "nvidia/riva-translate-4b-instruct-v1-1", "provider": "nvidia", "model": "riva-translate-4b-instruct-v1-1", "displayName": "riva-translate-4b-instruct-v1_1", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/riva-translate-4b-instruct-v1_1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/riva-translate-4b-instruct-v1_1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "riva-translate-4b-instruct-v1_1" ], "releaseDate": "2025-12-12", "lastUpdated": "2025-12-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/riva-translate-4b-instruct-v1_1", "modelKey": "nvidia/riva-translate-4b-instruct-v1_1", "displayName": "riva-translate-4b-instruct-v1_1", "metadata": { "lastUpdated": "2025-12-12", "openWeights": true, "releaseDate": "2025-12-12" } } ] }, { "id": "nvidia/sarvam-m", "provider": "nvidia", "model": "sarvam-m", "displayName": "sarvam-m", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/sarvamai/sarvam-m" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "sarvamai/sarvam-m", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "sarvam-m" ], "releaseDate": "2025-07-25", "lastUpdated": "2025-07-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "sarvamai/sarvam-m", "modelKey": "sarvamai/sarvam-m", "displayName": "sarvam-m", "metadata": { "lastUpdated": "2025-07-25", "openWeights": true, "releaseDate": "2025-07-25" } } ] }, { "id": "nvidia/seed-oss-36b-instruct", "provider": "nvidia", "model": "seed-oss-36b-instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/bytedance/seed-oss-36b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "bytedance/seed-oss-36b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "ByteDance-Seed/Seed-OSS-36B-Instruct" ], "families": [ "seed" ], "releaseDate": "2025-09-04", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "bytedance/seed-oss-36b-instruct", "modelKey": "bytedance/seed-oss-36b-instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-04" } } ] }, { "id": "nvidia/solar-10-7b-instruct", "provider": "nvidia", "model": "solar-10-7b-instruct", "displayName": "solar-10.7b-instruct", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/upstage/solar-10_7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "upstage/solar-10_7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "solar-10.7b-instruct" ], "releaseDate": "2024-06-05", "lastUpdated": "2025-04-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "upstage/solar-10_7b-instruct", "modelKey": "upstage/solar-10_7b-instruct", "displayName": "solar-10.7b-instruct", "metadata": { "lastUpdated": "2025-04-10", "openWeights": true, "releaseDate": "2024-06-05" } } ] }, { "id": "nvidia/sparsedrive", "provider": "nvidia", "model": "sparsedrive", "displayName": "sparsedrive", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/sparsedrive" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/sparsedrive", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "sparsedrive" ], "releaseDate": "2025-03-18", "lastUpdated": "2025-07-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/sparsedrive", "modelKey": "nvidia/sparsedrive", "displayName": "sparsedrive", "metadata": { "lastUpdated": "2025-07-20", "openWeights": true, "releaseDate": "2025-03-18" } } ] }, { "id": "nvidia/step-3.5-flash", "provider": "nvidia", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/stepfun-ai/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "stepfun-ai/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "releaseDate": "2026-02-02", "lastUpdated": "2026-02-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "stepfun-ai/step-3.5-flash", "modelKey": "stepfun-ai/step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "lastUpdated": "2026-02-02", "openWeights": true, "releaseDate": "2026-02-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "nvidia/step-3.7-flash", "provider": "nvidia", "model": "step-3.7-flash", "displayName": "Step 3.7 Flash", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/stepfun-ai/step-3.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "stepfun-ai/step-3.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash" ], "releaseDate": "2026-05-28", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "stepfun-ai/step-3.7-flash", "modelKey": "stepfun-ai/step-3.7-flash", "displayName": "Step 3.7 Flash", "metadata": { "lastUpdated": "2026-05-28", "openWeights": true, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high", "xhigh", "max" ] } ] } } ] }, { "id": "nvidia/streampetr", "provider": "nvidia", "model": "streampetr", "displayName": "streampetr", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/streampetr" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/streampetr", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "streampetr" ], "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/streampetr", "modelKey": "nvidia/streampetr", "displayName": "streampetr", "metadata": { "lastUpdated": "2025-11-13", "openWeights": true, "releaseDate": "2025-11-13" } } ] }, { "id": "nvidia/studiovoice", "provider": "nvidia", "model": "studiovoice", "displayName": "studiovoice", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/studiovoice" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/studiovoice", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "studiovoice" ], "releaseDate": "2024-10-03", "lastUpdated": "2025-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/studiovoice", "modelKey": "nvidia/studiovoice", "displayName": "studiovoice", "metadata": { "lastUpdated": "2025-06-13", "openWeights": true, "releaseDate": "2024-10-03" } } ] }, { "id": "nvidia/synthetic-video-detector", "provider": "nvidia", "model": "synthetic-video-detector", "displayName": "synthetic-video-detector", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/synthetic-video-detector" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/synthetic-video-detector", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "synthetic-video-detector" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/synthetic-video-detector", "modelKey": "nvidia/synthetic-video-detector", "displayName": "synthetic-video-detector", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-04-16" } } ] }, { "id": "nvidia/usdcode", "provider": "nvidia", "model": "usdcode", "displayName": "usdcode", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/usdcode" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/usdcode", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "usdcode" ], "releaseDate": "2026-01-01", "lastUpdated": "2026-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/usdcode", "modelKey": "nvidia/usdcode", "displayName": "usdcode", "metadata": { "lastUpdated": "2026-01-01", "openWeights": false, "releaseDate": "2026-01-01" } } ] }, { "id": "nvidia/usdvalidate", "provider": "nvidia", "model": "usdvalidate", "displayName": "usdvalidate", "sources": [ "models.dev" ], "providers": [ "nvidia" ], "aliases": [ "nvidia/usdvalidate" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nvidia", "model": "nvidia/usdvalidate", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "usdvalidate" ], "releaseDate": "2024-07-24", "lastUpdated": "2025-01-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "nvidia/usdvalidate", "modelKey": "nvidia/usdvalidate", "displayName": "usdvalidate", "metadata": { "lastUpdated": "2025-01-08", "openWeights": true, "releaseDate": "2024-07-24" } } ] }, { "id": "oci/cohere.command-a-03-2025", "provider": "oci", "model": "cohere.command-a-03-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-03-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-03-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-03-2025", "mode": "chat", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.command-a-reasoning", "provider": "oci", "model": "cohere.command-a-reasoning", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-reasoning", "mode": "chat", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.command-a-reasoning-08-2025", "provider": "oci", "model": "cohere.command-a-reasoning-08-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-reasoning-08-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-reasoning-08-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-reasoning-08-2025", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.command-a-translate-08-2025", "provider": "oci", "model": "cohere.command-a-translate-08-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-translate-08-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-translate-08-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.09 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-translate-08-2025", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.command-a-vision", "provider": "oci", "model": "cohere.command-a-vision", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-vision" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-vision", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-vision", "mode": "chat", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.command-a-vision-07-2025", "provider": "oci", "model": "cohere.command-a-vision-07-2025", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-a-vision-07-2025" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-a-vision-07-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-a-vision-07-2025", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.command-latest", "provider": "oci", "model": "cohere.command-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-latest", "mode": "chat", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.command-plus-latest", "provider": "oci", "model": "cohere.command-plus-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-plus-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-plus-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-plus-latest", "mode": "chat", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.command-r-08-2024", "provider": "oci", "model": "cohere.command-r-08-2024", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-r-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-r-08-2024", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-r-08-2024", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.command-r-plus-08-2024", "provider": "oci", "model": "cohere.command-r-plus-08-2024", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.command-r-plus-08-2024" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.command-r-plus-08-2024", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.56, "output": 1.56 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.command-r-plus-08-2024", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-english-image-v3.0", "provider": "oci", "model": "cohere.embed-english-image-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-english-image-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-english-image-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-english-image-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-english-light-image-v3.0", "provider": "oci", "model": "cohere.embed-english-light-image-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-english-light-image-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-english-light-image-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-english-light-image-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-english-light-v3.0", "provider": "oci", "model": "cohere.embed-english-light-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-english-light-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-english-light-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-english-light-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-english-v3.0", "provider": "oci", "model": "cohere.embed-english-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-english-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-english-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-english-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-multilingual-image-v3.0", "provider": "oci", "model": "cohere.embed-multilingual-image-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-multilingual-image-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-multilingual-image-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-multilingual-image-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" } } ] }, { "id": "oci/cohere.embed-multilingual-light-image-v3.0", "provider": "oci", "model": "cohere.embed-multilingual-light-image-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-multilingual-light-image-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-multilingual-light-image-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-multilingual-light-image-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-multilingual-light-v3.0", "provider": "oci", "model": "cohere.embed-multilingual-light-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-multilingual-light-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-multilingual-light-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-multilingual-light-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-multilingual-v3.0", "provider": "oci", "model": "cohere.embed-multilingual-v3.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-multilingual-v3.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-multilingual-v3.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-multilingual-v3.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/cohere.embed-v4.0", "provider": "oci", "model": "cohere.embed-v4.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/cohere.embed-v4.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "embeddingImageInput": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/cohere.embed-v4.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/cohere.embed-v4.0", "mode": "embedding", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/google.gemini-2.5-flash", "provider": "oci", "model": "google.gemini-2.5-flash", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/google.gemini-2.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/google.gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/google.gemini-2.5-flash", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/google.gemini-2.5-flash-lite", "provider": "oci", "model": "google.gemini-2.5-flash-lite", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/google.gemini-2.5-flash-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/google.gemini-2.5-flash-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/google.gemini-2.5-flash-lite", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/google.gemini-2.5-pro", "provider": "oci", "model": "google.gemini-2.5-pro", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/google.gemini-2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/google.gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/google.gemini-2.5-pro", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.1-405b-instruct", "provider": "oci", "model": "meta.llama-3.1-405b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.1-405b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.1-405b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10.68, "output": 10.68 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.1-405b-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.1-70b-instruct", "provider": "oci", "model": "meta.llama-3.1-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.1-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.1-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.1-70b-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.1-8b-instruct", "provider": "oci", "model": "meta.llama-3.1-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.1-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.1-8b-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.2-11b-vision-instruct", "provider": "oci", "model": "meta.llama-3.2-11b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.2-11b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.2-11b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.2-11b-vision-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.2-90b-vision-instruct", "provider": "oci", "model": "meta.llama-3.2-90b-vision-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.2-90b-vision-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.2-90b-vision-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.2-90b-vision-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.3-70b-instruct", "provider": "oci", "model": "meta.llama-3.3-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.3-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.3-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.3-70b-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-3.3-70b-instruct-fp8-dynamic", "provider": "oci", "model": "meta.llama-3.3-70b-instruct-fp8-dynamic", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-3.3-70b-instruct-fp8-dynamic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-3.3-70b-instruct-fp8-dynamic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-3.3-70b-instruct-fp8-dynamic", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "provider": "oci", "model": "meta.llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-4-maverick-17b-128e-instruct-fp8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/meta.llama-4-scout-17b-16e-instruct", "provider": "oci", "model": "meta.llama-4-scout-17b-16e-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/meta.llama-4-scout-17b-16e-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 10485760, "inputTokens": 10485760, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/meta.llama-4-scout-17b-16e-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/meta.llama-4-scout-17b-16e-instruct", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/openai.gpt-5", "provider": "oci", "model": "openai.gpt-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/openai.gpt-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/openai.gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/openai.gpt-5", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/openai.gpt-5-mini", "provider": "oci", "model": "openai.gpt-5-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/openai.gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/openai.gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/openai.gpt-5-mini", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/openai.gpt-5-nano", "provider": "oci", "model": "openai.gpt-5-nano", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/openai.gpt-5-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/openai.gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/openai.gpt-5-nano", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-3", "provider": "oci", "model": "xai.grok-3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-3", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-3-fast", "provider": "oci", "model": "xai.grok-3-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-3-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-3-fast", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-3-mini", "provider": "oci", "model": "xai.grok-3-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-3-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-3-mini", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-3-mini-fast", "provider": "oci", "model": "xai.grok-3-mini-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-3-mini-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-3-mini-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-3-mini-fast", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-4", "provider": "oci", "model": "xai.grok-4", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-4", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-4-fast", "provider": "oci", "model": "xai.grok-4-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-4-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-4-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-4-fast", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-4.1-fast", "provider": "oci", "model": "xai.grok-4.1-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-4.1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-4.1-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-4.1-fast", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-4.20", "provider": "oci", "model": "xai.grok-4.20", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-4.20" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-4.20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-4.20", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-4.20-multi-agent", "provider": "oci", "model": "xai.grok-4.20-multi-agent", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-4.20-multi-agent" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-4.20-multi-agent", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-4.20-multi-agent", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "oci/xai.grok-code-fast-1", "provider": "oci", "model": "xai.grok-code-fast-1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "oci" ], "aliases": [ "oci/xai.grok-code-fast-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "oci", "model": "oci/xai.grok-code-fast-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "oci", "model": "oci/xai.grok-code-fast-1", "mode": "chat", "metadata": { "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } } ] }, { "id": "ollama-cloud/cogito-2.1:671b", "provider": "ollama-cloud", "model": "cogito-2.1:671b", "displayName": "cogito-2.1:671b", "family": "cogito", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/cogito-2.1:671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "cogito-2.1:671b" ], "families": [ "cogito" ], "statuses": [ "deprecated" ], "releaseDate": "2025-11-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "cogito-2.1:671b", "modelKey": "cogito-2.1:671b", "displayName": "cogito-2.1:671b", "family": "cogito", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-11-19", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "ollama-cloud/gemma3:12b", "provider": "ollama-cloud", "model": "gemma3:12b", "displayName": "gemma3:12b", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gemma3:12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gemma3:12b" ], "families": [ "gemma" ], "releaseDate": "2024-12-01", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gemma3:12b", "modelKey": "gemma3:12b", "displayName": "gemma3:12b", "family": "gemma", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "ollama-cloud/gemma3:27b", "provider": "ollama-cloud", "model": "gemma3:27b", "displayName": "gemma3:27b", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gemma3:27b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gemma3:27b" ], "families": [ "gemma" ], "releaseDate": "2025-07-27", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gemma3:27b", "modelKey": "gemma3:27b", "displayName": "gemma3:27b", "family": "gemma", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-07-27" } } ] }, { "id": "ollama-cloud/gemma3:4b", "provider": "ollama-cloud", "model": "gemma3:4b", "displayName": "gemma3:4b", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gemma3:4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gemma3:4b" ], "families": [ "gemma" ], "releaseDate": "2024-12-01", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gemma3:4b", "modelKey": "gemma3:4b", "displayName": "gemma3:4b", "family": "gemma", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2024-12-01" } } ] }, { "id": "ollama-cloud/gemma4:31b", "provider": "ollama-cloud", "model": "gemma4:31b", "displayName": "gemma4:31b", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gemma4:31b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gemma4:31b" ], "families": [ "gemma" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gemma4:31b", "modelKey": "gemma4:31b", "displayName": "gemma4:31b", "family": "gemma", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-08", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "ollama-cloud/nemotron-3-nano:30b", "provider": "ollama-cloud", "model": "nemotron-3-nano:30b", "displayName": "nemotron-3-nano:30b", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/nemotron-3-nano:30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "nemotron-3-nano:30b" ], "families": [ "nemotron" ], "releaseDate": "2025-12-15", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "nemotron-3-nano:30b", "modelKey": "nemotron-3-nano:30b", "displayName": "nemotron-3-nano:30b", "family": "nemotron", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-15", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "ollama-cloud/nemotron-3-super", "provider": "ollama-cloud", "model": "nemotron-3-super", "displayName": "nemotron-3-super", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/nemotron-3-super" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "nemotron-3-super" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "nemotron-3-super", "modelKey": "nemotron-3-super", "displayName": "nemotron-3-super", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "ollama-cloud/nemotron-3-ultra", "provider": "ollama-cloud", "model": "nemotron-3-ultra", "displayName": "nemotron-3-ultra", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/nemotron-3-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "nemotron-3-ultra" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "nemotron-3-ultra", "modelKey": "nemotron-3-ultra", "displayName": "nemotron-3-ultra", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "ollama-cloud/rnj-1:8b", "provider": "ollama-cloud", "model": "rnj-1:8b", "displayName": "rnj-1:8b", "family": "rnj", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/rnj-1:8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "rnj-1:8b" ], "families": [ "rnj" ], "releaseDate": "2025-12-06", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "rnj-1:8b", "modelKey": "rnj-1:8b", "displayName": "rnj-1:8b", "family": "rnj", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-06" } } ] }, { "id": "ollama/codegeex4", "provider": "ollama", "model": "codegeex4", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/codegeex4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/codegeex4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/codegeex4", "mode": "chat" } ] }, { "id": "ollama/codegemma", "provider": "ollama", "model": "codegemma", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/codegemma" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/codegemma", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/codegemma", "mode": "completion" } ] }, { "id": "ollama/internlm2-5-20b-chat", "provider": "ollama", "model": "internlm2-5-20b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/internlm2_5-20b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/internlm2_5-20b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/internlm2_5-20b-chat", "mode": "chat" } ] }, { "id": "ollama/llama2", "provider": "ollama", "model": "llama2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama2", "mode": "chat" } ] }, { "id": "ollama/llama2-uncensored", "provider": "ollama", "model": "llama2-uncensored", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama2-uncensored" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama2-uncensored", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama2-uncensored", "mode": "completion" } ] }, { "id": "ollama/llama2:13b", "provider": "ollama", "model": "llama2:13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama2:13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama2:13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama2:13b", "mode": "chat" } ] }, { "id": "ollama/llama2:70b", "provider": "ollama", "model": "llama2:70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama2:70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama2:70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama2:70b", "mode": "chat" } ] }, { "id": "ollama/llama2:7b", "provider": "ollama", "model": "llama2:7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama2:7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama2:7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama2:7b", "mode": "chat" } ] }, { "id": "ollama/llama3", "provider": "ollama", "model": "llama3", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama3", "mode": "chat" } ] }, { "id": "ollama/llama3:70b", "provider": "ollama", "model": "llama3:70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama3:70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama3:70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama3:70b", "mode": "chat" } ] }, { "id": "ollama/llama3:8b", "provider": "ollama", "model": "llama3:8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama3:8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama3:8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama3:8b", "mode": "chat" } ] }, { "id": "ollama/llama3.1", "provider": "ollama", "model": "llama3.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/llama3.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/llama3.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/llama3.1", "mode": "chat" } ] }, { "id": "ollama/orca-mini", "provider": "ollama", "model": "orca-mini", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/orca-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/orca-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/orca-mini", "mode": "completion" } ] }, { "id": "ollama/vicuna", "provider": "ollama", "model": "vicuna", "mode": "completion", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/vicuna" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/vicuna", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/vicuna", "mode": "completion" } ] }, { "id": "openai/chatgpt-4o-latest", "provider": "openai", "model": "chatgpt-4o-latest", "displayName": "chatgpt-4o-latest", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "helicone", "openai", "poe" ], "aliases": [ "302ai/chatgpt-4o-latest", "helicone/chatgpt-4o-latest", "openai/chatgpt-4o-latest", "poe/openai/chatgpt-4o-latest" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "chatgpt-4o-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "helicone", "model": "chatgpt-4o-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.5, "input": 5, "output": 20 } }, { "source": "models.dev", "provider": "poe", "model": "openai/chatgpt-4o-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4.5, "output": 14 } }, { "source": "litellm", "provider": "openai", "model": "chatgpt-4o-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 } } ] }, "metadata": { "displayNames": [ "ChatGPT-4o-Latest", "OpenAI ChatGPT-4o", "chatgpt-4o-latest" ], "families": [ "gpt" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-08-08", "lastUpdated": "2024-08-08", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "chatgpt-4o-latest", "modelKey": "chatgpt-4o-latest", "displayName": "chatgpt-4o-latest", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-08", "openWeights": false, "releaseDate": "2024-08-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "chatgpt-4o-latest", "modelKey": "chatgpt-4o-latest", "displayName": "OpenAI ChatGPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2024-08-14", "openWeights": false, "releaseDate": "2024-08-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/chatgpt-4o-latest", "modelKey": "openai/chatgpt-4o-latest", "displayName": "ChatGPT-4o-Latest", "family": "gpt", "status": "deprecated", "metadata": { "lastUpdated": "2024-08-14", "openWeights": false, "releaseDate": "2024-08-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "chatgpt-4o-latest", "mode": "chat" } ] }, { "id": "openai/chatgpt-image-latest", "provider": "openai", "model": "chatgpt-image-latest", "displayName": "chatgpt-image-latest", "family": "gpt-image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "openai" ], "aliases": [ "openai/chatgpt-image-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "inputTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "chatgpt-image-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 10, "outputImage": 40 }, "extra": { "cache_read_input_image_token_cost": 0.0000025 } } ] }, "metadata": { "displayNames": [ "chatgpt-image-latest" ], "families": [ "gpt-image" ], "modes": [ "image_generation" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "chatgpt-image-latest", "modelKey": "chatgpt-image-latest", "displayName": "chatgpt-image-latest", "family": "gpt-image", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "chatgpt-image-latest", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } } ] }, { "id": "openai/codex-mini", "provider": "openai", "model": "codex-mini", "displayName": "Codex Mini", "family": "gpt-codex-mini", "mode": "responses", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/codex-mini", "azure/codex-mini" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.375, "input": 1.5, "output": 6 } }, { "source": "models.dev", "provider": "azure", "model": "codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.375, "input": 1.5, "output": 6 } }, { "source": "litellm", "provider": "azure", "model": "azure/codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.375, "input": 1.5, "output": 6 } } ] }, "metadata": { "displayNames": [ "Codex Mini" ], "families": [ "gpt-codex-mini" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-05-16", "lastUpdated": "2025-05-16", "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "codex-mini", "modelKey": "codex-mini", "displayName": "Codex Mini", "family": "gpt-codex-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-05-16", "openWeights": false, "releaseDate": "2025-05-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "codex-mini", "modelKey": "codex-mini", "displayName": "Codex Mini", "family": "gpt-codex-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-05-16", "openWeights": false, "releaseDate": "2025-05-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "openai/codex-mini-latest", "provider": "openai", "model": "codex-mini-latest", "mode": "responses", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/codex-mini-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "codex-mini-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.375, "input": 1.5, "output": 6 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "codex-mini-latest", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "openai/container", "provider": "openai", "model": "container", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/container" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "openai/container", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perSession": { "codeInterpreter": 0.03 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "openai/container", "mode": "chat" } ] }, { "id": "openai/dall-e-2", "provider": "openai", "model": "dall-e-2", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "aiml", "azure", "openai" ], "aliases": [ "aiml/dall-e-2", "azure/standard/1024-x-1024/dall-e-2", "openai/1024-x-1024/dall-e-2", "openai/256-x-256/dall-e-2", "openai/512-x-512/dall-e-2", "openai/dall-e-2" ], "mergedProviderModelRecords": 6, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.026 } }, { "source": "litellm", "provider": "azure", "model": "azure/standard/1024-x-1024/dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 0 } }, { "source": "litellm", "provider": "openai", "model": "1024-x-1024/dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.9e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "256-x-256/dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 2.4414e-7, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "512-x-512/dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 6.86e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "dall-e-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.02 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations", "/v1/images/variations" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/dall-e-2", "mode": "image_generation", "metadata": { "metadata": { "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/standard/1024-x-1024/dall-e-2", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1024-x-1024/dall-e-2", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "256-x-256/dall-e-2", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "512-x-512/dall-e-2", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "dall-e-2", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits", "/v1/images/variations" ] } } ] }, { "id": "openai/dall-e-3", "provider": "openai", "model": "dall-e-3", "displayName": "DALL-E-3", "family": "dall-e", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "aiml", "azure", "openai", "poe" ], "aliases": [ "aiml/dall-e-3", "azure/hd/1024-x-1024/dall-e-3", "azure/hd/1024-x-1792/dall-e-3", "azure/hd/1792-x-1024/dall-e-3", "azure/standard/1024-x-1024/dall-e-3", "azure/standard/1024-x-1792/dall-e-3", "azure/standard/1792-x-1024/dall-e-3", "openai/dall-e-3", "openai/hd/1024-x-1024/dall-e-3", "openai/hd/1024-x-1792/dall-e-3", "openai/hd/1792-x-1024/dall-e-3", "openai/standard/1024-x-1024/dall-e-3", "openai/standard/1024-x-1792/dall-e-3", "openai/standard/1792-x-1024/dall-e-3", "poe/openai/dall-e-3" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 800, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": false, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "aiml", "model": "aiml/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.052 } }, { "source": "litellm", "provider": "azure", "model": "azure/hd/1024-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 7.629e-8 } }, { "source": "litellm", "provider": "azure", "model": "azure/hd/1024-x-1792/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 6.539e-8 } }, { "source": "litellm", "provider": "azure", "model": "azure/hd/1792-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 6.539e-8 } }, { "source": "litellm", "provider": "azure", "model": "azure/standard/1024-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 3.81469e-8 } }, { "source": "litellm", "provider": "azure", "model": "azure/standard/1024-x-1792/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 4.359e-8 } }, { "source": "litellm", "provider": "azure", "model": "azure/standard/1792-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "output": 0 }, "perPixel": { "input": 4.359e-8 } }, { "source": "litellm", "provider": "openai", "model": "dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.04 } }, { "source": "litellm", "provider": "openai", "model": "hd/1024-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 7.629e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "hd/1024-x-1792/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 6.539e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "hd/1792-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 6.539e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 3.81469e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1792/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 4.359e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "standard/1792-x-1024/dall-e-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 4.359e-8, "output": 0 } } ] }, "metadata": { "displayNames": [ "DALL-E-3" ], "families": [ "dall-e" ], "modes": [ "image_generation" ], "releaseDate": "2023-11-06", "lastUpdated": "2023-11-06", "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/dall-e-3", "modelKey": "openai/dall-e-3", "displayName": "DALL-E-3", "family": "dall-e", "metadata": { "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "aiml", "model": "aiml/dall-e-3", "mode": "image_generation", "metadata": { "metadata": { "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" }, "source": "https://docs.aimlapi.com/", "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/hd/1024-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/hd/1024-x-1792/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/hd/1792-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/standard/1024-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/standard/1024-x-1792/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/standard/1792-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "dall-e-3", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "hd/1024-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "hd/1024-x-1792/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "hd/1792-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1024/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1792/dall-e-3", "mode": "image_generation" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1792-x-1024/dall-e-3", "mode": "image_generation" } ] }, { "id": "openai/ft:gpt-3.5-turbo", "provider": "openai", "model": "ft:gpt-3.5-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-3.5-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 6 }, "extra": { "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.000003 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-3.5-turbo", "mode": "chat" } ] }, { "id": "openai/ft:gpt-3.5-turbo-0125", "provider": "openai", "model": "ft:gpt-3.5-turbo-0125", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-3.5-turbo-0125" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-3.5-turbo-0125", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-3.5-turbo-0125", "mode": "chat" } ] }, { "id": "openai/ft:gpt-3.5-turbo-0613", "provider": "openai", "model": "ft:gpt-3.5-turbo-0613", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-3.5-turbo-0613" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-3.5-turbo-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-3.5-turbo-0613", "mode": "chat" } ] }, { "id": "openai/ft:gpt-3.5-turbo-1106", "provider": "openai", "model": "ft:gpt-3.5-turbo-1106", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-3.5-turbo-1106" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-3.5-turbo-1106", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-3.5-turbo-1106", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4-0613", "provider": "openai", "model": "ft:gpt-4-0613", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4-0613" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4-0613", "mode": "chat", "metadata": { "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing" } } ] }, { "id": "openai/ft:gpt-4.1-2025-04-14", "provider": "openai", "model": "ft:gpt-4.1-2025-04-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4.1-2025-04-14" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4.1-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 12 }, "extra": { "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.000006 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4.1-2025-04-14", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4.1-mini-2025-04-14", "provider": "openai", "model": "ft:gpt-4.1-mini-2025-04-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4.1-mini-2025-04-14" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4.1-mini-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 0.8, "output": 3.2 }, "extra": { "input_cost_per_token_batches": 4e-7, "output_cost_per_token_batches": 0.0000016 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4.1-mini-2025-04-14", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4.1-nano-2025-04-14", "provider": "openai", "model": "ft:gpt-4.1-nano-2025-04-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4.1-nano-2025-04-14" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4.1-nano-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.8 }, "extra": { "input_cost_per_token_batches": 1e-7, "output_cost_per_token_batches": 4e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4.1-nano-2025-04-14", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4o-2024-08-06", "provider": "openai", "model": "ft:gpt-4o-2024-08-06", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4o-2024-08-06" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.875, "input": 3.75, "output": 15 }, "extra": { "input_cost_per_token_batches": 0.000001875, "output_cost_per_token_batches": 0.0000075 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4o-2024-08-06", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4o-2024-11-20", "provider": "openai", "model": "ft:gpt-4o-2024-11-20", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4o-2024-11-20" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 1.875, "input": 3.75, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4o-2024-11-20", "mode": "chat" } ] }, { "id": "openai/ft:gpt-4o-mini-2024-07-18", "provider": "openai", "model": "ft:gpt-4o-mini-2024-07-18", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:gpt-4o-mini-2024-07-18" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 1.2 }, "extra": { "input_cost_per_token_batches": 1.5e-7, "output_cost_per_token_batches": 6e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:gpt-4o-mini-2024-07-18", "mode": "chat" } ] }, { "id": "openai/ft:o4-mini-2025-04-16", "provider": "openai", "model": "ft:o4-mini-2025-04-16", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/ft:o4-mini-2025-04-16" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "ft:o4-mini-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1, "input": 4, "output": 16 }, "extra": { "input_cost_per_token_batches": 0.000002, "output_cost_per_token_batches": 0.000008 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "ft:o4-mini-2025-04-16", "mode": "chat" } ] }, { "id": "openai/gpt-3.5-turbo", "provider": "openai", "model": "gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "cloudflare-ai-gateway", "github_copilot", "kilo", "llmgateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure/gpt-3.5-turbo", "cloudflare-ai-gateway/openai/gpt-3.5-turbo", "github_copilot/gpt-3.5-turbo", "kilo/openai/gpt-3.5-turbo", "llmgateway/gpt-3.5-turbo", "nano-gpt/openai/gpt-3.5-turbo", "openai/gpt-3.5-turbo", "openrouter/openai/gpt-3.5-turbo", "orcarouter/openai/gpt-3.5-turbo", "poe/openai/gpt-3.5-turbo", "vercel/openai/gpt-3.5-turbo", "vercel_ai_gateway/openai/gpt-3.5-turbo" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.4 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-3.5-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-3.5-turbo", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo", "GPT-3.5-Turbo", "GPT-3.5-turbo", "OpenAI: GPT-3.5 Turbo" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2021-09-01", "releaseDate": "2023-03-01", "lastUpdated": "2023-11-06", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-01", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "OpenAI: GPT-3.5 Turbo", "metadata": { "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-3.5-turbo", "modelKey": "gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-01", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5 Turbo", "family": "gpt", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2022-11-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-3.5-turbo", "modelKey": "gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-01", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-01", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5-turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-01", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5-Turbo", "family": "gpt", "metadata": { "lastUpdated": "2023-09-13", "openWeights": false, "releaseDate": "2023-09-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-3.5-turbo", "modelKey": "openai/gpt-3.5-turbo", "displayName": "GPT-3.5 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-05-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-3.5-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-3.5-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-3.5-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-3.5-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-3.5-turbo", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-3.5-turbo", "displayName": "OpenAI: GPT-3.5 Turbo", "metadata": { "canonicalSlug": "openai/gpt-3.5-turbo", "createdAt": "2023-05-28T00:00:00.000Z", "knowledgeCutoff": "2021-09-30", "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 16385, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-3.5-turbo-0125", "provider": "openai", "model": "gpt-3.5-turbo-0125", "displayName": "GPT-3.5 Turbo 0125", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "openai" ], "aliases": [ "azure-cognitive-services/gpt-3.5-turbo-0125", "azure/gpt-3.5-turbo-0125", "openai/gpt-3.5-turbo-0125" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-3.5-turbo-0125", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-3.5-turbo-0125", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-3.5-turbo-0125", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } }, { "source": "litellm", "provider": "openai", "model": "gpt-3.5-turbo-0125", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo 0125" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2021-08", "releaseDate": "2024-01-25", "lastUpdated": "2024-01-25", "deprecationDate": "2025-03-31", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0125", "modelKey": "gpt-3.5-turbo-0125", "displayName": "GPT-3.5 Turbo 0125", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0125", "modelKey": "gpt-3.5-turbo-0125", "displayName": "GPT-3.5 Turbo 0125", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-3.5-turbo-0125", "mode": "chat", "metadata": { "deprecationDate": "2025-03-31" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-3.5-turbo-0125", "mode": "chat" } ] }, { "id": "openai/gpt-3.5-turbo-0301", "provider": "openai", "model": "gpt-3.5-turbo-0301", "displayName": "GPT-3.5 Turbo 0301", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "azure", "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/gpt-3.5-turbo-0301", "azure/gpt-3.5-turbo-0301" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-3.5-turbo-0301", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-3.5-turbo-0301", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo 0301" ], "families": [ "gpt" ], "knowledgeCutoff": "2021-08", "releaseDate": "2023-03-01", "lastUpdated": "2023-03-01", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0301", "modelKey": "gpt-3.5-turbo-0301", "displayName": "GPT-3.5 Turbo 0301", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-03-01", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0301", "modelKey": "gpt-3.5-turbo-0301", "displayName": "GPT-3.5 Turbo 0301", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-03-01", "openWeights": false, "releaseDate": "2023-03-01" } } ] }, { "id": "openai/gpt-3.5-turbo-0613", "provider": "openai", "model": "gpt-3.5-turbo-0613", "displayName": "GPT-3.5 Turbo 0613", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "github_copilot", "kilo", "openrouter" ], "aliases": [ "azure-cognitive-services/gpt-3.5-turbo-0613", "azure/gpt-3.5-turbo-0613", "github_copilot/gpt-3.5-turbo-0613", "kilo/openai/gpt-3.5-turbo-0613", "openrouter/openai/gpt-3.5-turbo-0613" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-3.5-turbo-0613", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-3.5-turbo-0613", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-3.5-turbo-0613", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-0613", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-3.5-turbo-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-0613", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 2 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo (older v0613)", "GPT-3.5 Turbo 0613", "OpenAI: GPT-3.5 Turbo (older v0613)" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2021-08", "releaseDate": "2023-06-13", "lastUpdated": "2023-06-13", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0613", "modelKey": "gpt-3.5-turbo-0613", "displayName": "GPT-3.5 Turbo 0613", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-06-13", "openWeights": false, "releaseDate": "2023-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-0613", "modelKey": "gpt-3.5-turbo-0613", "displayName": "GPT-3.5 Turbo 0613", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-06-13", "openWeights": false, "releaseDate": "2023-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-3.5-turbo-0613", "modelKey": "openai/gpt-3.5-turbo-0613", "displayName": "OpenAI: GPT-3.5 Turbo (older v0613)", "metadata": { "lastUpdated": "2023-06-13", "openWeights": false, "releaseDate": "2023-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-3.5-turbo-0613", "modelKey": "openai/gpt-3.5-turbo-0613", "displayName": "GPT-3.5 Turbo (older v0613)", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-30", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-3.5-turbo-0613", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-0613", "displayName": "OpenAI: GPT-3.5 Turbo (older v0613)", "metadata": { "canonicalSlug": "openai/gpt-3.5-turbo-0613", "createdAt": "2024-01-25T00:00:00.000Z", "knowledgeCutoff": "2021-09-30", "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 4095, "max_completion_tokens": 4096, "is_moderated": false } } } ] }, { "id": "openai/gpt-3.5-turbo-1106", "provider": "openai", "model": "gpt-3.5-turbo-1106", "displayName": "GPT-3.5 Turbo 1106", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "openai" ], "aliases": [ "azure-cognitive-services/gpt-3.5-turbo-1106", "azure/gpt-3.5-turbo-1106", "openai/gpt-3.5-turbo-1106" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-3.5-turbo-1106", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-3.5-turbo-1106", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2 } }, { "source": "litellm", "provider": "openai", "model": "gpt-3.5-turbo-1106", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 2 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo 1106" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2021-08", "releaseDate": "2023-11-06", "lastUpdated": "2023-11-06", "deprecationDate": "2026-09-28", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-1106", "modelKey": "gpt-3.5-turbo-1106", "displayName": "GPT-3.5 Turbo 1106", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-1106", "modelKey": "gpt-3.5-turbo-1106", "displayName": "GPT-3.5 Turbo 1106", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-11-06", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-3.5-turbo-1106", "mode": "chat", "metadata": { "deprecationDate": "2026-09-28" } } ] }, { "id": "openai/gpt-3.5-turbo-16k", "provider": "openai", "model": "gpt-3.5-turbo-16k", "displayName": "GPT-3.5 Turbo 16k", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openai", "openrouter" ], "aliases": [ "kilo/openai/gpt-3.5-turbo-16k", "openai/gpt-3.5-turbo-16k", "openrouter/openai/gpt-3.5-turbo-16k" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-3.5-turbo-16k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-16k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "litellm", "provider": "openai", "model": "gpt-3.5-turbo-16k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-3.5-turbo-16k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-16k", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo 16k", "OpenAI: GPT-3.5 Turbo 16k" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2021-09-30", "releaseDate": "2023-08-28", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-3.5-turbo-16k", "modelKey": "openai/gpt-3.5-turbo-16k", "displayName": "OpenAI: GPT-3.5 Turbo 16k", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2023-08-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-3.5-turbo-16k", "modelKey": "openai/gpt-3.5-turbo-16k", "displayName": "GPT-3.5 Turbo 16k", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-30", "lastUpdated": "2023-08-28", "openWeights": false, "releaseDate": "2023-08-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-3.5-turbo-16k", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-3.5-turbo-16k", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-16k", "displayName": "OpenAI: GPT-3.5 Turbo 16k", "metadata": { "canonicalSlug": "openai/gpt-3.5-turbo-16k", "createdAt": "2023-08-28T00:00:00.000Z", "knowledgeCutoff": "2021-09-30", "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 16385, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-3.5-turbo-instruct", "provider": "openai", "model": "gpt-3.5-turbo-instruct", "displayName": "GPT-3.5 Turbo Instruct", "family": "gpt", "mode": "completion", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "kilo", "openrouter", "poe", "text-completion-openai", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/gpt-3.5-turbo-instruct", "azure/gpt-3.5-turbo-instruct", "kilo/openai/gpt-3.5-turbo-instruct", "openrouter/openai/gpt-3.5-turbo-instruct", "poe/openai/gpt-3.5-turbo-instruct", "text-completion-openai/gpt-3.5-turbo-instruct", "vercel/openai/gpt-3.5-turbo-instruct", "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 1.8 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "litellm", "provider": "text-completion-openai", "model": "gpt-3.5-turbo-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "GPT-3.5 Turbo Instruct", "GPT-3.5-Turbo-Instruct", "OpenAI: GPT-3.5 Turbo Instruct" ], "families": [ "gpt" ], "modes": [ "chat", "completion" ], "knowledgeCutoff": "2021-08", "releaseDate": "2023-09-21", "lastUpdated": "2023-09-21", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-instruct", "modelKey": "gpt-3.5-turbo-instruct", "displayName": "GPT-3.5 Turbo Instruct", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-09-21", "openWeights": false, "releaseDate": "2023-09-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-3.5-turbo-instruct", "modelKey": "gpt-3.5-turbo-instruct", "displayName": "GPT-3.5 Turbo Instruct", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-08", "lastUpdated": "2023-09-21", "openWeights": false, "releaseDate": "2023-09-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-3.5-turbo-instruct", "modelKey": "openai/gpt-3.5-turbo-instruct", "displayName": "OpenAI: GPT-3.5 Turbo Instruct", "metadata": { "lastUpdated": "2023-09-21", "openWeights": false, "releaseDate": "2023-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-3.5-turbo-instruct", "modelKey": "openai/gpt-3.5-turbo-instruct", "displayName": "GPT-3.5 Turbo Instruct", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09-30", "lastUpdated": "2023-09-28", "openWeights": false, "releaseDate": "2023-09-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-3.5-turbo-instruct", "modelKey": "openai/gpt-3.5-turbo-instruct", "displayName": "GPT-3.5-Turbo-Instruct", "family": "gpt", "metadata": { "lastUpdated": "2023-09-20", "openWeights": false, "releaseDate": "2023-09-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-3.5-turbo-instruct", "modelKey": "openai/gpt-3.5-turbo-instruct", "displayName": "GPT-3.5 Turbo Instruct", "family": "gpt", "metadata": { "knowledgeCutoff": "2021-09", "lastUpdated": "2023-03-01", "openWeights": false, "releaseDate": "2023-09-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "gpt-3.5-turbo-instruct", "mode": "completion" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-3.5-turbo-instruct", "displayName": "OpenAI: GPT-3.5 Turbo Instruct", "metadata": { "canonicalSlug": "openai/gpt-3.5-turbo-instruct", "createdAt": "2023-09-28T00:00:00.000Z", "instructType": "chatml", "knowledgeCutoff": "2021-09-30", "links": { "details": "/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 4095, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-3.5-turbo-instruct-0914", "provider": "openai", "model": "gpt-3.5-turbo-instruct-0914", "mode": "completion", "sources": [ "litellm" ], "providers": [ "azure_text", "text-completion-openai" ], "aliases": [ "azure_text/azure/gpt-3.5-turbo-instruct-0914", "text-completion-openai/gpt-3.5-turbo-instruct-0914" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4097, "outputTokens": 4097, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_text", "model": "azure/gpt-3.5-turbo-instruct-0914", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } }, { "source": "litellm", "provider": "text-completion-openai", "model": "gpt-3.5-turbo-instruct-0914", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_text", "model": "azure/gpt-3.5-turbo-instruct-0914", "mode": "completion" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "gpt-3.5-turbo-instruct-0914", "mode": "completion" } ] }, { "id": "openai/gpt-3.5-turbo-raw", "provider": "openai", "model": "gpt-3.5-turbo-raw", "displayName": "GPT-3.5-Turbo-Raw", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-3.5-turbo-raw" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4524, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-3.5-turbo-raw", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "GPT-3.5-Turbo-Raw" ], "families": [ "gpt" ], "releaseDate": "2023-09-27", "lastUpdated": "2023-09-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-3.5-turbo-raw", "modelKey": "openai/gpt-3.5-turbo-raw", "displayName": "GPT-3.5-Turbo-Raw", "family": "gpt", "metadata": { "lastUpdated": "2023-09-27", "openWeights": false, "releaseDate": "2023-09-27" } } ] }, { "id": "openai/gpt-35-turbo", "provider": "openai", "model": "gpt-35-turbo", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-35-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4097, "inputTokens": 4097, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-35-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-35-turbo", "mode": "chat" } ] }, { "id": "openai/gpt-35-turbo-0125", "provider": "openai", "model": "gpt-35-turbo-0125", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-35-turbo-0125" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-35-turbo-0125", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2025-05-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-35-turbo-0125", "mode": "chat", "metadata": { "deprecationDate": "2025-05-31" } } ] }, { "id": "openai/gpt-35-turbo-1106", "provider": "openai", "model": "gpt-35-turbo-1106", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-35-turbo-1106" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-35-turbo-1106", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 2 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2025-03-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-35-turbo-1106", "mode": "chat", "metadata": { "deprecationDate": "2025-03-31" } } ] }, { "id": "openai/gpt-35-turbo-16k", "provider": "openai", "model": "gpt-35-turbo-16k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-35-turbo-16k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-35-turbo-16k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-35-turbo-16k", "mode": "chat" } ] }, { "id": "openai/gpt-35-turbo-16k-0613", "provider": "openai", "model": "gpt-35-turbo-16k-0613", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-35-turbo-16k-0613" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16385, "inputTokens": 16385, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-35-turbo-16k-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-35-turbo-16k-0613", "mode": "chat" } ] }, { "id": "openai/gpt-35-turbo-instruct", "provider": "openai", "model": "gpt-35-turbo-instruct", "mode": "completion", "sources": [ "litellm" ], "providers": [ "azure_text" ], "aliases": [ "azure_text/azure/gpt-35-turbo-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4097, "inputTokens": 4097, "maxTokens": 4097, "outputTokens": 4097, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_text", "model": "azure/gpt-35-turbo-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_text", "model": "azure/gpt-35-turbo-instruct", "mode": "completion" } ] }, { "id": "openai/gpt-35-turbo-instruct-0914", "provider": "openai", "model": "gpt-35-turbo-instruct-0914", "mode": "completion", "sources": [ "litellm" ], "providers": [ "azure_text" ], "aliases": [ "azure_text/azure/gpt-35-turbo-instruct-0914" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4097, "inputTokens": 4097, "maxTokens": 4097, "outputTokens": 4097, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_text", "model": "azure/gpt-35-turbo-instruct-0914", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.5, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_text", "model": "azure/gpt-35-turbo-instruct-0914", "mode": "completion" } ] }, { "id": "openai/gpt-4", "provider": "openai", "model": "gpt-4", "displayName": "GPT-4", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "github_copilot", "kilo", "llmgateway", "openai", "openrouter", "orcarouter" ], "aliases": [ "azure-cognitive-services/gpt-4", "azure/gpt-4", "cloudflare-ai-gateway/openai/gpt-4", "github_copilot/gpt-4", "kilo/openai/gpt-4", "llmgateway/gpt-4", "openai/gpt-4", "openrouter/openai/gpt-4", "orcarouter/openai/gpt-4" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 60, "output": 120 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 60, "output": 120 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } } ] }, "metadata": { "displayNames": [ "GPT-4", "OpenAI: GPT-4" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-11", "releaseDate": "2023-03-14", "lastUpdated": "2023-03-14", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4", "modelKey": "gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2023-03-14", "openWeights": false, "releaseDate": "2023-03-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4", "modelKey": "gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2023-03-14", "openWeights": false, "releaseDate": "2023-03-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-4", "modelKey": "openai/gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4", "modelKey": "openai/gpt-4", "displayName": "OpenAI: GPT-4", "metadata": { "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-03-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4", "modelKey": "gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4", "modelKey": "gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4", "modelKey": "openai/gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4", "modelKey": "openai/gpt-4", "displayName": "GPT-4", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4", "displayName": "OpenAI: GPT-4", "metadata": { "canonicalSlug": "openai/gpt-4", "createdAt": "2023-05-28T00:00:00.000Z", "knowledgeCutoff": "2021-09-30", "links": { "details": "/api/v1/models/openai/gpt-4/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 8191, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-4-0125-preview", "provider": "openai", "model": "gpt-4-0125-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4-0125-preview", "openai/gpt-4-0125-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-0125-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-0125-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-03-26", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-0125-preview", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-0125-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-03-26" } } ] }, { "id": "openai/gpt-4-0314", "provider": "openai", "model": "gpt-4-0314", "displayName": "OpenAI: GPT-4 (older v0314)", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "kilo", "openai" ], "aliases": [ "kilo/openai/gpt-4-0314", "openai/gpt-4-0314" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4-0314", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-0314", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } } ] }, "metadata": { "displayNames": [ "OpenAI: GPT-4 (older v0314)" ], "modes": [ "chat" ], "releaseDate": "2023-05-28", "lastUpdated": "2026-03-15", "deprecationDate": "2026-03-26", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4-0314", "modelKey": "openai/gpt-4-0314", "displayName": "OpenAI: GPT-4 (older v0314)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2023-05-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-0314", "mode": "chat", "metadata": { "deprecationDate": "2026-03-26" } } ] }, { "id": "openai/gpt-4-0613", "provider": "openai", "model": "gpt-4-0613", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "github_copilot", "openai" ], "aliases": [ "azure/gpt-4-0613", "github_copilot/gpt-4-0613", "openai/gpt-4-0613" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 60 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2025-06-06", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-0613", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4-0613", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-0613", "mode": "chat", "metadata": { "deprecationDate": "2025-06-06" } } ] }, { "id": "openai/gpt-4-1106-preview", "provider": "openai", "model": "gpt-4-1106-preview", "displayName": "OpenAI: GPT-4 Turbo (older v1106)", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "kilo", "openai" ], "aliases": [ "azure/gpt-4-1106-preview", "kilo/openai/gpt-4-1106-preview", "openai/gpt-4-1106-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4-1106-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-1106-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-1106-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "displayNames": [ "OpenAI: GPT-4 Turbo (older v1106)" ], "modes": [ "chat" ], "releaseDate": "2023-11-06", "lastUpdated": "2026-03-15", "deprecationDate": "2026-03-26", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4-1106-preview", "modelKey": "openai/gpt-4-1106-preview", "displayName": "OpenAI: GPT-4 Turbo (older v1106)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-1106-preview", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-1106-preview", "mode": "chat", "metadata": { "deprecationDate": "2026-03-26" } } ] }, { "id": "openai/gpt-4-32k", "provider": "openai", "model": "gpt-4-32k", "displayName": "GPT-4 32K", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/gpt-4-32k", "azure/gpt-4-32k" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 60, "output": 120 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 60, "output": 120 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-32k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 60, "output": 120 } } ] }, "metadata": { "displayNames": [ "GPT-4 32K" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-11", "releaseDate": "2023-03-14", "lastUpdated": "2023-03-14", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-32k", "modelKey": "gpt-4-32k", "displayName": "GPT-4 32K", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2023-03-14", "openWeights": false, "releaseDate": "2023-03-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-32k", "modelKey": "gpt-4-32k", "displayName": "GPT-4 32K", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2023-03-14", "openWeights": false, "releaseDate": "2023-03-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-32k", "mode": "chat" } ] }, { "id": "openai/gpt-4-32k-0613", "provider": "openai", "model": "gpt-4-32k-0613", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-4-32k-0613" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-32k-0613", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 60, "output": 120 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-32k-0613", "mode": "chat" } ] }, { "id": "openai/gpt-4-classic", "provider": "openai", "model": "gpt-4-classic", "displayName": "GPT-4-Classic", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-4-classic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4-classic", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 27, "output": 54 } } ] }, "metadata": { "displayNames": [ "GPT-4-Classic" ], "families": [ "gpt" ], "statuses": [ "deprecated" ], "releaseDate": "2024-03-25", "lastUpdated": "2024-03-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4-classic", "modelKey": "openai/gpt-4-classic", "displayName": "GPT-4-Classic", "family": "gpt", "status": "deprecated", "metadata": { "lastUpdated": "2024-03-25", "openWeights": false, "releaseDate": "2024-03-25" } } ] }, { "id": "openai/gpt-4-classic-0314", "provider": "openai", "model": "gpt-4-classic-0314", "displayName": "GPT-4-Classic-0314", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-4-classic-0314" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4-classic-0314", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 27, "output": 54 } } ] }, "metadata": { "displayNames": [ "GPT-4-Classic-0314" ], "families": [ "gpt" ], "statuses": [ "deprecated" ], "releaseDate": "2024-08-26", "lastUpdated": "2024-08-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4-classic-0314", "modelKey": "openai/gpt-4-classic-0314", "displayName": "GPT-4-Classic-0314", "family": "gpt", "status": "deprecated", "metadata": { "lastUpdated": "2024-08-26", "openWeights": false, "releaseDate": "2024-08-26" } } ] }, { "id": "openai/gpt-4-o-preview", "provider": "openai", "model": "gpt-4-o-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "github_copilot" ], "aliases": [ "github_copilot/gpt-4-o-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4-o-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4-o-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4-turbo", "provider": "openai", "model": "gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "kilo", "llmgateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/gpt-4-turbo", "azure/gpt-4-turbo", "cloudflare-ai-gateway/openai/gpt-4-turbo", "kilo/openai/gpt-4-turbo", "llmgateway/gpt-4-turbo", "nano-gpt/openai/gpt-4-turbo", "openai/gpt-4-turbo", "openrouter/openai/gpt-4-turbo", "orcarouter/openai/gpt-4-turbo", "poe/openai/gpt-4-turbo", "vercel/openai/gpt-4-turbo", "vercel_ai_gateway/openai/gpt-4-turbo" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9, "output": 27 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4-turbo", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "displayNames": [ "GPT-4 Turbo", "GPT-4-Turbo", "OpenAI: GPT-4 Turbo" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12", "releaseDate": "2023-11-06", "lastUpdated": "2024-04-09", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-turbo", "modelKey": "gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-turbo", "modelKey": "gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "OpenAI: GPT-4 Turbo", "metadata": { "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-09-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4-turbo", "modelKey": "gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4-turbo", "modelKey": "gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4-Turbo", "family": "gpt", "metadata": { "lastUpdated": "2023-09-13", "openWeights": false, "releaseDate": "2023-09-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4-turbo", "modelKey": "openai/gpt-4-turbo", "displayName": "GPT-4 Turbo", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-turbo", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4-turbo", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4-turbo", "displayName": "OpenAI: GPT-4 Turbo", "metadata": { "canonicalSlug": "openai/gpt-4-turbo", "createdAt": "2024-04-09T00:00:00.000Z", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-4-turbo-2024-04-09", "provider": "openai", "model": "gpt-4-turbo-2024-04-09", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4-turbo-2024-04-09", "openai/gpt-4-turbo-2024-04-09" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-turbo-2024-04-09", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-turbo-2024-04-09", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-turbo-2024-04-09", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-turbo-2024-04-09", "mode": "chat" } ] }, { "id": "openai/gpt-4-turbo-preview", "provider": "openai", "model": "gpt-4-turbo-preview", "displayName": "OpenAI: GPT-4 Turbo Preview", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openai", "openrouter" ], "aliases": [ "kilo/openai/gpt-4-turbo-preview", "nano-gpt/openai/gpt-4-turbo-preview", "openai/gpt-4-turbo-preview", "openrouter/openai/gpt-4-turbo-preview" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "responseSchema": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 30.004999999999995 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4-turbo-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4-turbo-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4-turbo-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "displayNames": [ "GPT-4 Turbo Preview", "OpenAI: GPT-4 Turbo Preview" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-01-25", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4-turbo-preview", "modelKey": "openai/gpt-4-turbo-preview", "displayName": "OpenAI: GPT-4 Turbo Preview", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4-turbo-preview", "modelKey": "openai/gpt-4-turbo-preview", "displayName": "GPT-4 Turbo Preview", "family": "gpt", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4-turbo-preview", "modelKey": "openai/gpt-4-turbo-preview", "displayName": "GPT-4 Turbo Preview", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4-turbo-preview", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4-turbo-preview", "displayName": "OpenAI: GPT-4 Turbo Preview", "metadata": { "canonicalSlug": "openai/gpt-4-turbo-preview", "createdAt": "2024-01-25T00:00:00.000Z", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/openai/gpt-4-turbo-preview/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 4096, "is_moderated": true } } } ] }, { "id": "openai/gpt-4-turbo-vision", "provider": "openai", "model": "gpt-4-turbo-vision", "displayName": "GPT-4 Turbo Vision", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "azure", "azure-cognitive-services" ], "aliases": [ "azure-cognitive-services/gpt-4-turbo-vision", "azure/gpt-4-turbo-vision" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4-turbo-vision", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4-turbo-vision", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "displayNames": [ "GPT-4 Turbo Vision" ], "families": [ "gpt" ], "knowledgeCutoff": "2023-11", "releaseDate": "2023-11-06", "lastUpdated": "2024-04-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-turbo-vision", "modelKey": "gpt-4-turbo-vision", "displayName": "GPT-4 Turbo Vision", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4-turbo-vision", "modelKey": "gpt-4-turbo-vision", "displayName": "GPT-4 Turbo Vision", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-11", "lastUpdated": "2024-04-09", "openWeights": false, "releaseDate": "2023-11-06" } } ] }, { "id": "openai/gpt-4-turbo-vision-preview", "provider": "openai", "model": "gpt-4-turbo-vision-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-4-turbo-vision-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4-turbo-vision-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 30 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4-turbo-vision-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4.1", "provider": "openai", "model": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "anyapi", "azure", "azure-cognitive-services", "cortecs", "fastrouter", "github-copilot", "github-models", "github_copilot", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "orcarouter", "poe", "replicate", "requesty", "sap-ai-core", "vercel", "vercel_ai_gateway" ], "aliases": [ "302ai/gpt-4.1", "abacus/gpt-4.1", "anyapi/openai/gpt-4.1", "azure-cognitive-services/gpt-4.1", "azure/gpt-4.1", "cortecs/gpt-4.1", "fastrouter/openai/gpt-4.1", "github-copilot/gpt-4.1", "github-models/openai/gpt-4.1", "github_copilot/gpt-4.1", "helicone/gpt-4.1", "kilo/openai/gpt-4.1", "llmgateway/gpt-4.1", "merge-gateway/openai/gpt-4.1", "nano-gpt/openai/gpt-4.1", "nearai/openai/gpt-4.1", "openai/gpt-4.1", "openrouter/openai/gpt-4.1", "orcarouter/openai/gpt-4.1", "poe/openai/gpt-4.1", "replicate/openai/gpt-4.1", "requesty/openai/gpt-4.1", "sap-ai-core/gpt-4.1", "vercel/openai/gpt-4.1", "vercel_ai_gateway/openai/gpt-4.1" ], "mergedProviderModelRecords": 25, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "cortecs", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.354, "output": 9.417 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.45, "input": 1.8, "output": 7.2 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000004 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 0, "input": 2, "output": 8 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 4.1", "GPT-4.1", "OpenAI GPT-4.1", "OpenAI: GPT-4.1", "gpt-4.1" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 25 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "gpt-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT 4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "OpenAI GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "OpenAI: GPT-4.1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT 4.1", "family": "gpt", "metadata": { "lastUpdated": "2025-09-10", "openWeights": false, "releaseDate": "2025-09-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-4.1", "modelKey": "gpt-4.1", "displayName": "gpt-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4.1", "modelKey": "openai/gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-4.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4.1", "displayName": "OpenAI: GPT-4.1", "metadata": { "canonicalSlug": "openai/gpt-4.1-2025-04-14", "createdAt": "2025-04-14T17:23:05.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 1047576, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openai/gpt-4.1-2025-04-14", "provider": "openai", "model": "gpt-4.1-2025-04-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "github_copilot", "openai" ], "aliases": [ "azure/gpt-4.1-2025-04-14", "azure/us/gpt-4.1-2025-04-14", "github_copilot/gpt-4.1-2025-04-14", "openai/gpt-4.1-2025-04-14" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000004 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4.1-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 2.2, "output": 8.8 }, "extra": { "input_cost_per_token_batches": 0.0000011, "output_cost_per_token_batches": 0.0000044 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4.1-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000004 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4.1-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4.1-2025-04-14", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1-2025-04-14", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-4.1-mini", "provider": "openai", "model": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "anyapi", "azure", "azure-cognitive-services", "github-models", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "orcarouter", "poe", "replicate", "requesty", "sap-ai-core", "vercel", "vercel_ai_gateway" ], "aliases": [ "302ai/gpt-4.1-mini", "abacus/gpt-4.1-mini", "anyapi/openai/gpt-4.1-mini", "azure-cognitive-services/gpt-4.1-mini", "azure/gpt-4.1-mini", "github-models/openai/gpt-4.1-mini", "helicone/gpt-4.1-mini", "kilo/openai/gpt-4.1-mini", "llmgateway/gpt-4.1-mini", "merge-gateway/openai/gpt-4.1-mini", "nano-gpt/openai/gpt-4.1-mini", "nearai/openai/gpt-4.1-mini", "openai/gpt-4.1-mini", "openrouter/openai/gpt-4.1-mini", "orcarouter/openai/gpt-4.1-mini", "poe/openai/gpt-4.1-mini", "replicate/openai/gpt-4.1-mini", "requesty/openai/gpt-4.1-mini", "sap-ai-core/gpt-4.1-mini", "vercel/openai/gpt-4.1-mini", "vercel_ai_gateway/openai/gpt-4.1-mini" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09999999999999999, "input": 0.39999999999999997, "output": 1.5999999999999999 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09, "input": 0.36, "output": 1.4 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 }, "extra": { "input_cost_per_token_batches": 2e-7, "output_cost_per_token_batches": 8e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 }, "extra": { "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-4.1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 0, "input": 0.4, "output": 1.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4.1-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 4.1 Mini", "GPT-4.1 Mini", "GPT-4.1 mini", "GPT-4.1-mini", "OpenAI GPT-4.1 Mini", "OpenAI: GPT-4.1 Mini", "gpt-4.1-mini" ], "families": [ "gpt", "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "GPT-4.1 Mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "OpenAI GPT-4.1 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "OpenAI: GPT-4.1 Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT 4.1 Mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1-mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-4.1-mini", "modelKey": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4.1-mini", "modelKey": "openai/gpt-4.1-mini", "displayName": "GPT-4.1 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-4.1-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1-mini", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4.1-mini", "displayName": "OpenAI: GPT-4.1 Mini", "metadata": { "canonicalSlug": "openai/gpt-4.1-mini-2025-04-14", "createdAt": "2025-04-14T17:23:01.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 1047576, "max_completion_tokens": 32768, "is_moderated": true } } } ] }, { "id": "openai/gpt-4.1-mini-2025-04-14", "provider": "openai", "model": "gpt-4.1-mini-2025-04-14", "displayName": "OpenAI GPT-4.1 Mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "helicone", "openai" ], "aliases": [ "azure/gpt-4.1-mini-2025-04-14", "azure/us/gpt-4.1-mini-2025-04-14", "helicone/gpt-4.1-mini-2025-04-14", "openai/gpt-4.1-mini-2025-04-14" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "gpt-4.1-mini-2025-04-14", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09999999999999999, "input": 0.39999999999999997, "output": 1.5999999999999999 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1-mini-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 }, "extra": { "input_cost_per_token_batches": 2e-7, "output_cost_per_token_batches": 8e-7 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4.1-mini-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.44, "output": 1.76 }, "extra": { "input_cost_per_token_batches": 2.2e-7, "output_cost_per_token_batches": 8.8e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1-mini-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.4, "output": 1.6 }, "extra": { "input_cost_per_token_batches": 2e-7, "output_cost_per_token_batches": 8e-7 } } ] }, "metadata": { "displayNames": [ "OpenAI GPT-4.1 Mini" ], "families": [ "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4.1-mini-2025-04-14", "modelKey": "gpt-4.1-mini-2025-04-14", "displayName": "OpenAI GPT-4.1 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1-mini-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4.1-mini-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1-mini-2025-04-14", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-4.1-nano", "provider": "openai", "model": "gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "azure", "azure-cognitive-services", "github-models", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "orcarouter", "poe", "replicate", "vercel", "vercel_ai_gateway" ], "aliases": [ "302ai/gpt-4.1-nano", "abacus/gpt-4.1-nano", "azure-cognitive-services/gpt-4.1-nano", "azure/gpt-4.1-nano", "github-models/openai/gpt-4.1-nano", "helicone/gpt-4.1-nano", "kilo/openai/gpt-4.1-nano", "llmgateway/gpt-4.1-nano", "merge-gateway/openai/gpt-4.1-nano", "nano-gpt/openai/gpt-4.1-nano", "nearai/openai/gpt-4.1-nano", "openai/gpt-4.1-nano", "openrouter/openai/gpt-4.1-nano", "orcarouter/openai/gpt-4.1-nano", "poe/openai/gpt-4.1-nano", "replicate/openai/gpt-4.1-nano", "vercel/openai/gpt-4.1-nano", "vercel_ai_gateway/openai/gpt-4.1-nano" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.024999999999999998, "input": 0.09999999999999999, "output": 0.39999999999999997 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.022, "input": 0.09, "output": 0.36 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 }, "extra": { "input_cost_per_token_batches": 5e-8, "output_cost_per_token_batches": 2e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 }, "extra": { "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_priority": 2e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-4.1-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "cacheWrite": 0, "input": 0.1, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4.1-nano", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 4.1 Nano", "GPT-4.1 Nano", "GPT-4.1 nano", "GPT-4.1-nano", "OpenAI GPT-4.1 Nano", "OpenAI: GPT-4.1 Nano", "gpt-4.1-nano" ], "families": [ "gpt", "gpt-nano" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "GPT-4.1 Nano", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1-nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "OpenAI GPT-4.1 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "OpenAI: GPT-4.1 Nano", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT 4.1 Nano", "family": "gpt-nano", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4.1-nano", "modelKey": "gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1-nano", "family": "gpt-nano", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4.1-nano", "modelKey": "openai/gpt-4.1-nano", "displayName": "GPT-4.1 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4.1-nano", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-4.1-nano", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4.1-nano", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4.1-nano", "displayName": "OpenAI: GPT-4.1 Nano", "metadata": { "canonicalSlug": "openai/gpt-4.1-nano-2025-04-14", "createdAt": "2025-04-14T17:22:49.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 1047576, "max_completion_tokens": 32768, "is_moderated": true } } } ] }, { "id": "openai/gpt-4.1-nano-2025-04-14", "provider": "openai", "model": "gpt-4.1-nano-2025-04-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4.1-nano-2025-04-14", "azure/us/gpt-4.1-nano-2025-04-14", "openai/gpt-4.1-nano-2025-04-14" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1047576, "inputTokens": 1047576, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.1-nano-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 }, "extra": { "input_cost_per_token_batches": 5e-8, "output_cost_per_token_batches": 2e-7 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4.1-nano-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.11, "output": 0.44 }, "extra": { "input_cost_per_token_batches": 6e-8, "output_cost_per_token_batches": 2.2e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4.1-nano-2025-04-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.1, "output": 0.4 }, "extra": { "input_cost_per_token_batches": 5e-8, "output_cost_per_token_batches": 2e-7 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.1-nano-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4.1-nano-2025-04-14", "mode": "chat", "metadata": { "deprecationDate": "2026-11-04", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4.1-nano-2025-04-14", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-4.5-preview", "provider": "openai", "model": "gpt-4.5-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-4.5-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4.5-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 37.5, "input": 75, "output": 150 }, "extra": { "input_cost_per_token_batches": 0.0000375, "output_cost_per_token_batches": 0.000075 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4.5-preview", "mode": "chat" } ] }, { "id": "openai/gpt-41-copilot", "provider": "openai", "model": "gpt-41-copilot", "mode": "completion", "sources": [ "litellm" ], "providers": [ "github_copilot" ], "aliases": [ "github_copilot/gpt-41-copilot" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-41-copilot", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-41-copilot", "mode": "completion" } ] }, { "id": "openai/gpt-4o", "provider": "openai", "model": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "frogbot", "github-models", "github_copilot", "gmi", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "replicate", "vercel", "vercel_ai_gateway" ], "aliases": [ "302ai/gpt-4o", "azure-cognitive-services/gpt-4o", "azure/gpt-4o", "cloudflare-ai-gateway/openai/gpt-4o", "frogbot/gpt-4o", "github-models/openai/gpt-4o", "github_copilot/gpt-4o", "gmi/openai/gpt-4o", "helicone/gpt-4o", "kilo/openai/gpt-4o", "llmgateway/gpt-4o", "merge-gateway/openai/gpt-4o", "nano-gpt/openai/gpt-4o", "openai/gpt-4o", "openrouter/openai/gpt-4o", "orcarouter/openai/gpt-4o", "poe/openai/gpt-4o", "replicate/openai/gpt-4o", "vercel/openai/gpt-4o", "vercel_ai_gateway/openai/gpt-4o" ], "mergedProviderModelRecords": 20, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "frogbot", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 9.996 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4o", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/openai/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 0.000002125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.00000425, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_priority": 0.000017, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4o", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "cacheWrite": 0, "input": 2.5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-4o", "OpenAI GPT-4o", "OpenAI: GPT-4o", "gpt-4o" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-05-13", "lastUpdated": "2024-05-13", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 20 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "gpt-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "OpenAI GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "OpenAI: GPT-4o", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4o", "modelKey": "gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4o", "modelKey": "openai/gpt-4o", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/openai/gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-4o", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4o", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o", "displayName": "OpenAI: GPT-4o", "metadata": { "canonicalSlug": "openai/gpt-4o", "createdAt": "2024-05-13T00:00:00.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openai/gpt-4o-2024-05-13", "provider": "openai", "model": "gpt-4o-2024-05-13", "displayName": "GPT-4o (2024-05-13)", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "github_copilot", "kilo", "merge-gateway", "openai", "openrouter", "orcarouter" ], "aliases": [ "azure/gpt-4o-2024-05-13", "github_copilot/gpt-4o-2024-05-13", "kilo/openai/gpt-4o-2024-05-13", "merge-gateway/openai/gpt-4o-2024-05-13", "openai/gpt-4o-2024-05-13", "openrouter/openai/gpt-4o-2024-05-13", "orcarouter/openai/gpt-4o-2024-05-13" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "responseSchema": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-2024-05-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4o-2024-05-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4o-2024-05-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-2024-05-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4o-2024-05-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-2024-05-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-05-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-2024-05-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 }, "extra": { "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00000875, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00002625 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-4o-2024-05-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-2024-05-13", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 } } ] }, "metadata": { "displayNames": [ "GPT-4o (2024-05-13)", "OpenAI: GPT-4o (2024-05-13)" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-05-13", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-2024-05-13", "modelKey": "openai/gpt-4o-2024-05-13", "displayName": "OpenAI: GPT-4o (2024-05-13)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4o-2024-05-13", "modelKey": "openai/gpt-4o-2024-05-13", "displayName": "GPT-4o (2024-05-13)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4o-2024-05-13", "modelKey": "gpt-4o-2024-05-13", "displayName": "GPT-4o (2024-05-13)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-2024-05-13", "modelKey": "openai/gpt-4o-2024-05-13", "displayName": "GPT-4o (2024-05-13)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4o-2024-05-13", "modelKey": "openai/gpt-4o-2024-05-13", "displayName": "GPT-4o (2024-05-13)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-2024-05-13", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-05-13", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-2024-05-13", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-4o-2024-05-13", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-2024-05-13", "displayName": "OpenAI: GPT-4o (2024-05-13)", "metadata": { "canonicalSlug": "openai/gpt-4o-2024-05-13", "createdAt": "2024-05-13T00:00:00.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-2024-05-13/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 4096, "is_moderated": false } } } ] }, { "id": "openai/gpt-4o-2024-08-06", "provider": "openai", "model": "gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "github_copilot", "kilo", "merge-gateway", "nano-gpt", "openai", "openrouter", "orcarouter" ], "aliases": [ "azure/eu/gpt-4o-2024-08-06", "azure/global-standard/gpt-4o-2024-08-06", "azure/global/gpt-4o-2024-08-06", "azure/gpt-4o-2024-08-06", "azure/us/gpt-4o-2024-08-06", "github_copilot/gpt-4o-2024-08-06", "kilo/openai/gpt-4o-2024-08-06", "merge-gateway/openai/gpt-4o-2024-08-06", "nano-gpt/openai/gpt-4o-2024-08-06", "openai/gpt-4o-2024-08-06", "openrouter/openai/gpt-4o-2024-08-06", "orcarouter/openai/gpt-4o-2024-08-06" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.499, "output": 9.996 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.375, "input": 2.75, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/global-standard/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.375, "input": 2.75, "output": 11 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-2024-08-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 }, "extra": { "input_cost_per_token_batches": 0.00000125, "output_cost_per_token_batches": 0.000005, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-2024-08-06", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-4o (2024-08-06)", "OpenAI: GPT-4o (2024-08-06)" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-08-06", "lastUpdated": "2026-03-15", "deprecationDate": "2026-02-27", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-2024-08-06", "modelKey": "openai/gpt-4o-2024-08-06", "displayName": "OpenAI: GPT-4o (2024-08-06)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4o-2024-08-06", "modelKey": "openai/gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o-2024-08-06", "modelKey": "openai/gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "metadata": { "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4o-2024-08-06", "modelKey": "gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-2024-08-06", "modelKey": "openai/gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4o-2024-08-06", "modelKey": "openai/gpt-4o-2024-08-06", "displayName": "GPT-4o (2024-08-06)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-08-06", "openWeights": false, "releaseDate": "2024-08-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-2024-08-06", "mode": "chat", "metadata": { "deprecationDate": "2026-02-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global-standard/gpt-4o-2024-08-06", "mode": "chat", "metadata": { "deprecationDate": "2026-02-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-4o-2024-08-06", "mode": "chat", "metadata": { "deprecationDate": "2026-02-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-2024-08-06", "mode": "chat", "metadata": { "deprecationDate": "2026-02-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-2024-08-06", "mode": "chat", "metadata": { "deprecationDate": "2026-02-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-08-06", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-2024-08-06", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-2024-08-06", "displayName": "OpenAI: GPT-4o (2024-08-06)", "metadata": { "canonicalSlug": "openai/gpt-4o-2024-08-06", "createdAt": "2024-08-06T00:00:00.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-2024-08-06/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openai/gpt-4o-2024-11-20", "provider": "openai", "model": "gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "github_copilot", "kilo", "merge-gateway", "nano-gpt", "openai", "openrouter", "orcarouter" ], "aliases": [ "abacus/gpt-4o-2024-11-20", "azure/eu/gpt-4o-2024-11-20", "azure/global-standard/gpt-4o-2024-11-20", "azure/global/gpt-4o-2024-11-20", "azure/gpt-4o-2024-11-20", "azure/us/gpt-4o-2024-11-20", "github_copilot/gpt-4o-2024-11-20", "kilo/openai/gpt-4o-2024-11-20", "merge-gateway/openai/gpt-4o-2024-11-20", "nano-gpt/openai/gpt-4o-2024-11-20", "openai/gpt-4o-2024-11-20", "openrouter/openai/gpt-4o-2024-11-20", "orcarouter/openai/gpt-4o-2024-11-20" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 1.38, "input": 2.75, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/global-standard/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.75, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheWrite": 1.38, "input": 2.75, "output": 11 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-2024-11-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 }, "extra": { "input_cost_per_token_batches": 0.00000125, "output_cost_per_token_batches": 0.000005, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-2024-11-20", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-4o (2024-11-20)", "OpenAI: GPT-4o (2024-11-20)" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-11-20", "lastUpdated": "2024-11-20", "deprecationDate": "2026-03-01", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-4o-2024-11-20", "modelKey": "gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-2024-11-20", "modelKey": "openai/gpt-4o-2024-11-20", "displayName": "OpenAI: GPT-4o (2024-11-20)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4o-2024-11-20", "modelKey": "openai/gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o-2024-11-20", "modelKey": "openai/gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4o-2024-11-20", "modelKey": "gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-2024-11-20", "modelKey": "openai/gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4o-2024-11-20", "modelKey": "openai/gpt-4o-2024-11-20", "displayName": "GPT-4o (2024-11-20)", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-11-20", "openWeights": false, "releaseDate": "2024-11-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-2024-11-20", "mode": "chat", "metadata": { "deprecationDate": "2026-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global-standard/gpt-4o-2024-11-20", "mode": "chat", "metadata": { "deprecationDate": "2026-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-4o-2024-11-20", "mode": "chat", "metadata": { "deprecationDate": "2026-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-2024-11-20", "mode": "chat", "metadata": { "deprecationDate": "2026-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-2024-11-20", "mode": "chat", "metadata": { "deprecationDate": "2026-03-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o-2024-11-20", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-2024-11-20", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-2024-11-20", "displayName": "OpenAI: GPT-4o (2024-11-20)", "metadata": { "canonicalSlug": "openai/gpt-4o-2024-11-20", "createdAt": "2024-11-20T18:33:14.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-2024-11-20/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-4o-audio-preview", "provider": "openai", "model": "gpt-4o-audio-preview", "displayName": "OpenAI: GPT-4o Audio", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "kilo", "openai" ], "aliases": [ "kilo/openai/gpt-4o-audio-preview", "openai/gpt-4o-audio-preview" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": false, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-audio-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-audio-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } } ] }, "metadata": { "displayNames": [ "OpenAI: GPT-4o Audio" ], "modes": [ "chat" ], "releaseDate": "2025-08-15", "lastUpdated": "2026-03-15", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-audio-preview", "modelKey": "openai/gpt-4o-audio-preview", "displayName": "OpenAI: GPT-4o Audio", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-audio-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4o-audio-preview-2024-12-17", "provider": "openai", "model": "gpt-4o-audio-preview-2024-12-17", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-audio-preview-2024-12-17", "openai/gpt-4o-audio-preview-2024-12-17" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "nativeStreaming": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-audio-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-audio-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-audio-preview-2024-12-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-audio-preview-2024-12-17", "mode": "chat" } ] }, { "id": "openai/gpt-4o-audio-preview-2025-06-03", "provider": "openai", "model": "gpt-4o-audio-preview-2025-06-03", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-audio-preview-2025-06-03" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-audio-preview-2025-06-03", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-audio-preview-2025-06-03", "mode": "chat" } ] }, { "id": "openai/gpt-4o-aug", "provider": "openai", "model": "gpt-4o-aug", "displayName": "GPT-4o-Aug", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-4o-aug" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4o-aug", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.1, "input": 2.2, "output": 9 } } ] }, "metadata": { "displayNames": [ "GPT-4o-Aug" ], "families": [ "gpt" ], "releaseDate": "2024-11-21", "lastUpdated": "2024-11-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4o-aug", "modelKey": "openai/gpt-4o-aug", "displayName": "GPT-4o-Aug", "family": "gpt", "metadata": { "lastUpdated": "2024-11-21", "openWeights": false, "releaseDate": "2024-11-21" } } ] }, { "id": "openai/gpt-4o-mini", "provider": "openai", "model": "gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "github-models", "github_copilot", "gmi", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "replicate", "requesty", "vercel", "vercel_ai_gateway" ], "aliases": [ "abacus/gpt-4o-mini", "azure-cognitive-services/gpt-4o-mini", "azure/global-standard/gpt-4o-mini", "azure/gpt-4o-mini", "cloudflare-ai-gateway/openai/gpt-4o-mini", "github-models/openai/gpt-4o-mini", "github_copilot/gpt-4o-mini", "gmi/openai/gpt-4o-mini", "helicone/gpt-4o-mini", "kilo/openai/gpt-4o-mini", "llmgateway/gpt-4o-mini", "merge-gateway/openai/gpt-4o-mini", "nano-gpt/openai/gpt-4o-mini", "openai/gpt-4o-mini", "openrouter/openai/gpt-4o-mini", "orcarouter/openai/gpt-4o-mini", "poe/openai/gpt-4o-mini", "replicate/openai/gpt-4o-mini", "requesty/openai/gpt-4o-mini", "vercel/openai/gpt-4o-mini", "vercel_ai_gateway/openai/gpt-4o-mini" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1496, "output": 0.595 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.068, "input": 0.14, "output": 0.54 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4o-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "azure", "model": "azure/global-standard/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.165, "output": 0.66 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/openai/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 }, "extra": { "cache_read_input_token_cost_priority": 1.25e-7, "input_cost_per_token_batches": 7.5e-8, "input_cost_per_token_priority": 2.5e-7, "output_cost_per_token_batches": 3e-7, "output_cost_per_token_priority": 0.000001, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4o-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0, "input": 0.15, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "GPT-4o Mini", "GPT-4o mini", "GPT-4o-mini", "OpenAI GPT-4o-mini", "OpenAI: GPT-4o-mini" ], "families": [ "gpt", "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-04", "releaseDate": "2024-07-18", "lastUpdated": "2024-07-18", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "GPT-4o Mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "OpenAI GPT-4o-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "OpenAI: GPT-4o-mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-4o-mini", "modelKey": "gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o-mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4o-mini", "modelKey": "openai/gpt-4o-mini", "displayName": "GPT-4o mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global-standard/gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/openai/gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-4o-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/gpt-4o-mini", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-mini", "displayName": "OpenAI: GPT-4o-mini", "metadata": { "canonicalSlug": "openai/gpt-4o-mini", "createdAt": "2024-07-18T00:00:00.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openai/gpt-4o-mini-2024-07-18", "provider": "openai", "model": "gpt-4o-mini-2024-07-18", "displayName": "OpenAI: GPT-4o-mini (2024-07-18)", "family": "o-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "github_copilot", "kilo", "openai", "openrouter" ], "aliases": [ "azure/eu/gpt-4o-mini-2024-07-18", "azure/gpt-4o-mini-2024-07-18", "azure/us/gpt-4o-mini-2024-07-18", "github_copilot/gpt-4o-mini-2024-07-18", "kilo/openai/gpt-4o-mini-2024-07-18", "openai/gpt-4o-mini-2024-07-18", "openrouter/openai/gpt-4o-mini-2024-07-18" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-mini-2024-07-18", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-mini-2024-07-18", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.083, "input": 0.165, "output": 0.66 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.165, "output": 0.66 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.083, "input": 0.165, "output": 0.66 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-2024-07-18", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 }, "searchContextPerQuery": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "extra": { "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token_batches": 3e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-mini-2024-07-18", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "GPT-4o-mini (2024-07-18)", "OpenAI: GPT-4o-mini (2024-07-18)" ], "families": [ "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2024-07-18", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-mini-2024-07-18", "modelKey": "openai/gpt-4o-mini-2024-07-18", "displayName": "OpenAI: GPT-4o-mini (2024-07-18)", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-mini-2024-07-18", "modelKey": "openai/gpt-4o-mini-2024-07-18", "displayName": "GPT-4o-mini (2024-07-18)", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-mini-2024-07-18", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini-2024-07-18", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-mini-2024-07-18", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-4o-mini-2024-07-18", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-2024-07-18", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-mini-2024-07-18", "displayName": "OpenAI: GPT-4o-mini (2024-07-18)", "metadata": { "canonicalSlug": "openai/gpt-4o-mini-2024-07-18", "createdAt": "2024-07-18T00:00:00.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-4o-mini-audio-preview", "provider": "openai", "model": "gpt-4o-mini-audio-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-audio-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-audio-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "inputAudio": 10, "output": 0.6, "outputAudio": 20 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-audio-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4o-mini-audio-preview-2024-12-17", "provider": "openai", "model": "gpt-4o-mini-audio-preview-2024-12-17", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-mini-audio-preview-2024-12-17", "openai/gpt-4o-mini-audio-preview-2024-12-17" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "nativeStreaming": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini-audio-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-audio-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "inputAudio": 10, "output": 0.6, "outputAudio": 20 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini-audio-preview-2024-12-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-audio-preview-2024-12-17", "mode": "chat" } ] }, { "id": "openai/gpt-4o-mini-realtime-preview", "provider": "openai", "model": "gpt-4o-mini-realtime-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-realtime-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-realtime-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-realtime-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4o-mini-realtime-preview-2024-12-17", "provider": "openai", "model": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "azure/gpt-4o-mini-realtime-preview-2024-12-17", "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "openai/gpt-4o-mini-realtime-preview-2024-12-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "input": 0.66, "inputAudio": 11, "output": 2.64, "outputAudio": 22 }, "extra": { "cache_creation_input_audio_token_cost": 3.3e-7 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.33, "input": 0.66, "inputAudio": 11, "output": 2.64, "outputAudio": 22 }, "extra": { "cache_creation_input_audio_token_cost": 3.3e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat" } ] }, { "id": "openai/gpt-4o-mini-search", "provider": "openai", "model": "gpt-4o-mini-search", "displayName": "GPT-4o-mini-Search", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-4o-mini-search" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4o-mini-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.54 } } ] }, "metadata": { "displayNames": [ "GPT-4o-mini-Search" ], "families": [ "gpt-mini" ], "releaseDate": "2025-03-11", "lastUpdated": "2025-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4o-mini-search", "modelKey": "openai/gpt-4o-mini-search", "displayName": "GPT-4o-mini-Search", "family": "gpt-mini", "metadata": { "lastUpdated": "2025-03-11", "openWeights": false, "releaseDate": "2025-03-11" } } ] }, { "id": "openai/gpt-4o-mini-search-preview", "provider": "openai", "model": "gpt-4o-mini-search-preview", "displayName": "OpenAI: GPT-4o-mini Search Preview", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "llmgateway", "nano-gpt", "openai", "openrouter", "vercel" ], "aliases": [ "kilo/openai/gpt-4o-mini-search-preview", "llmgateway/gpt-4o-mini-search-preview", "nano-gpt/openai/gpt-4o-mini-search-preview", "openai/gpt-4o-mini-search-preview", "openrouter/openai/gpt-4o-mini-search-preview", "vercel/openai/gpt-4o-mini-search-preview" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-mini-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4o-mini-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o-mini-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.088, "output": 0.35 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-mini-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-4o-mini-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-search-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 }, "searchContextPerQuery": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "extra": { "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token_batches": 3e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-mini-search-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 }, "other": { "webSearch": 0.0275 } } ] }, "metadata": { "displayNames": [ "GPT 4o Mini Search Preview", "GPT-4o Mini Search Preview", "GPT-4o mini Search Preview", "GPT-4o-mini Search Preview", "OpenAI: GPT-4o-mini Search Preview" ], "families": [ "gpt", "gpt-mini", "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-01", "lastUpdated": "2025-01", "supportedParameters": [ "max_tokens", "response_format", "structured_outputs", "web_search_options" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-mini-search-preview", "modelKey": "openai/gpt-4o-mini-search-preview", "displayName": "OpenAI: GPT-4o-mini Search Preview", "metadata": { "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4o-mini-search-preview", "modelKey": "gpt-4o-mini-search-preview", "displayName": "GPT-4o Mini Search Preview", "family": "gpt", "metadata": { "lastUpdated": "2024-10-01", "openWeights": false, "releaseDate": "2024-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o-mini-search-preview", "modelKey": "openai/gpt-4o-mini-search-preview", "displayName": "GPT-4o mini Search Preview", "family": "gpt-mini", "metadata": { "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-mini-search-preview", "modelKey": "openai/gpt-4o-mini-search-preview", "displayName": "GPT-4o-mini Search Preview", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-03-12", "openWeights": false, "releaseDate": "2025-03-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-4o-mini-search-preview", "modelKey": "openai/gpt-4o-mini-search-preview", "displayName": "GPT 4o Mini Search Preview", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-03-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-search-preview", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-mini-search-preview", "displayName": "OpenAI: GPT-4o-mini Search Preview", "metadata": { "canonicalSlug": "openai/gpt-4o-mini-search-preview-2025-03-11", "createdAt": "2025-03-12T22:22:02.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-mini-search-preview-2025-03-11/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "structured_outputs", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-4o-mini-search-preview-2025-03-11", "provider": "openai", "model": "gpt-4o-mini-search-preview-2025-03-11", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-search-preview-2025-03-11" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-search-preview-2025-03-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 }, "extra": { "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token_batches": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-search-preview-2025-03-11", "mode": "chat" } ] }, { "id": "openai/gpt-4o-mini-transcribe", "provider": "openai", "model": "gpt-4o-mini-transcribe", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-mini-transcribe", "openai/gpt-4o-mini-transcribe" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini-transcribe", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "inputAudio": 1.25, "output": 5 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-transcribe", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "inputAudio": 1.25, "output": 5 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini-transcribe", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-transcribe", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/gpt-4o-mini-transcribe-2025-03-20", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-03-20", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-transcribe-2025-03-20" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-03-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "inputAudio": 1.25, "output": 5 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-03-20", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/gpt-4o-mini-transcribe-2025-12-15", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-12-15", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-transcribe-2025-12-15" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-12-15", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "inputAudio": 1.25, "output": 5 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-transcribe-2025-12-15", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/gpt-4o-mini-tts", "provider": "openai", "model": "gpt-4o-mini-tts", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-mini-tts", "openai/gpt-4o-mini-tts" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-mini-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10, "outputAudio": 12 }, "perAudioSecond": { "output": 0.00025 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-tts", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10, "outputAudio": 12 }, "perAudioSecond": { "output": 0.00025 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-mini-tts", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-tts", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/gpt-4o-mini-tts-2025-03-20", "provider": "openai", "model": "gpt-4o-mini-tts-2025-03-20", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-tts-2025-03-20" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-tts-2025-03-20", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10, "outputAudio": 12 }, "perAudioSecond": { "output": 0.00025 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-tts-2025-03-20", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/gpt-4o-mini-tts-2025-12-15", "provider": "openai", "model": "gpt-4o-mini-tts-2025-12-15", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-mini-tts-2025-12-15" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-mini-tts-2025-12-15", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10, "outputAudio": 12 }, "perAudioSecond": { "output": 0.00025 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-mini-tts-2025-12-15", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/gpt-4o-realtime-preview", "provider": "openai", "model": "gpt-4o-realtime-preview", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-realtime-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-realtime-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 5, "inputAudio": 40, "output": 20, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-realtime-preview", "mode": "chat" } ] }, { "id": "openai/gpt-4o-realtime-preview-2024-10-01", "provider": "openai", "model": "gpt-4o-realtime-preview-2024-10-01", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/eu/gpt-4o-realtime-preview-2024-10-01", "azure/gpt-4o-realtime-preview-2024-10-01", "azure/us/gpt-4o-realtime-preview-2024-10-01" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.75, "input": 5.5, "inputAudio": 110, "output": 22, "outputAudio": 220 }, "extra": { "cache_creation_input_audio_token_cost": 0.000022 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-realtime-preview-2024-10-01", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 5, "inputAudio": 100, "output": 20, "outputAudio": 200 }, "extra": { "cache_creation_input_audio_token_cost": 0.00002 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-realtime-preview-2024-10-01", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.75, "input": 5.5, "inputAudio": 110, "output": 22, "outputAudio": 220 }, "extra": { "cache_creation_input_audio_token_cost": 0.000022 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-realtime-preview-2024-10-01", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-realtime-preview-2024-10-01", "mode": "chat" } ] }, { "id": "openai/gpt-4o-realtime-preview-2024-12-17", "provider": "openai", "model": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/gpt-4o-realtime-preview-2024-12-17", "azure/gpt-4o-realtime-preview-2024-12-17", "azure/us/gpt-4o-realtime-preview-2024-12-17", "openai/gpt-4o-realtime-preview-2024-12-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.75, "input": 5.5, "inputAudio": 44, "output": 22, "outputAudio": 80 }, "extra": { "cache_read_input_audio_token_cost": 0.0000025 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 5, "inputAudio": 40, "output": 20, "outputAudio": 80 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-4o-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.75, "input": 5.5, "inputAudio": 44, "output": 22, "outputAudio": 80 }, "extra": { "cache_read_input_audio_token_cost": 0.0000025 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-realtime-preview-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 5, "inputAudio": 40, "output": 20, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-4o-realtime-preview-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat" } ] }, { "id": "openai/gpt-4o-realtime-preview-2025-06-03", "provider": "openai", "model": "gpt-4o-realtime-preview-2025-06-03", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-realtime-preview-2025-06-03" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-realtime-preview-2025-06-03", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 5, "inputAudio": 40, "output": 20, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-realtime-preview-2025-06-03", "mode": "chat" } ] }, { "id": "openai/gpt-4o-search", "provider": "openai", "model": "gpt-4o-search", "displayName": "GPT-4o-Search", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-4o-search" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-4o-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.2, "output": 9 } } ] }, "metadata": { "displayNames": [ "GPT-4o-Search" ], "families": [ "gpt" ], "releaseDate": "2025-03-11", "lastUpdated": "2025-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-4o-search", "modelKey": "openai/gpt-4o-search", "displayName": "GPT-4o-Search", "family": "gpt", "metadata": { "lastUpdated": "2025-03-11", "openWeights": false, "releaseDate": "2025-03-11" } } ] }, { "id": "openai/gpt-4o-search-preview", "provider": "openai", "model": "gpt-4o-search-preview", "displayName": "OpenAI: GPT-4o Search Preview", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "llmgateway", "nano-gpt", "openai", "openrouter" ], "aliases": [ "kilo/openai/gpt-4o-search-preview", "llmgateway/gpt-4o-search-preview", "nano-gpt/openai/gpt-4o-search-preview", "openai/gpt-4o-search-preview", "openrouter/openai/gpt-4o-search-preview" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "toolCalling": false, "structuredOutput": true, "temperature": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-4o-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-4o-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-4o-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.47, "output": 5.88 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-4o-search-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-search-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 }, "searchContextPerQuery": { "search_context_size_high": 0.05, "search_context_size_low": 0.03, "search_context_size_medium": 0.035 }, "extra": { "input_cost_per_token_batches": 0.00000125, "output_cost_per_token_batches": 0.000005 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-4o-search-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 }, "other": { "webSearch": 0.035 } } ] }, "metadata": { "displayNames": [ "GPT-4o Search Preview", "OpenAI: GPT-4o Search Preview" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-03-13", "lastUpdated": "2026-03-15", "supportedParameters": [ "max_tokens", "response_format", "structured_outputs", "web_search_options" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-4o-search-preview", "modelKey": "openai/gpt-4o-search-preview", "displayName": "OpenAI: GPT-4o Search Preview", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-4o-search-preview", "modelKey": "gpt-4o-search-preview", "displayName": "GPT-4o Search Preview", "family": "gpt", "metadata": { "lastUpdated": "2024-10-01", "openWeights": false, "releaseDate": "2024-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-4o-search-preview", "modelKey": "openai/gpt-4o-search-preview", "displayName": "GPT-4o Search Preview", "family": "gpt", "metadata": { "lastUpdated": "2024-05-13", "openWeights": false, "releaseDate": "2024-05-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-4o-search-preview", "modelKey": "openai/gpt-4o-search-preview", "displayName": "GPT-4o Search Preview", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-03-12", "openWeights": false, "releaseDate": "2025-03-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-search-preview", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-4o-search-preview", "displayName": "OpenAI: GPT-4o Search Preview", "metadata": { "canonicalSlug": "openai/gpt-4o-search-preview-2025-03-11", "createdAt": "2025-03-12T22:19:09.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/gpt-4o-search-preview-2025-03-11/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "structured_outputs", "web_search_options" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-4o-search-preview-2025-03-11", "provider": "openai", "model": "gpt-4o-search-preview-2025-03-11", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-4o-search-preview-2025-03-11" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-4o-search-preview-2025-03-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 2.5, "output": 10 }, "extra": { "input_cost_per_token_batches": 0.00000125, "output_cost_per_token_batches": 0.000005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-search-preview-2025-03-11", "mode": "chat" } ] }, { "id": "openai/gpt-4o-transcribe", "provider": "openai", "model": "gpt-4o-transcribe", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-transcribe", "openai/gpt-4o-transcribe" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-transcribe", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-transcribe", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 2.5, "output": 10 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-transcribe", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-transcribe", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/gpt-4o-transcribe-diarize", "provider": "openai", "model": "gpt-4o-transcribe-diarize", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-4o-transcribe-diarize", "openai/gpt-4o-transcribe-diarize" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 16000, "inputTokens": 16000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-4o-transcribe-diarize", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-4o-transcribe-diarize", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 2.5, "output": 10 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-4o-transcribe-diarize", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-4o-transcribe-diarize", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/gpt-5", "provider": "openai", "model": "gpt-5", "displayName": "GPT-5", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "anyapi", "azure", "azure-cognitive-services", "fastrouter", "github_copilot", "gmi", "helicone", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "neon", "openai", "opencode", "openrouter", "orcarouter", "poe", "qiniu-ai", "replicate", "requesty", "sap-ai-core", "vercel", "zenmux" ], "aliases": [ "302ai/gpt-5", "abacus/gpt-5", "anyapi/openai/gpt-5", "azure-cognitive-services/gpt-5", "azure/gpt-5", "fastrouter/openai/gpt-5", "github_copilot/gpt-5", "gmi/openai/gpt-5", "helicone/gpt-5", "kilo/openai/gpt-5", "llmgateway/gpt-5", "merge-gateway/openai/gpt-5", "nano-gpt/openai/gpt-5", "nearai/openai/gpt-5", "neon/gpt-5", "openai/gpt-5", "opencode/gpt-5", "openrouter/openai/gpt-5", "orcarouter/openai/gpt-5", "poe/openai/gpt-5", "qiniu-ai/openai/gpt-5", "replicate/openai/gpt-5", "requesty/openai/gpt-5", "sap-ai-core/gpt-5", "vercel/openai/gpt-5", "zenmux/openai/gpt-5" ], "mergedProviderModelRecords": 26, "limits": { "contextTokens": 409600, "inputTokens": 409600, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "audio", "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.107, "input": 1.07, "output": 8.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/openai/gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5", "GPT-5", "OpenAI GPT-5", "OpenAI/GPT-5", "OpenAI: GPT-5", "gpt-5" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 26 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "gpt-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "OpenAI GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "OpenAI: GPT-5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT 5", "family": "gpt", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "OpenAI/GPT-5", "metadata": { "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-5", "modelKey": "gpt-5", "displayName": "gpt-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5", "modelKey": "openai/gpt-5", "displayName": "GPT-5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/openai/gpt-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5", "displayName": "OpenAI: GPT-5", "metadata": { "canonicalSlug": "openai/gpt-5-2025-08-07", "createdAt": "2025-08-07T17:23:33.000Z", "knowledgeCutoff": "2024-09-30", "links": { "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openai/gpt-5-1", "provider": "openai", "model": "gpt-5-1", "displayName": "GPT-5.1", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gpt-5-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gpt-5-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-5.1" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-1", "modelKey": "gpt-5-1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-5-2", "provider": "openai", "model": "gpt-5-2", "displayName": "GPT-5.2", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gpt-5-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gpt-5-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.2" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-2", "modelKey": "gpt-5-2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "openai/gpt-5-2025-08-07", "provider": "openai", "model": "gpt-5-2025-08-07", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/gpt-5-2025-08-07", "azure/gpt-5-2025-08-07", "azure/us/gpt-5-2025-08-07", "openai/gpt-5-2025-08-07" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1375, "input": 1.375, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1375, "input": 1.375, "output": 11 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5-3-codex", "provider": "openai", "model": "gpt-5-3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "frogbot" ], "aliases": [ "frogbot/gpt-5-3-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "gpt-5-3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Codex" ], "families": [ "gpt" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-02-15", "lastUpdated": "2026-02-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-5-3-codex", "modelKey": "gpt-5-3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-02-15", "openWeights": false, "releaseDate": "2026-02-15" } } ] }, { "id": "openai/gpt-5-4", "provider": "openai", "model": "gpt-5-4", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "neon" ], "aliases": [ "neon/gpt-5-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neon", "model": "gpt-5-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-4", "modelKey": "gpt-5-4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "openai/gpt-5-4-mini", "provider": "openai", "model": "gpt-5-4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "frogbot", "neon" ], "aliases": [ "frogbot/gpt-5-4-mini", "neon/gpt-5-4-mini" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "gpt-5-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5-4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 Mini", "GPT-5.4 mini" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-17", "lastUpdated": "2026-03-17", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-5-4-mini", "modelKey": "gpt-5-4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-4-mini", "modelKey": "gpt-5-4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "openai/gpt-5-4-nano", "provider": "openai", "model": "gpt-5-4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "frogbot", "neon" ], "aliases": [ "frogbot/gpt-5-4-nano", "neon/gpt-5-4-nano" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "gpt-5-4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5-4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 Nano", "GPT-5.4 nano" ], "families": [ "gpt-nano" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-5-4-nano", "modelKey": "gpt-5-4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-4-nano", "modelKey": "gpt-5-4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "openai/gpt-5-5", "provider": "openai", "model": "gpt-5-5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "frogbot", "neon" ], "aliases": [ "frogbot/gpt-5-5", "neon/gpt-5-5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "gpt-5-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-5-5", "modelKey": "gpt-5-5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-5", "modelKey": "gpt-5-5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "openai/gpt-5-chat", "provider": "openai", "model": "gpt-5-chat", "displayName": "GPT-5 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "kilo", "openai", "openrouter", "poe", "requesty", "vercel" ], "aliases": [ "azure-cognitive-services/gpt-5-chat", "azure/gpt-5-chat", "kilo/openai/gpt-5-chat", "openai/gpt-5-chat", "openrouter/openai/gpt-5-chat", "poe/openai/gpt-5-chat", "requesty/openai/gpt-5-chat", "vercel/openai/gpt-5-chat" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 400000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": true, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "xhighReasoningEffort": false, "supports1MContext": false, "attachments": true, "openWeights": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-chat", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5 Chat", "GPT-5 Chat (latest)", "GPT-5-Chat", "OpenAI: GPT-5 Chat" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10-24", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "supportedParameters": [ "max_tokens", "response_format", "seed", "structured_outputs" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-chat", "modelKey": "gpt-5-chat", "displayName": "GPT-5 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-10-24", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-chat", "modelKey": "gpt-5-chat", "displayName": "GPT-5 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-10-24", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-chat", "modelKey": "openai/gpt-5-chat", "displayName": "OpenAI: GPT-5 Chat", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-chat", "modelKey": "openai/gpt-5-chat", "displayName": "GPT-5 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5-chat", "modelKey": "openai/gpt-5-chat", "displayName": "GPT-5-Chat", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-chat", "modelKey": "openai/gpt-5-chat", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5-chat", "modelKey": "openai/gpt-5-chat", "displayName": "GPT-5 Chat", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-chat", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5-chat", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-chat", "displayName": "OpenAI: GPT-5 Chat", "metadata": { "canonicalSlug": "openai/gpt-5-chat-2025-08-07", "createdAt": "2025-08-07T17:30:37.000Z", "knowledgeCutoff": "2024-09-30", "links": { "details": "/api/v1/models/openai/gpt-5-chat-2025-08-07/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "seed", "structured_outputs" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-chat-latest", "provider": "openai", "model": "gpt-5-chat-latest", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "helicone", "jiekou", "llmgateway", "merge-gateway", "openai", "orcarouter" ], "aliases": [ "azure/gpt-5-chat-latest", "helicone/gpt-5-chat-latest", "jiekou/gpt-5-chat-latest", "llmgateway/gpt-5-chat-latest", "merge-gateway/openai/gpt-5-chat-latest", "openai/gpt-5-chat-latest", "orcarouter/openai/gpt-5-chat-latest" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 16384, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-5 Chat (latest)", "OpenAI GPT-5 Chat Latest", "gpt-5-chat-latest" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-09-30", "lastUpdated": "2024-09-30", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5-chat-latest", "modelKey": "gpt-5-chat-latest", "displayName": "OpenAI GPT-5 Chat Latest", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-30", "openWeights": false, "releaseDate": "2024-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5-chat-latest", "modelKey": "gpt-5-chat-latest", "displayName": "gpt-5-chat-latest", "family": "gpt", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5-chat-latest", "modelKey": "gpt-5-chat-latest", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5-chat-latest", "modelKey": "openai/gpt-5-chat-latest", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5-chat-latest", "modelKey": "gpt-5-chat-latest", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5-chat-latest", "modelKey": "openai/gpt-5-chat-latest", "displayName": "GPT-5 Chat (latest)", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-chat-latest", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-chat-latest", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5-codex", "provider": "openai", "model": "gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "helicone", "jiekou", "kilo", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "zenmux" ], "aliases": [ "abacus/gpt-5-codex", "azure-cognitive-services/gpt-5-codex", "azure/gpt-5-codex", "helicone/gpt-5-codex", "jiekou/gpt-5-codex", "kilo/openai/gpt-5-codex", "nano-gpt/openai/gpt-5-codex", "openai/gpt-5-codex", "opencode/gpt-5-codex", "openrouter/openai/gpt-5-codex", "orcarouter/openai/gpt-5-codex", "poe/openai/gpt-5-codex", "requesty/openai/gpt-5-codex", "vercel/openai/gpt-5-codex", "zenmux/openai/gpt-5-codex" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 400000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.107, "input": 1.07, "output": 8.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-codex", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5 Codex", "GPT-5-Codex", "OpenAI: GPT-5 Codex", "gpt-5-codex" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-09-15", "lastUpdated": "2025-09-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "GPT-5 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "OpenAI: GPT-5 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "gpt-5-codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "OpenAI: GPT-5 Codex", "metadata": { "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5 Codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5-codex", "modelKey": "gpt-5-codex", "displayName": "GPT-5 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5-codex", "modelKey": "openai/gpt-5-codex", "displayName": "GPT-5 Codex", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5-codex", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-codex", "displayName": "OpenAI: GPT-5 Codex", "metadata": { "canonicalSlug": "openai/gpt-5-codex", "createdAt": "2025-09-23T16:03:23.000Z", "knowledgeCutoff": "2024-09-30", "links": { "details": "/api/v1/models/openai/gpt-5-codex/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-image", "provider": "openai", "model": "gpt-5-image", "displayName": "OpenAI: GPT-5 Image", "family": "gpt", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter", "requesty" ], "aliases": [ "kilo/openai/gpt-5-image", "openrouter/openai/gpt-5-image", "requesty/openai/gpt-5-image" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 10, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 10, "output": 10 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-image", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-image", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 10, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5 Image", "OpenAI: GPT-5 Image" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-10-01", "releaseDate": "2025-10-14", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-image", "modelKey": "openai/gpt-5-image", "displayName": "OpenAI: GPT-5 Image", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-10-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-image", "modelKey": "openai/gpt-5-image", "displayName": "GPT-5 Image", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-10-14", "openWeights": false, "releaseDate": "2025-10-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-image", "modelKey": "openai/gpt-5-image", "displayName": "GPT-5 Image", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-10-14", "openWeights": false, "releaseDate": "2025-10-14" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-image", "displayName": "OpenAI: GPT-5 Image", "metadata": { "canonicalSlug": "openai/gpt-5-image", "createdAt": "2025-10-14T13:19:46.000Z", "links": { "details": "/api/v1/models/openai/gpt-5-image/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-image-mini", "provider": "openai", "model": "gpt-5-image-mini", "displayName": "OpenAI: GPT-5 Image Mini", "family": "gpt", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/openai/gpt-5-image-mini", "openrouter/openai/gpt-5-image-mini" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-image-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-image-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-image-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 2 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5 Image Mini", "OpenAI: GPT-5 Image Mini" ], "families": [ "gpt" ], "releaseDate": "2025-10-16", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-image-mini", "modelKey": "openai/gpt-5-image-mini", "displayName": "OpenAI: GPT-5 Image Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-10-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-image-mini", "modelKey": "openai/gpt-5-image-mini", "displayName": "GPT-5 Image Mini", "family": "gpt", "metadata": { "lastUpdated": "2025-10-16", "openWeights": false, "releaseDate": "2025-10-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-image-mini", "displayName": "OpenAI: GPT-5 Image Mini", "metadata": { "canonicalSlug": "openai/gpt-5-image-mini", "createdAt": "2025-10-16T14:23:03.000Z", "links": { "details": "/api/v1/models/openai/gpt-5-image-mini/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-mini", "provider": "openai", "model": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "anyapi", "azure", "azure-cognitive-services", "fastrouter", "github-copilot", "github_copilot", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "neon", "openai", "openrouter", "orcarouter", "perplexity-agent", "poe", "qihang-ai", "replicate", "requesty", "sap-ai-core", "vercel", "vivgrid" ], "aliases": [ "302ai/gpt-5-mini", "abacus/gpt-5-mini", "anyapi/openai/gpt-5-mini", "azure-cognitive-services/gpt-5-mini", "azure/gpt-5-mini", "fastrouter/openai/gpt-5-mini", "github-copilot/gpt-5-mini", "github_copilot/gpt-5-mini", "helicone/gpt-5-mini", "jiekou/gpt-5-mini", "kilo/openai/gpt-5-mini", "llmgateway/gpt-5-mini", "merge-gateway/openai/gpt-5-mini", "nano-gpt/openai/gpt-5-mini", "nearai/openai/gpt-5-mini", "neon/gpt-5-mini", "openai/gpt-5-mini", "openrouter/openai/gpt-5-mini", "orcarouter/openai/gpt-5-mini", "perplexity-agent/openai/gpt-5-mini", "poe/openai/gpt-5-mini", "qihang-ai/gpt-5-mini", "replicate/openai/gpt-5-mini", "requesty/openai/gpt-5-mini", "sap-ai-core/gpt-5-mini", "vercel/openai/gpt-5-mini", "vivgrid/gpt-5-mini" ], "mergedProviderModelRecords": 27, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.024999999999999998, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.225, "output": 1.8 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.022, "input": 0.22, "output": 1.8 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.29 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "extra": { "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5 Mini", "GPT-5 Mini", "GPT-5-Mini", "GPT-5-mini", "OpenAI GPT-5 Mini", "OpenAI: GPT-5 Mini", "gpt-5-mini" ], "families": [ "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 27 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "gpt-5-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "OpenAI GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "gpt-5-mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "OpenAI: GPT-5 Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT 5 Mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5-mini", "family": "gpt-mini", "metadata": { "lastUpdated": "2025-06-25", "openWeights": false, "releaseDate": "2025-06-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5-Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-09-15", "openWeights": false, "releaseDate": "2025-09-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "gpt-5-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5-mini", "modelKey": "openai/gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5-mini", "modelKey": "gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-5-mini", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-mini", "displayName": "OpenAI: GPT-5 Mini", "metadata": { "canonicalSlug": "openai/gpt-5-mini-2025-08-07", "createdAt": "2025-08-07T17:23:27.000Z", "knowledgeCutoff": "2024-05-31", "links": { "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-mini-2025-08-07", "provider": "openai", "model": "gpt-5-mini-2025-08-07", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/gpt-5-mini-2025-08-07", "azure/gpt-5-mini-2025-08-07", "azure/us/gpt-5-mini-2025-08-07", "openai/gpt-5-mini-2025-08-07" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5-mini-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0275, "input": 0.275, "output": 2.2 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-mini-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5-mini-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0275, "input": 0.275, "output": 2.2 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-mini-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "extra": { "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5-mini-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-mini-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5-mini-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-mini-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5-nano", "provider": "openai", "model": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "azure-cognitive-services", "fastrouter", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "neon", "openai", "opencode", "openrouter", "orcarouter", "poe", "replicate", "requesty", "sap-ai-core", "vercel" ], "aliases": [ "abacus/gpt-5-nano", "azure-cognitive-services/gpt-5-nano", "azure/gpt-5-nano", "fastrouter/openai/gpt-5-nano", "helicone/gpt-5-nano", "jiekou/gpt-5-nano", "kilo/openai/gpt-5-nano", "llmgateway/gpt-5-nano", "merge-gateway/openai/gpt-5-nano", "nano-gpt/openai/gpt-5-nano", "nearai/openai/gpt-5-nano", "neon/gpt-5-nano", "openai/gpt-5-nano", "opencode/gpt-5-nano", "openrouter/openai/gpt-5-nano", "orcarouter/openai/gpt-5-nano", "poe/openai/gpt-5-nano", "replicate/openai/gpt-5-nano", "requesty/openai/gpt-5-nano", "sap-ai-core/gpt-5-nano", "vercel/openai/gpt-5-nano" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.049999999999999996, "output": 0.39999999999999997 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.36 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0045, "input": 0.045, "output": 0.36 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 }, "extra": { "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "output_cost_per_token_flex": 2e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-nano", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.05, "output": 0.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5 Nano", "GPT-5 Nano", "GPT-5-nano", "OpenAI GPT-5 Nano", "OpenAI: GPT-5 Nano", "gpt-5-nano" ], "families": [ "gpt-nano" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-10-01", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "OpenAI GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "gpt-5-nano", "family": "gpt-nano", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "OpenAI: GPT-5 Nano", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT 5 Nano", "family": "gpt-nano", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5-nano", "family": "gpt-nano", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-5-nano", "modelKey": "gpt-5-nano", "displayName": "gpt-5-nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5-nano", "modelKey": "openai/gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5-nano", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-5-nano", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-nano", "displayName": "OpenAI: GPT-5 Nano", "metadata": { "canonicalSlug": "openai/gpt-5-nano-2025-08-07", "createdAt": "2025-08-07T17:23:22.000Z", "knowledgeCutoff": "2024-05-31", "links": { "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openai/gpt-5-nano-2025-08-07", "provider": "openai", "model": "gpt-5-nano-2025-08-07", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/gpt-5-nano-2025-08-07", "azure/gpt-5-nano-2025-08-07", "azure/us/gpt-5-nano-2025-08-07", "openai/gpt-5-nano-2025-08-07" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5-nano-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0055, "input": 0.055, "output": 0.44 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-nano-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5-nano-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0055, "input": 0.055, "output": 0.44 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-nano-2025-08-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.005, "input": 0.05, "output": 0.4 }, "extra": { "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "output_cost_per_token_flex": 2e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5-nano-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-nano-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5-nano-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-nano-2025-08-07", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5-pro", "provider": "openai", "model": "gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "azure", "azure-cognitive-services", "helicone", "jiekou", "kilo", "llmgateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "requesty", "vercel" ], "aliases": [ "302ai/gpt-5-pro", "azure-cognitive-services/gpt-5-pro", "azure/gpt-5-pro", "helicone/gpt-5-pro", "jiekou/gpt-5-pro", "kilo/openai/gpt-5-pro", "llmgateway/gpt-5-pro", "nano-gpt/openai/gpt-5-pro", "openai/gpt-5-pro", "openrouter/openai/gpt-5-pro", "orcarouter/openai/gpt-5-pro", "poe/openai/gpt-5-pro", "requesty/openai/gpt-5-pro", "vercel/openai/gpt-5-pro" ], "mergedProviderModelRecords": 14, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 272000, "outputTokens": 272000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": false, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 13.5, "output": 108 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14, "output": 110 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 120 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 120 }, "extra": { "input_cost_per_token_batches": 0.0000075, "output_cost_per_token_batches": 0.00006, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 120 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5 Pro", "GPT-5 Pro", "GPT-5 pro", "GPT-5-Pro", "OpenAI: GPT-5 Pro", "gpt-5-pro" ], "families": [ "gpt", "gpt-pro" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-10-08", "lastUpdated": "2025-10-08", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 14 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "gpt-5-pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-08", "openWeights": false, "releaseDate": "2025-10-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06", "reasoningOptions": [ { "type": "effort", "values": [ "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06", "reasoningOptions": [ { "type": "effort", "values": [ "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "OpenAI: GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "gpt-5-pro", "family": "gpt-pro", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "OpenAI: GPT-5 Pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT 5 Pro", "family": "gpt-pro", "metadata": { "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5-pro", "modelKey": "gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06", "reasoningOptions": [ { "type": "effort", "values": [ "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT-5-Pro", "family": "gpt-pro", "metadata": { "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT-5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5-pro", "modelKey": "openai/gpt-5-pro", "displayName": "GPT-5 pro", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-08-07", "reasoningOptions": [ { "type": "effort", "values": [ "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5-pro", "mode": "responses", "metadata": { "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5-pro", "displayName": "OpenAI: GPT-5 Pro", "metadata": { "canonicalSlug": "openai/gpt-5-pro-2025-10-06", "createdAt": "2025-10-06T18:51:03.000Z", "knowledgeCutoff": "2024-09-30", "links": { "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high" ], "default_effort": "high" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5-pro-2025-10-06", "provider": "openai", "model": "gpt-5-pro-2025-10-06", "mode": "responses", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-5-pro-2025-10-06" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 272000, "outputTokens": 272000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": false, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-5-pro-2025-10-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 120 }, "extra": { "input_cost_per_token_batches": 0.0000075, "output_cost_per_token_batches": 0.00006 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-pro-2025-10-06", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5-search-api", "provider": "openai", "model": "gpt-5-search-api", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-5-search-api" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-5-search-api", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-search-api", "mode": "chat" } ] }, { "id": "openai/gpt-5-search-api-2025-10-14", "provider": "openai", "model": "gpt-5-search-api-2025-10-14", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-5-search-api-2025-10-14" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-5-search-api-2025-10-14", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5-search-api-2025-10-14", "mode": "chat" } ] }, { "id": "openai/gpt-5-thinking", "provider": "openai", "model": "gpt-5-thinking", "displayName": "gpt-5-thinking", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/gpt-5-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "gpt-5-thinking" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-08-08", "lastUpdated": "2025-08-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5-thinking", "modelKey": "gpt-5-thinking", "displayName": "gpt-5-thinking", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-08", "openWeights": false, "releaseDate": "2025-08-08" } } ] }, { "id": "openai/gpt-5.1", "provider": "openai", "model": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "github_copilot", "gmi", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "perplexity-agent", "poe", "requesty", "zenmux" ], "aliases": [ "302ai/gpt-5.1", "abacus/gpt-5.1", "aihubmix/gpt-5.1", "anyapi/openai/gpt-5.1", "azure-cognitive-services/gpt-5.1", "azure/eu/gpt-5.1", "azure/global/gpt-5.1", "azure/gpt-5.1", "azure/us/gpt-5.1", "cloudflare-ai-gateway/openai/gpt-5.1", "github_copilot/gpt-5.1", "gmi/openai/gpt-5.1", "helicone/gpt-5.1", "jiekou/gpt-5.1", "kilo/openai/gpt-5.1", "llmgateway/gpt-5.1", "merge-gateway/openai/gpt-5.1", "nano-gpt/openai/gpt-5.1", "nearai/openai/gpt-5.1", "openai/gpt-5.1", "opencode/gpt-5.1", "openrouter/openai/gpt-5.1", "orcarouter/openai/gpt-5.1", "perplexity-agent/openai/gpt-5.1", "poe/openai/gpt-5.1", "requesty/openai/gpt-5.1", "zenmux/openai/gpt-5.1" ], "mergedProviderModelRecords": 27, "limits": { "contextTokens": 409600, "inputTokens": 409600, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "audio", "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.107, "input": 1.07, "output": 8.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/openai/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.1", "GPT-5.1", "OpenAI GPT-5.1", "OpenAI: GPT-5.1", "gpt-5.1" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 27 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "gpt-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "OpenAI GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "gpt-5.1", "family": "gpt", "metadata": { "lastUpdated": "2026-02", "openWeights": false, "releaseDate": "2026-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "OpenAI: GPT-5.1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT 5.1", "family": "gpt", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.1", "modelKey": "gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "lastUpdated": "2025-11-12", "openWeights": false, "releaseDate": "2025-11-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.1", "modelKey": "openai/gpt-5.1", "displayName": "GPT-5.1", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/openai/gpt-5.1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.1", "displayName": "OpenAI: GPT-5.1", "metadata": { "canonicalSlug": "openai/gpt-5.1-20251113", "createdAt": "2025-11-13T18:58:25.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "none" ], "default_effort": "none" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openai/gpt-5.1-2025-11-13", "provider": "openai", "model": "gpt-5.1-2025-11-13", "displayName": "GPT-5.1 (2025-11-13)", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "nano-gpt", "openai" ], "aliases": [ "azure/gpt-5.1-2025-11-13", "nano-gpt/openai/gpt-5.1-2025-11-13", "openai/gpt-5.1-2025-11-13" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": true, "attachments": false, "openWeights": false, "structuredOutput": false, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.1-2025-11-13", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-2025-11-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1-2025-11-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } } ] }, "metadata": { "displayNames": [ "GPT-5.1 (2025-11-13)" ], "families": [ "gpt" ], "modes": [ "chat" ], "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.1-2025-11-13", "modelKey": "openai/gpt-5.1-2025-11-13", "displayName": "GPT-5.1 (2025-11-13)", "family": "gpt", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-2025-11-13", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1-2025-11-13", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.1-chat", "provider": "openai", "model": "gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "kilo", "openrouter", "requesty", "zenmux" ], "aliases": [ "azure-cognitive-services/gpt-5.1-chat", "azure/eu/gpt-5.1-chat", "azure/global/gpt-5.1-chat", "azure/gpt-5.1-chat", "azure/us/gpt-5.1-chat", "kilo/openai/gpt-5.1-chat", "openrouter/openai/gpt-5.1-chat", "requesty/openai/gpt-5.1-chat", "zenmux/openai/gpt-5.1-chat" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text" ], "output": [ "audio", "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.1-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5.1-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-5.1-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5.1-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.1-chat", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5.1 Chat", "OpenAI: GPT-5.1 Chat" ], "families": [ "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-chat", "modelKey": "gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-chat", "modelKey": "gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.1-chat", "modelKey": "openai/gpt-5.1-chat", "displayName": "OpenAI: GPT-5.1 Chat", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.1-chat", "modelKey": "openai/gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.1-chat", "modelKey": "openai/gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.1-chat", "modelKey": "openai/gpt-5.1-chat", "displayName": "GPT-5.1 Chat", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5.1-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-5.1-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5.1-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.1-chat", "displayName": "OpenAI: GPT-5.1 Chat", "metadata": { "canonicalSlug": "openai/gpt-5.1-chat-20251113", "createdAt": "2025-11-13T18:58:22.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.1-chat-20251113/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 32000, "is_moderated": false } } } ] }, { "id": "openai/gpt-5.1-chat-2025-11-13", "provider": "openai", "model": "gpt-5.1-chat-2025-11-13", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-5.1-chat-2025-11-13" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-chat-2025-11-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-chat-2025-11-13", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.1-chat-latest", "provider": "openai", "model": "gpt-5.1-chat-latest", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "helicone", "merge-gateway", "openai", "orcarouter" ], "aliases": [ "302ai/gpt-5.1-chat-latest", "abacus/gpt-5.1-chat-latest", "helicone/gpt-5.1-chat-latest", "merge-gateway/openai/gpt-5.1-chat-latest", "openai/gpt-5.1-chat-latest", "orcarouter/openai/gpt-5.1-chat-latest" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 400000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": false, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.1-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } } ] }, "metadata": { "displayNames": [ "GPT-5.1 Chat", "GPT-5.1 Chat Latest", "OpenAI GPT-5.1 Chat", "gpt-5.1-chat-latest" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-14", "lastUpdated": "2025-11-14", "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.1-chat-latest", "modelKey": "gpt-5.1-chat-latest", "displayName": "gpt-5.1-chat-latest", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.1-chat-latest", "modelKey": "gpt-5.1-chat-latest", "displayName": "GPT-5.1 Chat Latest", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5.1-chat-latest", "modelKey": "gpt-5.1-chat-latest", "displayName": "OpenAI GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.1-chat-latest", "modelKey": "openai/gpt-5.1-chat-latest", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.1-chat-latest", "modelKey": "gpt-5.1-chat-latest", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.1-chat-latest", "modelKey": "openai/gpt-5.1-chat-latest", "displayName": "GPT-5.1 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1-chat-latest", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.1-codex", "provider": "openai", "model": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "aihubmix", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "helicone", "jiekou", "kilo", "llmgateway", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "vivgrid", "zenmux" ], "aliases": [ "abacus/gpt-5.1-codex", "aihubmix/gpt-5.1-codex", "azure-cognitive-services/gpt-5.1-codex", "azure/eu/gpt-5.1-codex", "azure/global/gpt-5.1-codex", "azure/gpt-5.1-codex", "azure/us/gpt-5.1-codex", "cloudflare-ai-gateway/openai/gpt-5.1-codex", "helicone/gpt-5.1-codex", "jiekou/gpt-5.1-codex", "kilo/openai/gpt-5.1-codex", "llmgateway/gpt-5.1-codex", "nano-gpt/openai/gpt-5.1-codex", "openai/gpt-5.1-codex", "opencode/gpt-5.1-codex", "openrouter/openai/gpt-5.1-codex", "orcarouter/openai/gpt-5.1-codex", "poe/openai/gpt-5.1-codex", "requesty/openai/gpt-5.1-codex", "vercel/openai/gpt-5.1-codex", "vivgrid/gpt-5.1-codex", "zenmux/openai/gpt-5.1-codex" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "audio", "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": true, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12500000000000003, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.107, "input": 1.07, "output": 8.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5.1-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-5.1-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5.1-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.14, "input": 1.38, "output": 11 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.1-codex", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.13, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.1 Codex", "GPT-5.1 Codex", "GPT-5.1-Codex", "OpenAI: GPT-5.1 Codex", "OpenAI: GPT-5.1-Codex", "gpt-5.1-codex" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "OpenAI: GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "OpenAI: GPT-5.1-Codex", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT 5.1 Codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1-Codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-11-12", "openWeights": false, "releaseDate": "2025-11-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1-Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.1-codex", "modelKey": "gpt-5.1-codex", "displayName": "GPT-5.1 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.1-codex", "modelKey": "openai/gpt-5.1-codex", "displayName": "GPT-5.1-Codex", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5.1-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-5.1-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5.1-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.1-codex", "displayName": "OpenAI: GPT-5.1-Codex", "metadata": { "canonicalSlug": "openai/gpt-5.1-codex-20251113", "createdAt": "2025-11-13T18:58:18.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openai/gpt-5.1-codex-2025-11-13", "provider": "openai", "model": "gpt-5.1-codex-2025-11-13", "mode": "responses", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-5.1-codex-2025-11-13" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-codex-2025-11-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "extra": { "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token_priority": 0.00002 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-codex-2025-11-13", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.1-codex-max", "provider": "openai", "model": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "chatgpt", "github_copilot", "jiekou", "kilo", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "vivgrid" ], "aliases": [ "abacus/gpt-5.1-codex-max", "azure/gpt-5.1-codex-max", "chatgpt/gpt-5.1-codex-max", "github_copilot/gpt-5.1-codex-max", "jiekou/gpt-5.1-codex-max", "kilo/openai/gpt-5.1-codex-max", "nano-gpt/openai/gpt-5.1-codex-max", "openai/gpt-5.1-codex-max", "opencode/gpt-5.1-codex-max", "openrouter/openai/gpt-5.1-codex-max", "orcarouter/openai/gpt-5.1-codex-max", "poe/openai/gpt-5.1-codex-max", "requesty/openai/gpt-5.1-codex-max", "vercel/openai/gpt-5.1-codex-max", "vivgrid/gpt-5.1-codex-max" ], "mergedProviderModelRecords": 15, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.125, "output": 9 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 20 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.1-codex-max", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-codex-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.1-codex-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5.1-codex-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1-codex-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5.1-codex-max", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.1-codex-max", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.1 Codex Max", "GPT-5.1 Codex Max", "GPT-5.1-Codex-Max", "OpenAI: GPT-5.1-Codex-Max", "gpt-5.1-codex-max" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 15 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "OpenAI: GPT-5.1-Codex-Max", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT 5.1 Codex Max", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT-5.1-Codex-Max", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT-5.1-Codex-Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.1-codex-max", "modelKey": "openai/gpt-5.1-codex-max", "displayName": "GPT 5.1 Codex Max", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.1-codex-max", "modelKey": "gpt-5.1-codex-max", "displayName": "GPT-5.1 Codex Max", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-codex-max", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.1-codex-max", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5.1-codex-max", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1-codex-max", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5.1-codex-max", "mode": "chat", "metadata": { "source": "https://openrouter.ai/openai/gpt-5.1-codex-max" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.1-codex-max", "displayName": "OpenAI: GPT-5.1-Codex-Max", "metadata": { "canonicalSlug": "openai/gpt-5.1-codex-max-20251204", "createdAt": "2025-12-04T20:08:54.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.1-codex-mini", "provider": "openai", "model": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "azure", "azure-cognitive-services", "chatgpt", "helicone", "jiekou", "kilo", "llmgateway", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "zenmux" ], "aliases": [ "aihubmix/gpt-5.1-codex-mini", "azure-cognitive-services/gpt-5.1-codex-mini", "azure/eu/gpt-5.1-codex-mini", "azure/global/gpt-5.1-codex-mini", "azure/gpt-5.1-codex-mini", "azure/us/gpt-5.1-codex-mini", "chatgpt/gpt-5.1-codex-mini", "helicone/gpt-5.1-codex-mini", "jiekou/gpt-5.1-codex-mini", "kilo/openai/gpt-5.1-codex-mini", "llmgateway/gpt-5.1-codex-mini", "nano-gpt/openai/gpt-5.1-codex-mini", "openai/gpt-5.1-codex-mini", "opencode/gpt-5.1-codex-mini", "openrouter/openai/gpt-5.1-codex-mini", "orcarouter/openai/gpt-5.1-codex-mini", "poe/openai/gpt-5.1-codex-mini", "requesty/openai/gpt-5.1-codex-mini", "vercel/openai/gpt-5.1-codex-mini", "zenmux/openai/gpt-5.1-codex-mini" ], "mergedProviderModelRecords": 20, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.024999999999999998, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.225, "output": 1.8 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.022, "input": 0.22, "output": 1.8 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "azure", "model": "azure/eu/gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "input": 0.275, "output": 2.2 } }, { "source": "litellm", "provider": "azure", "model": "azure/global/gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.028, "input": 0.275, "output": 2.2 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.1-codex-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "extra": { "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token_priority": 0.0000036 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.1-codex-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.1 Codex Mini", "GPT-5.1 Codex Mini", "GPT-5.1 Codex mini", "GPT-5.1-Codex-Mini", "OpenAI: GPT-5.1 Codex Mini", "OpenAI: GPT-5.1-Codex-Mini", "gpt-5.1-codex-mini" ], "families": [ "gpt", "gpt-codex", "gpt-codex-mini" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 20 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex Mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex Mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-14", "openWeights": false, "releaseDate": "2025-11-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "OpenAI: GPT-5.1 Codex Mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "OpenAI: GPT-5.1-Codex-Mini", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT 5.1 Codex Mini", "family": "gpt-codex-mini", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.1-codex-mini", "modelKey": "gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex Mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1-Codex-Mini", "family": "gpt-codex", "metadata": { "lastUpdated": "2025-11-12", "openWeights": false, "releaseDate": "2025-11-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1-Codex-Mini", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1 Codex mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-12", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.1-codex-mini", "modelKey": "openai/gpt-5.1-codex-mini", "displayName": "GPT-5.1-Codex-Mini", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/global/gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.1-codex-mini", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.1-codex-mini", "displayName": "OpenAI: GPT-5.1-Codex-Mini", "metadata": { "canonicalSlug": "openai/gpt-5.1-codex-mini-20251113", "createdAt": "2025-11-13T18:17:00.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.1-codex-mini-2025-11-13", "provider": "openai", "model": "gpt-5.1-codex-mini-2025-11-13", "mode": "responses", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-5.1-codex-mini-2025-11-13" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.1-codex-mini-2025-11-13", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 2 }, "extra": { "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token_priority": 0.0000036 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.1-codex-mini-2025-11-13", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.1-instant", "provider": "openai", "model": "gpt-5.1-instant", "displayName": "GPT-5.1-Instant", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "poe", "vercel" ], "aliases": [ "poe/openai/gpt-5.1-instant", "vercel/openai/gpt-5.1-instant" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 111616, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.1-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 1.1, "output": 9 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.1-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT-5.1 Instant", "GPT-5.1-Instant" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-11-12", "lastUpdated": "2025-11-12", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.1-instant", "modelKey": "openai/gpt-5.1-instant", "displayName": "GPT-5.1-Instant", "family": "gpt", "metadata": { "lastUpdated": "2025-11-12", "openWeights": false, "releaseDate": "2025-11-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.1-instant", "modelKey": "openai/gpt-5.1-instant", "displayName": "GPT-5.1 Instant", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-11-12", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } } ] }, { "id": "openai/gpt-5.1-thinking", "provider": "openai", "model": "gpt-5.1-thinking", "displayName": "GPT 5.1 Thinking", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/openai/gpt-5.1-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.1-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "displayNames": [ "GPT 5.1 Thinking" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-11-12", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.1-thinking", "modelKey": "openai/gpt-5.1-thinking", "displayName": "GPT 5.1 Thinking", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-11-12", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-5.2", "provider": "openai", "model": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "azure", "azure-cognitive-services", "chatgpt", "cloudflare-ai-gateway", "github-copilot", "github_copilot", "gmi", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "perplexity-agent", "poe", "qihang-ai", "qiniu-ai", "requesty", "vercel", "zenmux" ], "aliases": [ "302ai/gpt-5.2", "abacus/gpt-5.2", "aihubmix/gpt-5.2", "anyapi/openai/gpt-5.2", "azure-cognitive-services/gpt-5.2", "azure/gpt-5.2", "chatgpt/gpt-5.2", "cloudflare-ai-gateway/openai/gpt-5.2", "github-copilot/gpt-5.2", "github_copilot/gpt-5.2", "gmi/openai/gpt-5.2", "jiekou/gpt-5.2", "kilo/openai/gpt-5.2", "llmgateway/gpt-5.2", "merge-gateway/openai/gpt-5.2", "nano-gpt/openai/gpt-5.2", "nearai/openai/gpt-5.2", "openai/gpt-5.2", "opencode/gpt-5.2", "openrouter/openai/gpt-5.2", "orcarouter/openai/gpt-5.2", "perplexity-agent/openai/gpt-5.2", "poe/openai/gpt-5.2", "qihang-ai/gpt-5.2", "qiniu-ai/openai/gpt-5.2", "requesty/openai/gpt-5.2", "vercel/openai/gpt-5.2", "zenmux/openai/gpt-5.2" ], "mergedProviderModelRecords": 28, "limits": { "contextTokens": 409600, "inputTokens": 409600, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.125, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.575, "output": 12.6 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.18, "input": 1.8, "output": 15.5 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 13 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.17, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "gmi", "model": "gmi/openai/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.2", "GPT-5.2", "OpenAI/GPT-5.2", "OpenAI: GPT-5.2", "gpt-5.2" ], "families": [ "gpt" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-12", "lastUpdated": "2025-12-12", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 28 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "gpt-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-12", "openWeights": false, "releaseDate": "2025-12-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "gpt-5.2", "family": "gpt", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "OpenAI: GPT-5.2", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT 5.2", "family": "gpt", "metadata": { "lastUpdated": "2026-01-01", "openWeights": false, "releaseDate": "2026-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gpt-5.2", "modelKey": "gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "OpenAI/GPT-5.2", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.2", "modelKey": "openai/gpt-5.2", "displayName": "GPT-5.2", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.2", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5.2", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/openai/gpt-5.2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.2", "displayName": "OpenAI: GPT-5.2", "metadata": { "canonicalSlug": "openai/gpt-5.2-20251211", "createdAt": "2025-12-10T18:02:55.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.2-2025-12-11", "provider": "openai", "model": "gpt-5.2-2025-12-11", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-5.2-2025-12-11", "openai/gpt-5.2-2025-12-11" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-2025-12-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2-2025-12-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-2025-12-11", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2-2025-12-11", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.2-chat", "provider": "openai", "model": "gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "azure-cognitive-services", "kilo", "openrouter", "requesty", "vercel" ], "aliases": [ "azure-cognitive-services/gpt-5.2-chat", "azure/gpt-5.2-chat", "kilo/openai/gpt-5.2-chat", "openrouter/openai/gpt-5.2-chat", "requesty/openai/gpt-5.2-chat", "vercel/openai/gpt-5.2-chat" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.2-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.2-chat", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5.2 Chat", "OpenAI: GPT-5.2 Chat" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2-chat", "modelKey": "gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2-chat", "modelKey": "gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.2-chat", "modelKey": "openai/gpt-5.2-chat", "displayName": "OpenAI: GPT-5.2 Chat", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.2-chat", "modelKey": "openai/gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-10", "openWeights": false, "releaseDate": "2025-12-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.2-chat", "modelKey": "openai/gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.2-chat", "modelKey": "openai/gpt-5.2-chat", "displayName": "GPT-5.2 Chat", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-chat", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.2-chat", "displayName": "OpenAI: GPT-5.2 Chat", "metadata": { "canonicalSlug": "openai/gpt-5.2-chat-20251211", "createdAt": "2025-12-10T18:03:03.000Z", "expirationDate": "2026-08-10", "links": { "details": "/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.2-chat-2025-12-11", "provider": "openai", "model": "gpt-5.2-chat-2025-12-11", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-5.2-chat-2025-12-11" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-chat-2025-12-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-chat-2025-12-11", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.2-chat-latest", "provider": "openai", "model": "gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "llmgateway", "merge-gateway", "openai", "orcarouter" ], "aliases": [ "302ai/gpt-5.2-chat-latest", "abacus/gpt-5.2-chat-latest", "llmgateway/gpt-5.2-chat-latest", "merge-gateway/openai/gpt-5.2-chat-latest", "openai/gpt-5.2-chat-latest", "orcarouter/openai/gpt-5.2-chat-latest" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 400000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.2-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } } ] }, "metadata": { "displayNames": [ "GPT-5.2 Chat", "GPT-5.2 Chat Latest", "gpt-5.2-chat-latest" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-12", "lastUpdated": "2025-12-12", "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.2-chat-latest", "modelKey": "gpt-5.2-chat-latest", "displayName": "gpt-5.2-chat-latest", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-12", "openWeights": false, "releaseDate": "2025-12-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.2-chat-latest", "modelKey": "gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat Latest", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2026-01-01", "openWeights": false, "releaseDate": "2026-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.2-chat-latest", "modelKey": "gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.2-chat-latest", "modelKey": "openai/gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.2-chat-latest", "modelKey": "gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.2-chat-latest", "modelKey": "openai/gpt-5.2-chat-latest", "displayName": "GPT-5.2 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2-chat-latest", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.2-codex", "provider": "openai", "model": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "aihubmix", "azure", "azure-cognitive-services", "chatgpt", "cloudflare-ai-gateway", "github-copilot", "jiekou", "kilo", "llmgateway", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "qihang-ai", "requesty", "vercel", "vivgrid", "zenmux" ], "aliases": [ "abacus/gpt-5.2-codex", "aihubmix/gpt-5.2-codex", "azure-cognitive-services/gpt-5.2-codex", "azure/gpt-5.2-codex", "chatgpt/gpt-5.2-codex", "cloudflare-ai-gateway/openai/gpt-5.2-codex", "github-copilot/gpt-5.2-codex", "jiekou/gpt-5.2-codex", "kilo/openai/gpt-5.2-codex", "llmgateway/gpt-5.2-codex", "nano-gpt/openai/gpt-5.2-codex", "openai/gpt-5.2-codex", "opencode/gpt-5.2-codex", "openrouter/openai/gpt-5.2-codex", "orcarouter/openai/gpt-5.2-codex", "poe/openai/gpt-5.2-codex", "qihang-ai/gpt-5.2-codex", "requesty/openai/gpt-5.2-codex", "vercel/openai/gpt-5.2-codex", "vivgrid/gpt-5.2-codex", "zenmux/openai/gpt-5.2-codex" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 13 } }, { "source": "models.dev", "provider": "qihang-ai", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 1.14 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.17, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.2-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.2-codex", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.2 Codex", "GPT-5.2 Codex", "GPT-5.2-Codex", "OpenAI: GPT-5.2-Codex", "gpt-5.2-codex" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "gpt-5.2-codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "OpenAI: GPT-5.2-Codex", "metadata": { "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT 5.2 Codex", "family": "gpt-codex", "metadata": { "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2-Codex", "metadata": { "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qihang-ai", "providerName": "QiHang", "providerApi": "https://api.qhaigc.net/v1", "providerDoc": "https://www.qhaigc.net/docs", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.2-codex", "modelKey": "gpt-5.2-codex", "displayName": "GPT-5.2 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-01-14", "openWeights": false, "releaseDate": "2026-01-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.2-codex", "modelKey": "openai/gpt-5.2-codex", "displayName": "GPT-5.2-Codex", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-15", "openWeights": false, "releaseDate": "2026-01-15", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.2-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-codex", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.2-codex", "displayName": "OpenAI: GPT-5.2-Codex", "metadata": { "canonicalSlug": "openai/gpt-5.2-codex-20260114", "createdAt": "2026-01-14T16:48:35.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.2-instant", "provider": "openai", "model": "gpt-5.2-instant", "displayName": "GPT-5.2-Instant", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/openai/gpt-5.2-instant" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.2-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 13 } } ] }, "metadata": { "displayNames": [ "GPT-5.2-Instant" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.2-instant", "modelKey": "openai/gpt-5.2-instant", "displayName": "GPT-5.2-Instant", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "openai/gpt-5.2-pro", "provider": "openai", "model": "gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "jiekou", "kilo", "llmgateway", "nano-gpt", "openai", "openrouter", "orcarouter", "poe", "requesty", "vercel", "zenmux" ], "aliases": [ "azure/gpt-5.2-pro", "jiekou/gpt-5.2-pro", "kilo/openai/gpt-5.2-pro", "llmgateway/gpt-5.2-pro", "nano-gpt/openai/gpt-5.2-pro", "openai/gpt-5.2-pro", "openrouter/openai/gpt-5.2-pro", "orcarouter/openai/gpt-5.2-pro", "poe/openai/gpt-5.2-pro", "requesty/openai/gpt-5.2-pro", "vercel/openai/gpt-5.2-pro", "zenmux/openai/gpt-5.2-pro" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "jiekou", "model": "gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 18.9, "output": 151.2 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 19, "output": 150 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 }, "perImage": { "input": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.2-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.2", "GPT 5.2 Pro", "GPT-5.2 Pro", "GPT-5.2-Pro", "OpenAI: GPT-5.2 Pro", "gpt-5.2-pro" ], "families": [ "gpt", "gpt-pro" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-01", "lastUpdated": "2026-01", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "gpt-5.2-pro", "modelKey": "gpt-5.2-pro", "displayName": "gpt-5.2-pro", "family": "gpt-pro", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "OpenAI: GPT-5.2 Pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.2-pro", "modelKey": "gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT 5.2 Pro", "family": "gpt-pro", "metadata": { "lastUpdated": "2026-01-01", "openWeights": false, "releaseDate": "2026-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.2-pro", "modelKey": "gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT-5.2-Pro", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT-5.2 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT 5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.2-pro", "modelKey": "openai/gpt-5.2-pro", "displayName": "GPT-5.2-Pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-5.2-pro", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.2-pro", "displayName": "OpenAI: GPT-5.2 Pro", "metadata": { "canonicalSlug": "openai/gpt-5.2-pro-20251211", "createdAt": "2025-12-10T18:03:00.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high", "medium" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.2-pro-2025-12-11", "provider": "openai", "model": "gpt-5.2-pro-2025-12-11", "mode": "responses", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-5.2-pro-2025-12-11", "openai/gpt-5.2-pro-2025-12-11" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 272000, "inputTokens": 272000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.2-pro-2025-12-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.2-pro-2025-12-11", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 21, "output": 168 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.2-pro-2025-12-11", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.2-pro-2025-12-11", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.3-chat", "provider": "openai", "model": "gpt-5.3-chat", "displayName": "GPT-5.3 Chat", "family": "gpt-codex", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "kilo", "openrouter", "vercel", "zenmux" ], "aliases": [ "azure/gpt-5.3-chat", "kilo/openai/gpt-5.3-chat", "openrouter/openai/gpt-5.3-chat", "vercel/openai/gpt-5.3-chat", "zenmux/openai/gpt-5.3-chat" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "gpt-5.3-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.3-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.3-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.3-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.3-chat", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.3-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.3-chat", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Chat", "OpenAI: GPT-5.3 Chat" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.3-chat", "modelKey": "gpt-5.3-chat", "displayName": "GPT-5.3 Chat", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.3-chat", "modelKey": "openai/gpt-5.3-chat", "displayName": "OpenAI: GPT-5.3 Chat", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.3-chat", "modelKey": "openai/gpt-5.3-chat", "displayName": "GPT-5.3 Chat", "family": "gpt", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.3-chat", "modelKey": "openai/gpt-5.3-chat", "displayName": "GPT-5.3 Chat", "family": "gpt", "metadata": { "lastUpdated": "2026-03-06", "openWeights": false, "releaseDate": "2026-03-03", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.3-chat", "modelKey": "openai/gpt-5.3-chat", "displayName": "GPT-5.3 Chat", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.3-chat", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.3-chat", "displayName": "OpenAI: GPT-5.3 Chat", "metadata": { "canonicalSlug": "openai/gpt-5.3-chat-20260303", "createdAt": "2026-03-03T18:54:21.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.3-chat-20260303/endpoints" }, "supportedParameters": [ "max_completion_tokens", "max_tokens", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openai/gpt-5.3-chat-latest", "provider": "openai", "model": "gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat (latest)", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "chatgpt", "llmgateway", "merge-gateway", "openai", "orcarouter" ], "aliases": [ "abacus/gpt-5.3-chat-latest", "chatgpt/gpt-5.3-chat-latest", "llmgateway/gpt-5.3-chat-latest", "merge-gateway/openai/gpt-5.3-chat-latest", "openai/gpt-5.3-chat-latest", "orcarouter/openai/gpt-5.3-chat-latest" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 400000, "inputTokens": 128000, "maxTokens": 64000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.3-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.3-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.3-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.3-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.3-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.3-chat-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Chat (latest)", "GPT-5.3 Chat Latest" ], "families": [ "gpt" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-01", "lastUpdated": "2026-03-01", "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.3-chat-latest", "modelKey": "gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat Latest", "family": "gpt", "metadata": { "lastUpdated": "2026-03-01", "openWeights": false, "releaseDate": "2026-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.3-chat-latest", "modelKey": "gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat (latest)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.3-chat-latest", "modelKey": "openai/gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat (latest)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.3-chat-latest", "modelKey": "gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat (latest)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.3-chat-latest", "modelKey": "openai/gpt-5.3-chat-latest", "displayName": "GPT-5.3 Chat (latest)", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-chat-latest", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.3-chat-latest", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.3-codex", "provider": "openai", "model": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "aihubmix", "azure", "azure-cognitive-services", "chatgpt", "cloudflare-ai-gateway", "fastrouter", "freemodel", "github-copilot", "github_copilot", "kilo", "llmgateway", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "vivgrid", "zenmux" ], "aliases": [ "abacus/gpt-5.3-codex", "aihubmix/gpt-5.3-codex", "azure-cognitive-services/gpt-5.3-codex", "azure/gpt-5.3-codex", "chatgpt/gpt-5.3-codex", "cloudflare-ai-gateway/openai/gpt-5.3-codex", "fastrouter/openai/gpt-5.3-codex", "freemodel/gpt-5.3-codex", "github-copilot/gpt-5.3-codex", "github_copilot/gpt-5.3-codex", "kilo/openai/gpt-5.3-codex", "llmgateway/gpt-5.3-codex", "nano-gpt/openai/gpt-5.3-codex", "openai/gpt-5.3-codex", "opencode/gpt-5.3-codex", "openrouter/openai/gpt-5.3-codex", "orcarouter/openai/gpt-5.3-codex", "poe/openai/gpt-5.3-codex", "requesty/openai/gpt-5.3-codex", "vercel/openai/gpt-5.3-codex", "vivgrid/gpt-5.3-codex", "zenmux/openai/gpt-5.3-codex" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 400000, "inputTokens": 400000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "freemodel", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "cacheWrite": 1.75, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 13 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.3-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/gpt-5.3-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.3-codex", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "extra": { "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_priority": 0.000028 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.3-codex", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.3 Codex", "GPT-5.3 Codex", "GPT-5.3-Codex", "OpenAI: GPT-5.3-Codex" ], "families": [ "gpt", "gpt-codex" ], "modes": [ "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "OpenAI: GPT-5.3-Codex", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-02-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT 5.3 Codex", "metadata": { "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3-Codex", "metadata": { "lastUpdated": "2026-02-10", "openWeights": false, "releaseDate": "2026-02-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3-Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT 5.3 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.3-codex", "modelKey": "gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "family": "gpt-codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-24", "openWeights": false, "releaseDate": "2026-02-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.3-codex", "modelKey": "openai/gpt-5.3-codex", "displayName": "GPT-5.3 Codex", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.3-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/gpt-5.3-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.3-codex", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.3-codex", "displayName": "OpenAI: GPT-5.3-Codex", "metadata": { "canonicalSlug": "openai/gpt-5.3-codex-20260224", "createdAt": "2026-02-24T18:52:44.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.3-codex-spark", "provider": "openai", "model": "gpt-5.3-codex-spark", "displayName": "GPT-5.3 Codex Spark", "family": "gpt-codex-spark", "mode": "responses", "sources": [ "litellm", "models.dev" ], "providers": [ "chatgpt", "openai", "opencode", "poe" ], "aliases": [ "chatgpt/gpt-5.3-codex-spark", "openai/gpt-5.3-codex-spark", "opencode/gpt-5.3-codex-spark", "poe/openai/gpt-5.3-codex-spark" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openai", "model": "gpt-5.3-codex-spark", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.3-codex-spark", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 1.75, "output": 14 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.3-codex-spark", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-codex-spark", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "GPT-5.3 Codex Spark", "GPT-5.3-Codex-Spark" ], "families": [ "gpt-codex-spark" ], "modes": [ "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "supportedEndpoints": [ "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.3-codex-spark", "modelKey": "gpt-5.3-codex-spark", "displayName": "GPT-5.3 Codex Spark", "family": "gpt-codex-spark", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.3-codex-spark", "modelKey": "gpt-5.3-codex-spark", "displayName": "GPT-5.3 Codex Spark", "family": "gpt-codex-spark", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.3-codex-spark", "modelKey": "openai/gpt-5.3-codex-spark", "displayName": "GPT-5.3-Codex-Spark", "metadata": { "lastUpdated": "2026-03-04", "openWeights": false, "releaseDate": "2026-03-04" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-codex-spark", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.3-codex-xhigh", "provider": "openai", "model": "gpt-5.3-codex-xhigh", "displayName": "GPT-5.3 Codex XHigh", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "abacus" ], "aliases": [ "abacus/gpt-5.3-codex-xhigh" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "gpt-5.3-codex-xhigh", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.75, "output": 14 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Codex XHigh" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.3-codex-xhigh", "modelKey": "gpt-5.3-codex-xhigh", "displayName": "GPT-5.3 Codex XHigh", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "openai/gpt-5.3-instant", "provider": "openai", "model": "gpt-5.3-instant", "displayName": "GPT-5.3-Instant", "mode": "responses", "sources": [ "litellm", "models.dev" ], "providers": [ "chatgpt", "poe" ], "aliases": [ "chatgpt/gpt-5.3-instant", "poe/openai/gpt-5.3-instant" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 64000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "responseSchema": true, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.3-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.16, "input": 1.6, "output": 13 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-instant", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "GPT-5.3-Instant" ], "modes": [ "responses" ], "releaseDate": "2026-03-03", "lastUpdated": "2026-03-03", "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.3-instant", "modelKey": "openai/gpt-5.3-instant", "displayName": "GPT-5.3-Instant", "metadata": { "lastUpdated": "2026-03-03", "openWeights": false, "releaseDate": "2026-03-03" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.3-instant", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.4", "provider": "openai", "model": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "aihubmix", "anyapi", "azure", "azure-cognitive-services", "azure_ai", "chatgpt", "cloudflare-ai-gateway", "cortecs", "freemodel", "github-copilot", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "perplexity-agent", "poe", "requesty", "sap-ai-core", "vercel", "vivgrid", "zenmux" ], "aliases": [ "302ai/gpt-5.4", "abacus/gpt-5.4", "aihubmix/gpt-5.4", "anyapi/openai/gpt-5.4", "azure-cognitive-services/gpt-5.4", "azure/gpt-5.4", "azure_ai/gpt-5.4", "chatgpt/gpt-5.4", "cloudflare-ai-gateway/openai/gpt-5.4", "cortecs/gpt-5.4", "freemodel/gpt-5.4", "github-copilot/gpt-5.4", "kilo/openai/gpt-5.4", "llmgateway/gpt-5.4", "merge-gateway/openai/gpt-5.4", "nano-gpt/openai/gpt-5.4", "nearai/openai/gpt-5.4", "openai/gpt-5.4", "opencode/gpt-5.4", "openrouter/openai/gpt-5.4", "orcarouter/openai/gpt-5.4", "perplexity-agent/openai/gpt-5.4", "poe/openai/gpt-5.4", "requesty/openai/gpt-5.4", "sap-ai-core/gpt-5.4", "vercel/openai/gpt-5.4", "vivgrid/gpt-5.4", "zenmux/openai/gpt-5.4" ], "mergedProviderModelRecords": 28, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "xhighReasoningEffort": true, "supports1MContext": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 0, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5 }, "tiers": [ { "input": 5, "output": 22.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "abacus", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "cortecs", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 3, "output": 16.13 } }, { "source": "models.dev", "provider": "freemodel", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "cacheWrite": 2.5, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 5, "output": 22.5 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 2.2, "output": 14 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "tiered": { "contextOver200K": { "input": 5, "output": 22.5, "cache_read": 0.5 }, "tiers": [ { "input": 5, "output": 22.5, "cache_read": 0.5, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.75, "output": 18.75 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.4", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.4", "GPT-5.4", "OpenAI: GPT-5.4", "gpt-5.4" ], "families": [ "gpt" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 28 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "gpt-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "OpenAI: GPT-5.4", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT 5.4", "metadata": { "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "metadata": { "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "gpt-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT 5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.4", "modelKey": "gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.4", "modelKey": "openai/gpt-5.4", "displayName": "GPT-5.4", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.4", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.4", "displayName": "OpenAI: GPT-5.4", "metadata": { "canonicalSlug": "openai/gpt-5.4-20260305", "createdAt": "2026-03-05T18:12:32.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.4-2026-03-05", "provider": "openai", "model": "gpt-5.4-2026-03-05", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "azure_ai", "openai" ], "aliases": [ "azure/gpt-5.4-2026-03-05", "azure_ai/gpt-5.4-2026-03-05", "openai/gpt-5.4-2026-03-05" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": true, "minimalReasoningEffort": true, "noneReasoningEffort": true, "webSearch": true, "xhighReasoningEffort": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 2.5, "output": 15 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-2026-03-05", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-2026-03-05", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-2026-03-05", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.4-image-2", "provider": "openai", "model": "gpt-5.4-image-2", "displayName": "OpenAI: GPT-5.4 Image 2", "family": "gpt", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/openai/gpt-5.4-image-2", "openrouter/openai/gpt-5.4-image-2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.4-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2, "input": 8, "output": 15 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.4-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2, "input": 8, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.4-image-2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2, "input": 8, "output": 15 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 Image 2", "OpenAI: GPT-5.4 Image 2" ], "families": [ "gpt" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-05-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "top_logprobs" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.4-image-2", "modelKey": "openai/gpt-5.4-image-2", "displayName": "OpenAI: GPT-5.4 Image 2", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.4-image-2", "modelKey": "openai/gpt-5.4-image-2", "displayName": "GPT-5.4 Image 2", "family": "gpt", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.4-image-2", "displayName": "OpenAI: GPT-5.4 Image 2", "metadata": { "canonicalSlug": "openai/gpt-5.4-image-2-20260421", "createdAt": "2026-04-21T18:52:08.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "top_logprobs" ], "tokenizer": "GPT", "topProvider": { "context_length": 272000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.4-mini", "provider": "openai", "model": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "aihubmix", "azure", "azure-cognitive-services", "azure_ai", "fastrouter", "freemodel", "github-copilot", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "poe", "vercel", "vivgrid", "zenmux" ], "aliases": [ "302ai/gpt-5.4-mini", "aihubmix/gpt-5.4-mini", "azure-cognitive-services/gpt-5.4-mini", "azure/gpt-5.4-mini", "azure_ai/gpt-5.4-mini", "fastrouter/openai/gpt-5.4-mini", "freemodel/gpt-5.4-mini", "github-copilot/gpt-5.4-mini", "kilo/openai/gpt-5.4-mini", "llmgateway/gpt-5.4-mini", "merge-gateway/openai/gpt-5.4-mini", "nano-gpt/openai/gpt-5.4-mini", "nearai/openai/gpt-5.4-mini", "openai/gpt-5.4-mini", "opencode/gpt-5.4-mini", "openrouter/openai/gpt-5.4-mini", "orcarouter/openai/gpt-5.4-mini", "poe/openai/gpt-5.4-mini", "vercel/openai/gpt-5.4-mini", "vivgrid/gpt-5.4-mini", "zenmux/openai/gpt-5.4-mini" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "freemodel", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "cacheWrite": 0.75, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.068, "input": 0.68, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 4.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "extra": { "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.4-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.4 Mini", "GPT-5.4 Mini", "GPT-5.4 mini", "GPT-5.4-Mini", "OpenAI: GPT-5.4 Mini", "gpt-5.4-mini" ], "families": [ "gpt", "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "gpt-5.4-mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "OpenAI: GPT-5.4 Mini", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT 5.4 Mini", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4-Mini", "metadata": { "lastUpdated": "2026-03-12", "openWeights": false, "releaseDate": "2026-03-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT 5.4 Mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.4-mini", "modelKey": "gpt-5.4-mini", "displayName": "GPT-5.4 Mini", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.4-mini", "modelKey": "openai/gpt-5.4-mini", "displayName": "GPT-5.4 Mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-mini", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.4-mini", "displayName": "OpenAI: GPT-5.4 Mini", "metadata": { "canonicalSlug": "openai/gpt-5.4-mini-20260317", "createdAt": "2026-03-17T11:49:38.000Z", "knowledgeCutoff": "2025-08-31", "links": { "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.4-mini-2026-03-17", "provider": "openai", "model": "gpt-5.4-mini-2026-03-17", "displayName": "gpt-5.4-mini-2026-03-17", "family": "gpt-mini", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "azure", "azure_ai", "openai" ], "aliases": [ "302ai/gpt-5.4-mini-2026-03-17", "azure/gpt-5.4-mini-2026-03-17", "azure_ai/gpt-5.4-mini-2026-03-17", "openai/gpt-5.4-mini-2026-03-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true, "attachments": true, "openWeights": false, "structuredOutput": true, "temperature": false, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4-mini-2026-03-17", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 4.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-mini-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-mini-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-mini-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "extra": { "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009 } } ] }, "metadata": { "displayNames": [ "gpt-5.4-mini-2026-03-17" ], "families": [ "gpt-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4-mini-2026-03-17", "modelKey": "gpt-5.4-mini-2026-03-17", "displayName": "gpt-5.4-mini-2026-03-17", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-mini-2026-03-17", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-mini-2026-03-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-mini-2026-03-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.4-nano", "provider": "openai", "model": "gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "azure", "azure-cognitive-services", "azure_ai", "fastrouter", "github-copilot", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "poe", "vercel", "vivgrid", "zenmux" ], "aliases": [ "302ai/gpt-5.4-nano", "azure-cognitive-services/gpt-5.4-nano", "azure/gpt-5.4-nano", "azure_ai/gpt-5.4-nano", "fastrouter/openai/gpt-5.4-nano", "github-copilot/gpt-5.4-nano", "kilo/openai/gpt-5.4-nano", "llmgateway/gpt-5.4-nano", "merge-gateway/openai/gpt-5.4-nano", "nano-gpt/openai/gpt-5.4-nano", "nearai/openai/gpt-5.4-nano", "openai/gpt-5.4-nano", "opencode/gpt-5.4-nano", "openrouter/openai/gpt-5.4-nano", "orcarouter/openai/gpt-5.4-nano", "poe/openai/gpt-5.4-nano", "vercel/openai/gpt-5.4-nano", "vivgrid/gpt-5.4-nano", "zenmux/openai/gpt-5.4-nano" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.018, "input": 0.18, "output": 1.1 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.25 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 }, "extra": { "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.4-nano", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.4 Nano", "GPT-5.4 Nano", "GPT-5.4 nano", "GPT-5.4-Nano", "OpenAI: GPT-5.4 Nano", "gpt-5.4-nano" ], "families": [ "gpt", "gpt-nano" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "gpt-5.4-nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "OpenAI: GPT-5.4 Nano", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT 5.4 Nano", "metadata": { "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4-Nano", "metadata": { "lastUpdated": "2026-03-11", "openWeights": false, "releaseDate": "2026-03-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT 5.4 Nano", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.4-nano", "modelKey": "gpt-5.4-nano", "displayName": "GPT-5.4 Nano", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2026-03-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.4-nano", "modelKey": "openai/gpt-5.4-nano", "displayName": "GPT-5.4 Nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-nano", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-nano", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.4-nano", "displayName": "OpenAI: GPT-5.4 Nano", "metadata": { "canonicalSlug": "openai/gpt-5.4-nano-20260317", "createdAt": "2026-03-17T11:49:47.000Z", "knowledgeCutoff": "2025-08-31", "links": { "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openai/gpt-5.4-nano-2026-03-17", "provider": "openai", "model": "gpt-5.4-nano-2026-03-17", "displayName": "gpt-5.4-nano-2026-03-17", "family": "gpt-nano", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "azure", "azure_ai", "openai" ], "aliases": [ "302ai/gpt-5.4-nano-2026-03-17", "azure/gpt-5.4-nano-2026-03-17", "azure_ai/gpt-5.4-nano-2026-03-17", "openai/gpt-5.4-nano-2026-03-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true, "attachments": true, "openWeights": false, "structuredOutput": true, "temperature": false, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4-nano-2026-03-17", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.25 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-nano-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-nano-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-nano-2026-03-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.25 }, "extra": { "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7 } } ] }, "metadata": { "displayNames": [ "gpt-5.4-nano-2026-03-17" ], "families": [ "gpt-nano" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-19", "lastUpdated": "2026-03-19", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4-nano-2026-03-17", "modelKey": "gpt-5.4-nano-2026-03-17", "displayName": "gpt-5.4-nano-2026-03-17", "family": "gpt-nano", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-19", "openWeights": false, "releaseDate": "2026-03-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-nano-2026-03-17", "mode": "chat", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-nano-2026-03-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-nano-2026-03-17", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.4-pro", "provider": "openai", "model": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "azure", "azure-cognitive-services", "azure_ai", "chatgpt", "kilo", "llmgateway", "nano-gpt", "openai", "opencode", "openrouter", "orcarouter", "poe", "requesty", "vercel", "zenmux" ], "aliases": [ "302ai/gpt-5.4-pro", "azure-cognitive-services/gpt-5.4-pro", "azure/gpt-5.4-pro", "azure_ai/gpt-5.4-pro", "chatgpt/gpt-5.4-pro", "kilo/openai/gpt-5.4-pro", "llmgateway/gpt-5.4-pro", "nano-gpt/openai/gpt-5.4-pro", "openai/gpt-5.4-pro", "opencode/gpt-5.4-pro", "openrouter/openai/gpt-5.4-pro", "orcarouter/openai/gpt-5.4-pro", "poe/openai/gpt-5.4-pro", "requesty/openai/gpt-5.4-pro", "vercel/openai/gpt-5.4-pro", "zenmux/openai/gpt-5.4-pro" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 30, "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 60, "output": 270 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 27, "output": 160 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 30, "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 45, "output": 225 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027 } }, { "source": "litellm", "provider": "chatgpt", "model": "chatgpt/gpt-5.4-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.4-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 180 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.4 Pro", "GPT-5.4 Pro", "GPT-5.4-Pro", "OpenAI: GPT-5.4 Pro", "gpt-5.4-pro" ], "families": [ "gpt", "gpt-pro" ], "modes": [ "responses" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "gpt-5.4-pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "OpenAI: GPT-5.4 Pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT 5.4 Pro", "metadata": { "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.4-pro", "modelKey": "gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT-5.4-Pro", "metadata": { "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT 5.4 Pro", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.4-pro", "modelKey": "openai/gpt-5.4-pro", "displayName": "GPT-5.4 Pro", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-pro", "mode": "responses", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "chatgpt", "model": "chatgpt/gpt-5.4-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.4-pro", "displayName": "OpenAI: GPT-5.4 Pro", "metadata": { "canonicalSlug": "openai/gpt-5.4-pro-20260305", "createdAt": "2026-03-05T18:12:46.000Z", "links": { "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high", "medium" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.4-pro-2026-03-05", "provider": "openai", "model": "gpt-5.4-pro-2026-03-05", "mode": "responses", "sources": [ "litellm" ], "providers": [ "azure", "azure_ai", "openai" ], "aliases": [ "azure/gpt-5.4-pro-2026-03-05", "azure_ai/gpt-5.4-pro-2026-03-05", "openai/gpt-5.4-pro-2026-03-05" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": true, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-pro-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.4-pro-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.4-pro-2026-03-05", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-5.4-pro-2026-03-05", "mode": "responses", "metadata": { "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.4-pro-2026-03-05", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.4-pro-2026-03-05", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } } ] }, { "id": "openai/gpt-5.5", "provider": "openai", "model": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "fastrouter", "freemodel", "github-copilot", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "opencode", "openrouter", "orcarouter", "perplexity-agent", "poe", "sap-ai-core", "vercel", "vivgrid", "zenmux" ], "aliases": [ "aihubmix/gpt-5.5", "azure-cognitive-services/gpt-5.5", "azure/gpt-5.5", "cloudflare-ai-gateway/openai/gpt-5.5", "fastrouter/openai/gpt-5.5", "freemodel/gpt-5.5", "github-copilot/gpt-5.5", "kilo/openai/gpt-5.5", "llmgateway/gpt-5.5", "merge-gateway/openai/gpt-5.5", "nano-gpt/openai/gpt-5.5", "nearai/openai/gpt-5.5", "openai/gpt-5.5", "opencode/gpt-5.5", "openrouter/openai/gpt-5.5", "orcarouter/openai/gpt-5.5", "perplexity-agent/openai/gpt-5.5", "poe/openai/gpt-5.5", "sap-ai-core/gpt-5.5", "vercel/openai/gpt-5.5", "vivgrid/gpt-5.5", "zenmux/openai/gpt-5.5" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "azure", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "freemodel", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "github-copilot", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4545, "input": 4.5455, "output": 27.2727 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "vivgrid", "model": "gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "tiered": { "contextOver200K": { "input": 10, "output": 45, "cache_read": 1 }, "tiers": [ { "input": 10, "output": 45, "cache_read": 1, "tier": { "size": 272000 } } ] } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.5", "GPT-5.5", "OpenAI: GPT-5.5", "gpt-5.5" ], "families": [ "gpt" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "freemodel", "providerName": "FreeModel", "providerApi": "https://cc.freemodel.dev/v1", "providerDoc": "https://freemodel.dev", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-copilot", "providerName": "GitHub Copilot", "providerApi": "https://api.githubcopilot.com", "providerDoc": "https://docs.github.com/en/copilot", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "OpenAI: GPT-5.5", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT 5.5", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-08", "openWeights": false, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "gpt-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT 5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vivgrid", "providerName": "Vivgrid", "providerApi": "https://api.vivgrid.com/v1", "providerDoc": "https://docs.vivgrid.com/models", "model": "gpt-5.5", "modelKey": "gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.5", "modelKey": "openai/gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.5", "displayName": "OpenAI: GPT-5.5", "metadata": { "canonicalSlug": "openai/gpt-5.5-20260423", "createdAt": "2026-04-24T17:31:33.000Z", "knowledgeCutoff": "2025-12-01", "links": { "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.5-2026-04-23", "provider": "openai", "model": "gpt-5.5-2026-04-23", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-5.5-2026-04-23", "openai/gpt-5.5-2026-04-23" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.5-2026-04-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.5-2026-04-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.5-2026-04-23", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.5-2026-04-23", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/gpt-5.5-instant", "provider": "openai", "model": "gpt-5.5-instant", "displayName": "GPT-5.5 Instant", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/openai/gpt-5.5-instant" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.5-instant", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } } ] }, "metadata": { "displayNames": [ "GPT-5.5 Instant" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-05-05", "lastUpdated": "2026-05-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.5-instant", "modelKey": "openai/gpt-5.5-instant", "displayName": "GPT-5.5 Instant", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-05-28", "openWeights": false, "releaseDate": "2026-05-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-5.5-pro", "provider": "openai", "model": "gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "fastrouter", "kilo", "llmgateway", "openai", "opencode", "openrouter", "orcarouter", "poe", "vercel", "zenmux" ], "aliases": [ "azure/gpt-5.5-pro", "fastrouter/openai/gpt-5.5-pro", "kilo/openai/gpt-5.5-pro", "llmgateway/gpt-5.5-pro", "openai/gpt-5.5-pro", "opencode/gpt-5.5-pro", "openrouter/openai/gpt-5.5-pro", "orcarouter/openai/gpt-5.5-pro", "poe/openai/gpt-5.5-pro", "vercel/openai/gpt-5.5-pro", "zenmux/openai/gpt-5.5-pro" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "lowReasoningEffort": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "openai", "model": "gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "opencode", "model": "gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 30, "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "orcarouter", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 27.2727, "output": 163.6364 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 } }, { "source": "models.dev", "provider": "zenmux", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 30, "output": 180 }, "tiered": { "contextOver200K": { "input": 60, "output": 270 }, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000 } } ] } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-5.5-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 30, "output": 180 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT 5.5 Pro", "GPT-5.5 Pro", "GPT-5.5-Pro", "OpenAI: GPT-5.5 Pro" ], "families": [ "gpt", "gpt-pro" ], "modes": [ "responses" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "OpenAI: GPT-5.5 Pro", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-5.5-pro", "modelKey": "gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-5.5-pro", "modelKey": "gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "gpt-5.5-pro", "modelKey": "gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-24", "openWeights": false, "releaseDate": "2026-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT-5.5-Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-08", "openWeights": false, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT 5.5 Pro", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "openai/gpt-5.5-pro", "modelKey": "openai/gpt-5.5-pro", "displayName": "GPT-5.5 Pro", "family": "gpt-pro", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "medium", "high", "xhigh" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.5-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.5-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-5.5-pro", "displayName": "OpenAI: GPT-5.5 Pro", "metadata": { "canonicalSlug": "openai/gpt-5.5-pro-20260423", "createdAt": "2026-04-24T17:31:36.000Z", "knowledgeCutoff": "2025-12-01", "links": { "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high", "medium" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-5.5-pro-2026-04-23", "provider": "openai", "model": "gpt-5.5-pro-2026-04-23", "mode": "responses", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-5.5-pro-2026-04-23", "openai/gpt-5.5-pro-2026-04-23" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1050000, "inputTokens": 1050000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "lowReasoningEffort": false, "minimalReasoningEffort": false, "moderation": false, "nativeStreaming": true, "noneReasoningEffort": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "serviceTier": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "xhighReasoningEffort": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-5.5-pro-2026-04-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027 } }, { "source": "litellm", "provider": "openai", "model": "gpt-5.5-pro-2026-04-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 3, "input": 30, "output": 180 }, "extra": { "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-5.5-pro-2026-04-23", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-5.5-pro-2026-04-23", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } } ] }, { "id": "openai/gpt-audio", "provider": "openai", "model": "gpt-audio", "displayName": "OpenAI: GPT Audio", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openai", "openrouter" ], "aliases": [ "kilo/openai/gpt-audio", "openai/gpt-audio", "openrouter/openai/gpt-audio" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false, "attachments": true, "openWeights": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-audio", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-audio", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "litellm", "provider": "openai", "model": "gpt-audio", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 32, "output": 10, "outputAudio": 64 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-audio", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 }, "other": { "audio": 0.000032 } } ] }, "metadata": { "displayNames": [ "GPT Audio", "OpenAI: GPT Audio" ], "families": [ "gpt" ], "modes": [ "chat" ], "releaseDate": "2026-01-20", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/realtime", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-audio", "modelKey": "openai/gpt-audio", "displayName": "OpenAI: GPT Audio", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-audio", "modelKey": "openai/gpt-audio", "displayName": "GPT Audio", "family": "gpt", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-audio", "displayName": "OpenAI: GPT Audio", "metadata": { "canonicalSlug": "openai/gpt-audio", "createdAt": "2026-01-19T22:42:49.000Z", "links": { "details": "/api/v1/models/openai/gpt-audio/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-audio-1.5", "provider": "openai", "model": "gpt-audio-1.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-audio-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-audio-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 32, "output": 10, "outputAudio": 64 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio-1.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "openai/gpt-audio-1.5-2026-02-23", "provider": "openai", "model": "gpt-audio-1.5-2026-02-23", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-audio-1.5-2026-02-23" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-audio-1.5-2026-02-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/chat/completions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-audio-1.5-2026-02-23", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } } ] }, { "id": "openai/gpt-audio-2025-08-28", "provider": "openai", "model": "gpt-audio-2025-08-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-audio-2025-08-28", "openai/gpt-audio-2025-08-28" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-audio-2025-08-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 40, "output": 10, "outputAudio": 80 } }, { "source": "litellm", "provider": "openai", "model": "gpt-audio-2025-08-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "inputAudio": 32, "output": 10, "outputAudio": 64 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/realtime", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-audio-2025-08-28", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio-2025-08-28", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ] } } ] }, { "id": "openai/gpt-audio-mini", "provider": "openai", "model": "gpt-audio-mini", "displayName": "OpenAI: GPT Audio Mini", "family": "o-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openai", "openrouter" ], "aliases": [ "kilo/openai/gpt-audio-mini", "openai/gpt-audio-mini", "openrouter/openai/gpt-audio-mini" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false, "attachments": true, "openWeights": false, "temperature": true, "toolCalling": true, "structuredOutput": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-audio-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-audio-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.4 } }, { "source": "litellm", "provider": "openai", "model": "gpt-audio-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-audio-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.4 }, "other": { "audio": 6e-7 } } ] }, "metadata": { "displayNames": [ "GPT Audio Mini", "OpenAI: GPT Audio Mini" ], "families": [ "o-mini" ], "modes": [ "chat" ], "releaseDate": "2026-01-20", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/realtime", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-audio-mini", "modelKey": "openai/gpt-audio-mini", "displayName": "OpenAI: GPT Audio Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-audio-mini", "modelKey": "openai/gpt-audio-mini", "displayName": "GPT Audio Mini", "family": "o-mini", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-audio-mini", "displayName": "OpenAI: GPT Audio Mini", "metadata": { "canonicalSlug": "openai/gpt-audio-mini", "createdAt": "2026-01-19T21:50:19.000Z", "links": { "details": "/api/v1/models/openai/gpt-audio-mini/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 128000, "max_completion_tokens": 16384, "is_moderated": true } } } ] }, { "id": "openai/gpt-audio-mini-2025-10-06", "provider": "openai", "model": "gpt-audio-mini-2025-10-06", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-audio-mini-2025-10-06", "openai/gpt-audio-mini-2025-10-06" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-audio-mini-2025-10-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 } }, { "source": "litellm", "provider": "openai", "model": "gpt-audio-mini-2025-10-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/realtime", "/v1/responses" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-audio-mini-2025-10-06", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio-mini-2025-10-06", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ] } } ] }, { "id": "openai/gpt-audio-mini-2025-12-15", "provider": "openai", "model": "gpt-audio-mini-2025-12-15", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-audio-mini-2025-12-15" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": false, "reasoning": false, "rerank": false, "responseSchema": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-audio-mini-2025-12-15", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/realtime", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-audio-mini-2025-12-15", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ] } } ] }, { "id": "openai/gpt-chat-latest", "provider": "openai", "model": "gpt-chat-latest", "displayName": "OpenAI: GPT Chat Latest", "family": "gpt", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/openai/gpt-chat-latest", "nano-gpt/openai/gpt-chat-latest", "openrouter/openai/gpt-chat-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 400000, "inputTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-chat-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-chat-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT Chat Latest", "OpenAI: GPT Chat Latest" ], "families": [ "gpt" ], "releaseDate": "2026-05-05", "lastUpdated": "2026-05-07", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "tool_choice", "tools", "top_logprobs" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-chat-latest", "modelKey": "openai/gpt-chat-latest", "displayName": "OpenAI: GPT Chat Latest", "metadata": { "lastUpdated": "2026-05-07", "openWeights": false, "releaseDate": "2026-05-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-chat-latest", "modelKey": "openai/gpt-chat-latest", "displayName": "GPT Chat Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-chat-latest", "modelKey": "openai/gpt-chat-latest", "displayName": "GPT Chat Latest", "family": "gpt", "metadata": { "lastUpdated": "2026-05-05", "openWeights": false, "releaseDate": "2026-05-05" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-chat-latest", "displayName": "OpenAI: GPT Chat Latest", "metadata": { "canonicalSlug": "openai/gpt-chat-latest-20260505", "createdAt": "2026-05-05T16:56:52.000Z", "links": { "details": "/api/v1/models/openai/gpt-chat-latest-20260505/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "tool_choice", "tools", "top_logprobs" ], "tokenizer": "GPT", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-image-1", "provider": "openai", "model": "gpt-image-1", "displayName": "gpt-image-1", "family": "gpt-image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "openai", "poe", "vercel" ], "aliases": [ "azure/gpt-image-1", "azure/high/1024-x-1024/gpt-image-1", "azure/high/1024-x-1536/gpt-image-1", "azure/high/1536-x-1024/gpt-image-1", "azure/low/1024-x-1024/gpt-image-1", "azure/low/1024-x-1536/gpt-image-1", "azure/low/1536-x-1024/gpt-image-1", "azure/medium/1024-x-1024/gpt-image-1", "azure/medium/1024-x-1536/gpt-image-1", "azure/medium/1536-x-1024/gpt-image-1", "openai/gpt-image-1", "openai/high/1024-x-1024/gpt-image-1", "openai/high/1024-x-1536/gpt-image-1", "openai/high/1536-x-1024/gpt-image-1", "openai/low/1024-x-1024/gpt-image-1", "openai/low/1024-x-1536/gpt-image-1", "openai/low/1536-x-1024/gpt-image-1", "openai/medium/1024-x-1024/gpt-image-1", "openai/medium/1024-x-1536/gpt-image-1", "openai/medium/1536-x-1024/gpt-image-1", "poe/openai/gpt-image-1", "vercel/openai/gpt-image-1" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 128000, "inputTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "gpt-image-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 40 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-image-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 40 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 10, "outputImage": 40 }, "extra": { "cache_read_input_image_token_cost": 0.0000025 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.59263611e-7, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.58945719e-7, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.58945719e-7, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.0490417e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.0172526e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 1.0172526e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 4.0054321e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 4.0054321e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 4.0054321e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 10, "outputImage": 40 }, "extra": { "cache_read_input_image_token_cost": 0.0000025 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.167 }, "perPixel": { "input": 1.59263611e-7, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.25 }, "perPixel": { "input": 1.58945719e-7, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.25 }, "perPixel": { "input": 1.58945719e-7, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.011 }, "perPixel": { "input": 1.0490417e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.016 }, "perPixel": { "input": 1.0172526e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.016 }, "perPixel": { "input": 1.0172526e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.042 }, "perPixel": { "input": 4.0054321e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.063 }, "perPixel": { "input": 4.0054321e-8, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.063 }, "perPixel": { "input": 4.0054321e-8, "output": 0 } } ] }, "metadata": { "displayNames": [ "GPT Image 1", "GPT-Image-1", "gpt-image-1" ], "families": [ "gpt", "gpt-image" ], "modes": [ "image_generation" ], "releaseDate": "2025-04-24", "lastUpdated": "2025-04-24", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-image-1", "modelKey": "gpt-image-1", "displayName": "GPT-Image-1", "family": "gpt-image", "metadata": { "lastUpdated": "2025-04-24", "openWeights": false, "releaseDate": "2025-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-image-1", "modelKey": "gpt-image-1", "displayName": "gpt-image-1", "family": "gpt-image", "metadata": { "lastUpdated": "2025-04-24", "openWeights": false, "releaseDate": "2025-04-24" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-image-1", "modelKey": "openai/gpt-image-1", "displayName": "GPT-Image-1", "family": "gpt", "metadata": { "lastUpdated": "2025-03-31", "openWeights": false, "releaseDate": "2025-03-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-image-1", "modelKey": "openai/gpt-image-1", "displayName": "GPT Image 1", "family": "gpt-image", "metadata": { "lastUpdated": "2025-04-24", "openWeights": false, "releaseDate": "2025-03-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "openai/gpt-image-1-mini", "provider": "openai", "model": "gpt-image-1-mini", "displayName": "gpt-image-1-mini", "family": "gpt-image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "openai", "poe", "vercel" ], "aliases": [ "azure/gpt-image-1-mini", "azure/high/1024-x-1024/gpt-image-1-mini", "azure/high/1024-x-1536/gpt-image-1-mini", "azure/high/1536-x-1024/gpt-image-1-mini", "azure/low/1024-x-1024/gpt-image-1-mini", "azure/low/1024-x-1536/gpt-image-1-mini", "azure/low/1536-x-1024/gpt-image-1-mini", "azure/medium/1024-x-1024/gpt-image-1-mini", "azure/medium/1024-x-1536/gpt-image-1-mini", "azure/medium/1536-x-1024/gpt-image-1-mini", "openai/gpt-image-1-mini", "openai/low/1024-x-1024/gpt-image-1-mini", "openai/low/1024-x-1536/gpt-image-1-mini", "openai/low/1536-x-1024/gpt-image-1-mini", "openai/medium/1024-x-1024/gpt-image-1-mini", "openai/medium/1024-x-1536/gpt-image-1-mini", "openai/medium/1536-x-1024/gpt-image-1-mini", "poe/openai/gpt-image-1-mini", "vercel/openai/gpt-image-1-mini" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 0, "inputTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-image-1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "inputImage": 2.5, "outputImage": 8 }, "extra": { "cache_read_input_image_token_cost": 2.5e-7 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1024-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 3.173828125e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1024-x-1536/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 3.173828125e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/high/1536-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 3.1575520833e-8, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1024-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 2.0751953125e-9, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1024-x-1536/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 2.0751953125e-9, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/low/1536-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 2.0345052083e-9, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1024-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 8.056640625e-9, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1024-x-1536/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 8.056640625e-9, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/medium/1536-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perPixel": { "input": 7.9752604167e-9, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "inputImage": 2.5, "outputImage": 8 }, "extra": { "cache_read_input_image_token_cost": 2.5e-7 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.005 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.006 } }, { "source": "litellm", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.006 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.011 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.015 } }, { "source": "litellm", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.015 } } ] }, "metadata": { "displayNames": [ "GPT Image 1 Mini", "GPT-Image-1-Mini", "gpt-image-1-mini" ], "families": [ "gpt", "gpt-image" ], "modes": [ "image_generation" ], "releaseDate": "2025-09-26", "lastUpdated": "2025-09-26", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-image-1-mini", "modelKey": "gpt-image-1-mini", "displayName": "gpt-image-1-mini", "family": "gpt-image", "metadata": { "lastUpdated": "2025-09-26", "openWeights": false, "releaseDate": "2025-09-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-image-1-mini", "modelKey": "openai/gpt-image-1-mini", "displayName": "GPT-Image-1-Mini", "family": "gpt", "metadata": { "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-image-1-mini", "modelKey": "openai/gpt-image-1-mini", "displayName": "GPT Image 1 Mini", "family": "gpt-image", "metadata": { "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1024-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1024-x-1536/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/high/1536-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1024-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1024-x-1536/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/low/1536-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1024-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1024-x-1536/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/medium/1536-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1-mini", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "openai/gpt-image-1.5", "provider": "openai", "model": "gpt-image-1.5", "displayName": "gpt-image-1.5", "family": "gpt-image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "openai", "poe", "vercel" ], "aliases": [ "azure/gpt-image-1.5", "openai/1024-x-1024/gpt-image-1.5", "openai/1024-x-1536/gpt-image-1.5", "openai/1536-x-1024/gpt-image-1.5", "openai/gpt-image-1.5", "openai/high/1024-x-1024/gpt-image-1.5", "openai/high/1024-x-1536/gpt-image-1.5", "openai/high/1536-x-1024/gpt-image-1.5", "openai/low/1024-x-1024/gpt-image-1.5", "openai/low/1024-x-1536/gpt-image-1.5", "openai/low/1536-x-1024/gpt-image-1.5", "openai/medium/1024-x-1024/gpt-image-1.5", "openai/medium/1024-x-1536/gpt-image-1.5", "openai/medium/1536-x-1024/gpt-image-1.5", "openai/standard/1024-x-1024/gpt-image-1.5", "openai/standard/1024-x-1536/gpt-image-1.5", "openai/standard/1536-x-1024/gpt-image-1.5", "poe/openai/gpt-image-1.5", "vercel/openai/gpt-image-1.5" ], "mergedProviderModelRecords": 19, "limits": { "contextTokens": 128000, "inputTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "gpt-image-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 32 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-image-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 32 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "outputImage": 32 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "1024-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "1024-x-1536/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "1536-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 32 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.133 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.2 } }, { "source": "litellm", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.2 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.034 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.05 } }, { "source": "litellm", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.05 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1536/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "standard/1536-x-1024/gpt-image-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } } ] }, "metadata": { "displayNames": [ "GPT Image 1.5", "GPT-Image-1.5", "gpt-image-1.5" ], "families": [ "gpt-image" ], "modes": [ "image_generation" ], "releaseDate": "2025-11-25", "lastUpdated": "2025-11-25", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 19 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-image-1.5", "modelKey": "gpt-image-1.5", "displayName": "GPT-Image-1.5", "family": "gpt-image", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-image-1.5", "modelKey": "gpt-image-1.5", "displayName": "gpt-image-1.5", "family": "gpt-image", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-image-1.5", "modelKey": "openai/gpt-image-1.5", "displayName": "gpt-image-1.5", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-image-1.5", "modelKey": "openai/gpt-image-1.5", "displayName": "GPT Image 1.5", "family": "gpt-image", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-12-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1024-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1024-x-1536/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1536-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1536/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1536-x-1024/gpt-image-1.5", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } } ] }, { "id": "openai/gpt-image-1.5-2025-12-16", "provider": "openai", "model": "gpt-image-1.5-2025-12-16", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-image-1.5-2025-12-16", "openai/1024-x-1024/gpt-image-1.5-2025-12-16", "openai/1024-x-1536/gpt-image-1.5-2025-12-16", "openai/1536-x-1024/gpt-image-1.5-2025-12-16", "openai/gpt-image-1.5-2025-12-16", "openai/high/1024-x-1024/gpt-image-1.5-2025-12-16", "openai/high/1024-x-1536/gpt-image-1.5-2025-12-16", "openai/high/1536-x-1024/gpt-image-1.5-2025-12-16", "openai/low/1024-x-1024/gpt-image-1.5-2025-12-16", "openai/low/1024-x-1536/gpt-image-1.5-2025-12-16", "openai/low/1536-x-1024/gpt-image-1.5-2025-12-16", "openai/medium/1024-x-1024/gpt-image-1.5-2025-12-16", "openai/medium/1024-x-1536/gpt-image-1.5-2025-12-16", "openai/medium/1536-x-1024/gpt-image-1.5-2025-12-16", "openai/standard/1024-x-1024/gpt-image-1.5-2025-12-16", "openai/standard/1024-x-1536/gpt-image-1.5-2025-12-16", "openai/standard/1536-x-1024/gpt-image-1.5-2025-12-16" ], "mergedProviderModelRecords": 17, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "outputImage": 32 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "1024-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "1024-x-1536/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "1536-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 32 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.133 } }, { "source": "litellm", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.2 } }, { "source": "litellm", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.2 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.034 } }, { "source": "litellm", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.05 } }, { "source": "litellm", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.05 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.009 } }, { "source": "litellm", "provider": "openai", "model": "standard/1024-x-1536/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } }, { "source": "litellm", "provider": "openai", "model": "standard/1536-x-1024/gpt-image-1.5-2025-12-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.013 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 17 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1024-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1024-x-1536/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "1536-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1024-x-1536/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "high/1536-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1024-x-1536/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "low/1536-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1024-x-1536/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "medium/1536-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1024-x-1536/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "standard/1536-x-1024/gpt-image-1.5-2025-12-16", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } } ] }, { "id": "openai/gpt-image-2", "provider": "openai", "model": "gpt-image-2", "displayName": "gpt-image-2", "family": "gpt-image", "mode": "image_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "fastrouter", "openai", "poe", "vercel" ], "aliases": [ "azure/gpt-image-2", "fastrouter/openai/gpt-image-2", "openai/gpt-image-2", "poe/openai/gpt-image-2", "vercel/openai/gpt-image-2" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": true, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "gpt-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "openai", "model": "gpt-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "poe", "model": "openai/gpt-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.2626, "input": 5.0505, "output": 32.3232 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-image-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 30 } }, { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 30 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 30 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } } ] }, "metadata": { "displayNames": [ "GPT Image 2", "GPT-Image-2", "gpt-image-2" ], "families": [ "gpt-image" ], "modes": [ "image_generation" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "gpt-image-2", "modelKey": "gpt-image-2", "displayName": "GPT-Image-2", "family": "gpt-image", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-image-2", "modelKey": "openai/gpt-image-2", "displayName": "GPT Image 2", "family": "gpt-image", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "gpt-image-2", "modelKey": "gpt-image-2", "displayName": "gpt-image-2", "family": "gpt-image", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/gpt-image-2", "modelKey": "openai/gpt-image-2", "displayName": "GPT-Image-2", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-image-2", "modelKey": "openai/gpt-image-2", "displayName": "GPT Image 2", "family": "gpt-image", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-2", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-2", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } } ] }, { "id": "openai/gpt-image-2-2026-04-21", "provider": "openai", "model": "gpt-image-2-2026-04-21", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-image-2-2026-04-21", "openai/gpt-image-2-2026-04-21" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-image-2-2026-04-21", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 30 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } }, { "source": "litellm", "provider": "openai", "model": "gpt-image-2-2026-04-21", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "inputImage": 8, "output": 10, "outputImage": 30 }, "extra": { "cache_read_input_image_token_cost": 0.000002 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/edits", "/v1/images/generations" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-image-2-2026-04-21", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-image-2-2026-04-21", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations", "/v1/images/edits" ] } } ] }, { "id": "openai/gpt-latest", "provider": "openai", "model": "gpt-latest", "displayName": "OpenAI: GPT Latest", "family": "gpt", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/~openai/gpt-latest", "nano-gpt/openai/gpt-latest", "openrouter/~openai/gpt-latest" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1050000, "inputTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~openai/gpt-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "models.dev", "provider": "openrouter", "model": "~openai/gpt-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 } }, { "source": "openrouter", "provider": "openrouter", "model": "~openai/gpt-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 5, "output": 30 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "GPT Latest", "OpenAI GPT Latest", "OpenAI: GPT Latest" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~openai/gpt-latest", "modelKey": "~openai/gpt-latest", "displayName": "OpenAI: GPT Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-latest", "modelKey": "openai/gpt-latest", "displayName": "GPT Latest", "metadata": { "lastUpdated": "2026-03-29", "openWeights": false, "releaseDate": "2026-03-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~openai/gpt-latest", "modelKey": "~openai/gpt-latest", "displayName": "OpenAI GPT Latest", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~openai/gpt-latest", "displayName": "OpenAI GPT Latest", "metadata": { "canonicalSlug": "~openai/gpt-latest", "createdAt": "2026-04-27T19:32:14.000Z", "knowledgeCutoff": "2025-12-01", "links": { "details": "/api/v1/models/~openai/gpt-latest/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "Router", "topProvider": { "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-mini-latest", "provider": "openai", "model": "gpt-mini-latest", "displayName": "OpenAI: GPT Mini Latest", "family": "gpt-mini", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/~openai/gpt-mini-latest", "openrouter/~openai/gpt-mini-latest" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 400000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "~openai/gpt-mini-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "~openai/gpt-mini-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "~openai/gpt-mini-latest", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.75, "output": 4.5 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI GPT Mini Latest", "OpenAI: GPT Mini Latest" ], "families": [ "gpt-mini" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-04-27", "lastUpdated": "2026-05-01", "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "~openai/gpt-mini-latest", "modelKey": "~openai/gpt-mini-latest", "displayName": "OpenAI: GPT Mini Latest", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "~openai/gpt-mini-latest", "modelKey": "~openai/gpt-mini-latest", "displayName": "OpenAI GPT Mini Latest", "family": "gpt-mini", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-04-27", "openWeights": false, "releaseDate": "2026-04-27", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "~openai/gpt-mini-latest", "displayName": "OpenAI GPT Mini Latest", "metadata": { "canonicalSlug": "~openai/gpt-mini-latest", "createdAt": "2026-04-27T19:34:31.000Z", "knowledgeCutoff": "2025-08-31", "links": { "details": "/api/v1/models/~openai/gpt-mini-latest/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false, "supported_efforts": [ "xhigh", "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "Router", "topProvider": { "context_length": 400000, "max_completion_tokens": 128000, "is_moderated": true } } } ] }, { "id": "openai/gpt-oss-120b", "provider": "openai", "model": "gpt-oss-120b", "displayName": "OpenAI GPT 120B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure_ai", "baseten", "berget", "cerebras", "cloudferro-sherlock", "cloudflare-ai-gateway", "cloudflare-workers-ai", "cortecs", "crusoe", "deepinfra", "dinference", "evroc", "fastrouter", "fireworks-ai", "fireworks_ai", "frogbot", "groq", "helicone", "io-net", "kilo", "llmgateway", "nano-gpt", "nearai", "nebius", "neon", "novita", "novita-ai", "nvidia", "openrouter", "ovhcloud", "privatemode-ai", "qiniu-ai", "regolo-ai", "replicate", "sambanova", "scaleway", "siliconflow", "stackit", "submodel", "synthetic", "together_ai", "togetherai", "vercel", "wandb", "watsonx" ], "aliases": [ "abacus/openai/gpt-oss-120b", "azure_ai/gpt-oss-120b", "baseten/openai/gpt-oss-120b", "berget/openai/gpt-oss-120b", "cerebras/gpt-oss-120b", "cloudferro-sherlock/openai/gpt-oss-120b", "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b", "cloudflare-workers-ai/@cf/openai/gpt-oss-120b", "cortecs/gpt-oss-120b", "crusoe/openai/gpt-oss-120b", "deepinfra/openai/gpt-oss-120b", "dinference/gpt-oss-120b", "evroc/openai/gpt-oss-120b", "fastrouter/openai/gpt-oss-120b", "fireworks-ai/accounts/fireworks/models/gpt-oss-120b", "fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "frogbot/gpt-oss-120b", "groq/openai/gpt-oss-120b", "helicone/gpt-oss-120b", "io-net/openai/gpt-oss-120b", "kilo/openai/gpt-oss-120b", "llmgateway/gpt-oss-120b", "nano-gpt/TEE/gpt-oss-120b", "nano-gpt/openai/gpt-oss-120b", "nearai/openai/gpt-oss-120b", "nebius/openai/gpt-oss-120b", "neon/gpt-oss-120b", "novita-ai/openai/gpt-oss-120b", "novita/openai/gpt-oss-120b", "nvidia/openai/gpt-oss-120b", "openrouter/openai/gpt-oss-120b", "ovhcloud/gpt-oss-120b", "privatemode-ai/gpt-oss-120b", "qiniu-ai/gpt-oss-120b", "regolo-ai/gpt-oss-120b", "replicate/openai/gpt-oss-120b", "sambanova/gpt-oss-120b", "scaleway/gpt-oss-120b", "siliconflow/openai/gpt-oss-120b", "stackit/openai/gpt-oss-120b", "submodel/openai/gpt-oss-120b", "synthetic/hf:openai/gpt-oss-120b", "together_ai/openai/gpt-oss-120b", "togetherai/openai/gpt-oss-120b", "vercel/openai/gpt-oss-120b", "wandb/openai/gpt-oss-120b", "watsonx/openai/gpt-oss-120b" ], "mergedProviderModelRecords": 47, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "functionCalling": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.44 } }, { "source": "models.dev", "provider": "baseten", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.5 } }, { "source": "models.dev", "provider": "berget", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.44, "output": 0.99 } }, { "source": "models.dev", "provider": "cerebras", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.75 } }, { "source": "models.dev", "provider": "cloudferro-sherlock", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.92, "output": 2.92 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.75 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.75 } }, { "source": "models.dev", "provider": "cortecs", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "deepinfra", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.039, "output": 0.19 } }, { "source": "models.dev", "provider": "dinference", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0675, "output": 0.27 } }, { "source": "models.dev", "provider": "evroc", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.24, "output": 0.94 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "frogbot", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "groq", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.16 } }, { "source": "models.dev", "provider": "io-net", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.08, "input": 0.04, "output": 0.4 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.039, "output": 0.19 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 2 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.55 } }, { "source": "models.dev", "provider": "nebius", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "cacheWrite": 0.18, "input": 0.15, "output": 0.6, "reasoningOutput": 0.6 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.072, "output": 0.28 } }, { "source": "models.dev", "provider": "novita-ai", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "models.dev", "provider": "nvidia", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.039, "output": 0.18 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.47 } }, { "source": "models.dev", "provider": "privatemode-ai", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 4.2 } }, { "source": "models.dev", "provider": "scaleway", "model": "gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "siliconflow", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.45 } }, { "source": "models.dev", "provider": "stackit", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.49, "output": 0.71 } }, { "source": "models.dev", "provider": "submodel", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.5 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "models.dev", "provider": "togetherai", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 0.35, "output": 0.75 } }, { "source": "models.dev", "provider": "wandb", "model": "openai/gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.5 } }, { "source": "litellm", "provider": "cerebras", "model": "cerebras/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 0.75 } }, { "source": "litellm", "provider": "crusoe", "model": "crusoe/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.45 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "groq", "model": "groq/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "novita", "model": "novita/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.25 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.8 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.08, "output": 0.4 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0.72 } }, { "source": "litellm", "provider": "sambanova", "model": "sambanova/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 4.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15000, "output": 60000 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/openai/gpt-oss-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-oss-120b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.039, "output": 0.18 } } ] }, "metadata": { "displayNames": [ "GPT OSS 120B", "GPT Oss 120b", "GPT-OSS 120B", "GPT-OSS 120B TEE", "GPT-OSS-120B", "OpenAI GPT 120B", "OpenAI GPT OSS 120B", "OpenAI GPT-OSS 120b", "OpenAI: gpt-oss-120b", "gpt-oss-120b", "openai/gpt-oss-120b" ], "families": [ "gpt", "gpt-oss" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-08", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 47 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "OpenAI GPT 120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS-120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cerebras", "providerName": "Cerebras", "providerDoc": "https://inference-docs.cerebras.ai/models/overview", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-06-10", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudferro-sherlock", "providerName": "CloudFerro Sherlock", "providerApi": "https://api-sherlock.cloudferro.com/openai/v1/", "providerDoc": "https://docs.sherlock.cloudferro.com/", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "OpenAI GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/openai/gpt-oss-120b", "modelKey": "workers-ai/@cf/openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/openai/gpt-oss-120b", "modelKey": "@cf/openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT Oss 120b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-01", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "dinference", "providerName": "DInference", "providerApi": "https://api.dinference.com/v1", "providerDoc": "https://dinference.com", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT OSS 120B", "metadata": { "lastUpdated": "2025-08", "openWeights": true, "releaseDate": "2025-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/gpt-oss-120b", "modelKey": "accounts/fireworks/models/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "1970-01-01", "openWeights": true, "releaseDate": "1970-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-10-21", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "OpenAI GPT-OSS 120b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS 120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "OpenAI: gpt-oss-120b", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gpt-oss-120b", "modelKey": "TEE/gpt-oss-120b", "displayName": "GPT-OSS 120B TEE", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "gpt-oss-120b", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2026-01-10", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "OpenAI GPT OSS 120B", "metadata": { "lastUpdated": "2025-08-06", "openWeights": true, "releaseDate": "2025-08-06", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS-120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-14", "openWeights": true, "releaseDate": "2025-08-04", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "gpt-oss-120b", "metadata": { "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "privatemode-ai", "providerName": "Privatemode AI", "providerApi": "http://localhost:8080/v1", "providerDoc": "https://docs.privatemode.ai/api/overview", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-14", "openWeights": true, "releaseDate": "2025-08-04", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "gpt-oss-120b", "metadata": { "lastUpdated": "2025-08-06", "openWeights": false, "releaseDate": "2025-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT-OSS-120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "gpt-oss-120b", "modelKey": "gpt-oss-120b", "displayName": "GPT-OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2024-01-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "openai/gpt-oss-120b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-13", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT-OSS 120B", "family": "gpt", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-23", "openWeights": true, "releaseDate": "2025-08-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:openai/gpt-oss-120b", "modelKey": "hf:openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "openai/gpt-oss-120b", "modelKey": "openai/gpt-oss-120b", "displayName": "gpt-oss-120b", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-03-12", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "cerebras", "model": "cerebras/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "crusoe", "model": "crusoe/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/openai/gpt-oss-120b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sambanova", "model": "sambanova/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/openai/gpt-oss-120b", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/gpt-oss-120b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/openai/gpt-oss-120b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/openai/gpt-oss-120b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-oss-120b", "displayName": "OpenAI: gpt-oss-120b", "metadata": { "canonicalSlug": "openai/gpt-oss-120b", "createdAt": "2025-08-05T17:17:11.000Z", "huggingFaceId": "openai/gpt-oss-120b", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-oss-120b/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openai/gpt-oss-120b-cs", "provider": "openai", "model": "gpt-oss-120b-cs", "displayName": "GPT-OSS-120B-CS", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/cerebras/gpt-oss-120b-cs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poe", "model": "cerebras/gpt-oss-120b-cs", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "GPT-OSS-120B-CS" ], "releaseDate": "2025-08-06", "lastUpdated": "2025-08-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "cerebras/gpt-oss-120b-cs", "modelKey": "cerebras/gpt-oss-120b-cs", "displayName": "GPT-OSS-120B-CS", "metadata": { "lastUpdated": "2025-08-06", "openWeights": false, "releaseDate": "2025-08-06", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss-120b-fast", "provider": "openai", "model": "gpt-oss-120b-fast", "displayName": "gpt-oss-120b-fast", "sources": [ "models.dev" ], "providers": [ "nebius" ], "aliases": [ "nebius/openai/gpt-oss-120b-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 7000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nebius", "model": "openai/gpt-oss-120b-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.125, "input": 0.1, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "gpt-oss-120b-fast" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-06-10", "lastUpdated": "2026-05-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "openai/gpt-oss-120b-fast", "modelKey": "openai/gpt-oss-120b-fast", "displayName": "gpt-oss-120b-fast", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-05-07", "openWeights": true, "releaseDate": "2025-06-10", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss-120b-high-throughput", "provider": "openai", "model": "gpt-oss-120b-high-throughput", "displayName": "GPT OSS 120B High Throughput", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "clarifai" ], "aliases": [ "clarifai/openai/chat-completion/models/gpt-oss-120b-high-throughput" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "openai/chat-completion/models/gpt-oss-120b-high-throughput", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } } ] }, "metadata": { "displayNames": [ "GPT OSS 120B High Throughput" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "openai/chat-completion/models/gpt-oss-120b-high-throughput", "modelKey": "openai/chat-completion/models/gpt-oss-120b-high-throughput", "displayName": "GPT OSS 120B High Throughput", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss-120b-maas", "provider": "openai", "model": "gpt-oss-120b-maas", "displayName": "GPT OSS 120B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-openai_models" ], "aliases": [ "google-vertex/openai/gpt-oss-120b-maas", "vertex_ai-openai_models/vertex_ai/openai/gpt-oss-120b-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "openai/gpt-oss-120b-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "litellm", "provider": "vertex_ai-openai_models", "model": "vertex_ai/openai/gpt-oss-120b-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "GPT OSS 120B" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "openai/gpt-oss-120b-maas", "modelKey": "openai/gpt-oss-120b-maas", "displayName": "GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-openai_models", "model": "vertex_ai/openai/gpt-oss-120b-maas", "mode": "chat", "metadata": { "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" } } ] }, { "id": "openai/gpt-oss-120b-mxfp-gguf", "provider": "openai", "model": "gpt-oss-120b-mxfp-gguf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lemonade" ], "aliases": [ "lemonade/gpt-oss-120b-mxfp-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lemonade", "model": "lemonade/gpt-oss-120b-mxfp-GGUF", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lemonade", "model": "lemonade/gpt-oss-120b-mxfp-GGUF", "mode": "chat" } ] }, { "id": "openai/gpt-oss-120b-tee", "provider": "openai", "model": "gpt-oss-120b-tee", "displayName": "gpt oss 120b TEE", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/openai/gpt-oss-120b-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "openai/gpt-oss-120b-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.045, "input": 0.09, "output": 0.36 } } ] }, "metadata": { "displayNames": [ "gpt oss 120b TEE" ], "families": [ "gpt-oss" ], "releaseDate": "2025-12-29", "lastUpdated": "2026-04-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "openai/gpt-oss-120b-TEE", "modelKey": "openai/gpt-oss-120b-TEE", "displayName": "gpt oss 120b TEE", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss-120b:free", "provider": "openai", "model": "gpt-oss-120b:free", "displayName": "gpt-oss-120b (free)", "family": "gpt-oss", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/openai/gpt-oss-120b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-oss-120b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-oss-120b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "OpenAI: gpt-oss-120b (free)", "gpt-oss-120b (free)" ], "families": [ "gpt-oss" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "supportedParameters": [ "include_reasoning", "max_tokens", "min_p", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-oss-120b:free", "modelKey": "openai/gpt-oss-120b:free", "displayName": "gpt-oss-120b (free)", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-oss-120b:free", "displayName": "OpenAI: gpt-oss-120b (free)", "metadata": { "canonicalSlug": "openai/gpt-oss-120b", "createdAt": "2025-08-05T17:17:11.000Z", "huggingFaceId": "openai/gpt-oss-120b", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-oss-120b/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "min_p", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": true } } } ] }, { "id": "openai/gpt-oss-20b", "provider": "openai", "model": "gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "clarifai", "cloudflare-ai-gateway", "cloudflare-workers-ai", "deepinfra", "fastrouter", "fireworks-ai", "fireworks_ai", "frogbot", "groq", "helicone", "io-net", "kilo", "llmgateway", "lmstudio", "nano-gpt", "neon", "novita", "novita-ai", "nvidia", "openrouter", "ovhcloud", "qiniu-ai", "regolo-ai", "replicate", "siliconflow", "together_ai", "togetherai", "vercel", "wandb" ], "aliases": [ "clarifai/openai/chat-completion/models/gpt-oss-20b", "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b", "cloudflare-workers-ai/@cf/openai/gpt-oss-20b", "deepinfra/openai/gpt-oss-20b", "fastrouter/openai/gpt-oss-20b", "fireworks-ai/accounts/fireworks/models/gpt-oss-20b", "fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "frogbot/gpt-oss-20b", "groq/openai/gpt-oss-20b", "helicone/gpt-oss-20b", "io-net/openai/gpt-oss-20b", "kilo/openai/gpt-oss-20b", "llmgateway/gpt-oss-20b", "lmstudio/openai/gpt-oss-20b", "nano-gpt/TEE/gpt-oss-20b", "nano-gpt/openai/gpt-oss-20b", "neon/gpt-oss-20b", "novita-ai/openai/gpt-oss-20b", "novita/openai/gpt-oss-20b", "nvidia/openai/gpt-oss-20b", "openrouter/openai/gpt-oss-20b", "ovhcloud/gpt-oss-20b", "qiniu-ai/gpt-oss-20b", "regolo-ai/gpt-oss-20b", "replicate/replicateopenai/gpt-oss-20b", "siliconflow/openai/gpt-oss-20b", "together_ai/openai/gpt-oss-20b", "togetherai/openai/gpt-oss-20b", "vercel/openai/gpt-oss-20b", "wandb/openai/gpt-oss-20b" ], "mergedProviderModelRecords": 30, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": true, "systemMessages": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "clarifai", "model": "openai/chat-completion/models/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.18 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.3 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.3 } }, { "source": "models.dev", "provider": "deepinfra", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.14 } }, { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.035, "input": 0.07, "output": 0.3 } }, { "source": "models.dev", "provider": "frogbot", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.2 } }, { "source": "models.dev", "provider": "groq", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0375, "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "helicone", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.049999999999999996, "output": 0.19999999999999998 } }, { "source": "models.dev", "provider": "io-net", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "cacheWrite": 0.06, "input": 0.03, "output": 0.14 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.14 } }, { "source": "models.dev", "provider": "llmgateway", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "models.dev", "provider": "lmstudio", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "neon", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "models.dev", "provider": "nvidia", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.029, "output": 0.14 } }, { "source": "models.dev", "provider": "ovhcloud", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.18 } }, { "source": "models.dev", "provider": "regolo-ai", "model": "gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.8 } }, { "source": "models.dev", "provider": "siliconflow", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.18 } }, { "source": "models.dev", "provider": "togetherai", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "models.dev", "provider": "wandb", "model": "openai/gpt-oss-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "litellm", "provider": "groq", "model": "groq/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0375, "input": 0.075, "output": 0.3 } }, { "source": "litellm", "provider": "novita", "model": "novita/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0.1 } }, { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.15 } }, { "source": "litellm", "provider": "replicate", "model": "replicateopenai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.36 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/openai/gpt-oss-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5000, "output": 20000 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-oss-20b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.029, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "GPT OSS 20B", "GPT-OSS 20B", "GPT-OSS 20B TEE", "GPT-OSS-20B", "OpenAI GPT-OSS 20b", "OpenAI: GPT OSS 20B", "OpenAI: gpt-oss-20b", "gpt-oss-20b", "openai/gpt-oss-20b" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-08-05", "lastUpdated": "2025-12-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 30 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "clarifai", "providerName": "Clarifai", "providerApi": "https://api.clarifai.com/v2/ext/openai/v1", "providerDoc": "https://docs.clarifai.com/compute/inference/", "model": "openai/chat-completion/models/gpt-oss-20b", "modelKey": "openai/chat-completion/models/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-12-12", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/openai/gpt-oss-20b", "modelKey": "workers-ai/@cf/openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/openai/gpt-oss-20b", "modelKey": "@cf/openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/gpt-oss-20b", "modelKey": "accounts/fireworks/models/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "1970-01-01", "openWeights": true, "releaseDate": "1970-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-09-25", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "OpenAI GPT-OSS 20b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT-OSS 20B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": true, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "OpenAI: gpt-oss-20b", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lmstudio", "providerName": "LMStudio", "providerApi": "http://127.0.0.1:1234/v1", "providerDoc": "https://lmstudio.ai/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/gpt-oss-20b", "modelKey": "TEE/gpt-oss-20b", "displayName": "GPT-OSS 20B TEE", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neon", "providerName": "Neon", "providerApi": "${NEON_AI_GATEWAY_BASE_URL}/ai-gateway/mlflow/v1", "providerDoc": "https://neon.com/docs", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "OpenAI: GPT OSS 20B", "metadata": { "lastUpdated": "2025-08-06", "openWeights": true, "releaseDate": "2025-08-06", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ovhcloud", "providerName": "OVHcloud AI Endpoints", "providerApi": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "providerDoc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "gpt-oss-20b", "metadata": { "lastUpdated": "2025-08-28", "openWeights": true, "releaseDate": "2025-08-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "gpt-oss-20b", "metadata": { "lastUpdated": "2025-08-06", "openWeights": false, "releaseDate": "2025-08-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "regolo-ai", "providerName": "Regolo AI", "providerApi": "https://api.regolo.ai/v1", "providerDoc": "https://docs.regolo.ai/", "model": "gpt-oss-20b", "modelKey": "gpt-oss-20b", "displayName": "GPT-OSS-20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-03-01", "openWeights": true, "releaseDate": "2026-03-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "openai/gpt-oss-20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "openai/gpt-oss-20b", "modelKey": "openai/gpt-oss-20b", "displayName": "gpt-oss-20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-03-12", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/openai/gpt-oss-20b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/openai/gpt-oss-20b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/openai/gpt-oss-20b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/gpt-oss-20b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/openai/gpt-oss-20b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/gpt-oss-20b", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicateopenai/gpt-oss-20b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/openai/gpt-oss-20b", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/gpt-oss-20b" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/openai/gpt-oss-20b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-oss-20b", "displayName": "OpenAI: gpt-oss-20b", "metadata": { "canonicalSlug": "openai/gpt-oss-20b", "createdAt": "2025-08-05T17:17:09.000Z", "huggingFaceId": "openai/gpt-oss-20b", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-oss-20b/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openai/gpt-oss-20b-maas", "provider": "openai", "model": "gpt-oss-20b-maas", "displayName": "GPT OSS 20B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-openai_models" ], "aliases": [ "google-vertex/openai/gpt-oss-20b-maas", "vertex_ai-openai_models/vertex_ai/openai/gpt-oss-20b-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "openai/gpt-oss-20b-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.25 } }, { "source": "litellm", "provider": "vertex_ai-openai_models", "model": "vertex_ai/openai/gpt-oss-20b-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "GPT OSS 20B" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "openai/gpt-oss-20b-maas", "modelKey": "openai/gpt-oss-20b-maas", "displayName": "GPT OSS 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-openai_models", "model": "vertex_ai/openai/gpt-oss-20b-maas", "mode": "chat", "metadata": { "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" } } ] }, { "id": "openai/gpt-oss-20b-mxfp4-gguf", "provider": "openai", "model": "gpt-oss-20b-mxfp4-gguf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "lemonade" ], "aliases": [ "lemonade/gpt-oss-20b-mxfp4-GGUF" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "lemonade", "model": "lemonade/gpt-oss-20b-mxfp4-GGUF", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "lemonade", "model": "lemonade/gpt-oss-20b-mxfp4-GGUF", "mode": "chat" } ] }, { "id": "openai/gpt-oss-20b:free", "provider": "openai", "model": "gpt-oss-20b:free", "displayName": "gpt-oss-20b (free)", "family": "gpt-oss", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/openai/gpt-oss-20b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-oss-20b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-oss-20b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "OpenAI: gpt-oss-20b (free)", "gpt-oss-20b (free)" ], "families": [ "gpt-oss" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-oss-20b:free", "modelKey": "openai/gpt-oss-20b:free", "displayName": "gpt-oss-20b (free)", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-08-05", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-oss-20b:free", "displayName": "OpenAI: gpt-oss-20b (free)", "metadata": { "canonicalSlug": "openai/gpt-oss-20b", "createdAt": "2025-08-05T17:17:09.000Z", "huggingFaceId": "openai/gpt-oss-20b", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/gpt-oss-20b/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openai/gpt-oss-safeguard-120b", "provider": "openai", "model": "gpt-oss-safeguard-120b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b", "mode": "chat" } ] }, { "id": "openai/gpt-oss-safeguard-20b", "provider": "openai", "model": "gpt-oss-safeguard-20b", "displayName": "Safety GPT OSS 20B", "family": "gpt-oss", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "fireworks_ai", "groq", "kilo", "nano-gpt", "openrouter", "vercel" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b", "groq/openai/gpt-oss-safeguard-20b", "kilo/openai/gpt-oss-safeguard-20b", "nano-gpt/openai/gpt-oss-safeguard-20b", "openrouter/openai/gpt-oss-safeguard-20b", "vercel/openai/gpt-oss-safeguard-20b" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "supports1MContext": false, "parallelFunctionCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "groq", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.037, "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.037, "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0375, "input": 0.075, "output": 0.3 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.037, "input": 0.075, "output": 0.3 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.5 } }, { "source": "litellm", "provider": "groq", "model": "groq/openai/gpt-oss-safeguard-20b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.037, "input": 0.075, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/gpt-oss-safeguard-20b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0375, "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "GPT OSS Safeguard 20B", "OpenAI: gpt-oss-safeguard-20b", "Safety GPT OSS 20B", "gpt-oss-safeguard-20b" ], "families": [ "gpt-oss" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-10-29", "lastUpdated": "2025-10-29", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "openai/gpt-oss-safeguard-20b", "modelKey": "openai/gpt-oss-safeguard-20b", "displayName": "Safety GPT OSS 20B", "family": "gpt-oss", "status": "beta", "metadata": { "lastUpdated": "2025-10-29", "openWeights": true, "releaseDate": "2025-10-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/gpt-oss-safeguard-20b", "modelKey": "openai/gpt-oss-safeguard-20b", "displayName": "OpenAI: gpt-oss-safeguard-20b", "metadata": { "lastUpdated": "2025-10-29", "openWeights": false, "releaseDate": "2025-10-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/gpt-oss-safeguard-20b", "modelKey": "openai/gpt-oss-safeguard-20b", "displayName": "GPT OSS Safeguard 20B", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-10-29", "openWeights": false, "releaseDate": "2025-10-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/gpt-oss-safeguard-20b", "modelKey": "openai/gpt-oss-safeguard-20b", "displayName": "gpt-oss-safeguard-20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2025-10-29", "openWeights": true, "releaseDate": "2025-10-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/gpt-oss-safeguard-20b", "modelKey": "openai/gpt-oss-safeguard-20b", "displayName": "gpt-oss-safeguard-20b", "family": "gpt-oss", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/openai/gpt-oss-safeguard-20b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/gpt-oss-safeguard-20b", "displayName": "OpenAI: gpt-oss-safeguard-20b", "metadata": { "canonicalSlug": "openai/gpt-oss-safeguard-20b", "createdAt": "2025-10-29T15:47:16.000Z", "huggingFaceId": "openai/gpt-oss-safeguard-20b", "links": { "details": "/api/v1/models/openai/gpt-oss-safeguard-20b/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 131072, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openai/gpt-oss:120b", "provider": "openai", "model": "gpt-oss:120b", "displayName": "gpt-oss:120b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gpt-oss:120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gpt-oss:120b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gpt-oss:120b", "modelKey": "gpt-oss:120b", "displayName": "gpt-oss:120b", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss:120b-cloud", "provider": "openai", "model": "gpt-oss:120b-cloud", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/gpt-oss:120b-cloud" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/gpt-oss:120b-cloud", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/gpt-oss:120b-cloud", "mode": "chat" } ] }, { "id": "openai/gpt-oss:20b", "provider": "openai", "model": "gpt-oss:20b", "displayName": "gpt-oss:20b", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "ollama-cloud" ], "aliases": [ "ollama-cloud/gpt-oss:20b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "gpt-oss:20b" ], "families": [ "gpt-oss" ], "releaseDate": "2025-08-05", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "gpt-oss:20b", "modelKey": "gpt-oss:20b", "displayName": "gpt-oss:20b", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-08-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "openai/gpt-oss:20b-cloud", "provider": "openai", "model": "gpt-oss:20b-cloud", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ollama" ], "aliases": [ "ollama/gpt-oss:20b-cloud" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ollama", "model": "ollama/gpt-oss:20b-cloud", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ollama", "model": "ollama/gpt-oss:20b-cloud", "mode": "chat" } ] }, { "id": "openai/gpt-realtime", "provider": "openai", "model": "gpt-realtime", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-realtime" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-realtime", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 4e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-1.5", "provider": "openai", "model": "gpt-realtime-1.5", "displayName": "GPT Realtime 1.5", "family": "gpt", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "fastrouter", "openai" ], "aliases": [ "fastrouter/openai/gpt-realtime-1.5", "openai/gpt-realtime-1.5" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "openai/gpt-realtime-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4, "output": 16 } }, { "source": "litellm", "provider": "openai", "model": "gpt-realtime-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 4e-7 } } ] }, "metadata": { "displayNames": [ "GPT Realtime 1.5" ], "families": [ "gpt" ], "modes": [ "chat" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "openai/gpt-realtime-1.5", "modelKey": "openai/gpt-realtime-1.5", "displayName": "GPT Realtime 1.5", "family": "gpt", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-1.5", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-1.5-2026-02-23", "provider": "openai", "model": "gpt-realtime-1.5-2026-02-23", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/gpt-realtime-1.5-2026-02-23" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-realtime-1.5-2026-02-23", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 0.000004 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-realtime-1.5-2026-02-23", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-2", "provider": "openai", "model": "gpt-realtime-2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-realtime-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-realtime-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 4e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-2", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-2025-08-28", "provider": "openai", "model": "gpt-realtime-2025-08-28", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-realtime-2025-08-28", "openai/gpt-realtime-2025-08-28" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-realtime-2025-08-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 0.000004 } }, { "source": "litellm", "provider": "openai", "model": "gpt-realtime-2025-08-28", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.4, "input": 4, "inputAudio": 32, "output": 16, "outputAudio": 64 }, "perImage": { "input": 0.000005 }, "extra": { "cache_creation_input_audio_token_cost": 4e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-realtime-2025-08-28", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-2025-08-28", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-mini", "provider": "openai", "model": "gpt-realtime-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-realtime-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-realtime-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-mini-2025-10-06", "provider": "openai", "model": "gpt-realtime-mini-2025-10-06", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/gpt-realtime-mini-2025-10-06", "openai/gpt-realtime-mini-2025-10-06" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/gpt-realtime-mini-2025-10-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "perImage": { "input": 8e-7 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7 } }, { "source": "litellm", "provider": "openai", "model": "gpt-realtime-mini-2025-10-06", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "perImage": { "input": 8e-7 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/gpt-realtime-mini-2025-10-06", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-mini-2025-10-06", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/gpt-realtime-mini-2025-12-15", "provider": "openai", "model": "gpt-realtime-mini-2025-12-15", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/gpt-realtime-mini-2025-12-15" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "capabilities": { "audioInput": true, "audioOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "gpt-realtime-mini-2025-12-15", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.6, "inputAudio": 10, "output": 2.4, "outputAudio": 20 }, "perImage": { "input": 8e-7 }, "extra": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7 } } ] }, "metadata": { "modes": [ "chat" ], "supportedEndpoints": [ "/v1/realtime" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "gpt-realtime-mini-2025-12-15", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/realtime" ] } } ] }, { "id": "openai/o1", "provider": "openai", "model": "o1", "displayName": "o1", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "github-models", "kilo", "merge-gateway", "nano-gpt", "openai", "openrouter", "poe", "replicate", "vercel", "vercel_ai_gateway" ], "aliases": [ "cloudflare-ai-gateway/openai/o1", "github-models/openai/o1", "kilo/openai/o1", "merge-gateway/openai/o1", "nano-gpt/openai/o1", "openai/o1", "openrouter/openai/o1", "poe/openai/o1", "replicate/openai/o1", "vercel/openai/o1", "vercel_ai_gateway/openai/o1" ], "mergedProviderModelRecords": 11, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.993999999999998, "output": 59.993 } }, { "source": "models.dev", "provider": "openai", "model": "o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14, "output": 54 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "openai", "model": "o1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/o1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/o1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 60, "reasoningOutput": 60 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "cacheWrite": 0, "input": 15, "output": 60 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o1", "OpenAI: o1", "o1" ], "families": [ "o" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-12-05", "lastUpdated": "2024-12-05", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 11 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "OpenAI o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-17", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "OpenAI: o1", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "OpenAI o1", "family": "o", "metadata": { "lastUpdated": "2024-12-17", "openWeights": false, "releaseDate": "2024-12-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o1", "modelKey": "o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "o1", "family": "o", "metadata": { "lastUpdated": "2024-12-18", "openWeights": false, "releaseDate": "2024-12-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o1", "modelKey": "openai/o1", "displayName": "o1", "family": "o", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-12-05", "openWeights": false, "releaseDate": "2024-12-05", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/o1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/o1", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o1", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o1", "displayName": "OpenAI: o1", "metadata": { "canonicalSlug": "openai/o1-2024-12-17", "createdAt": "2024-12-17T18:26:39.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/o1-2024-12-17/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o1-2024-12-17", "provider": "openai", "model": "o1-2024-12-17", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/o1-2024-12-17", "azure/o1-2024-12-17", "azure/us/o1-2024-12-17", "openai/o1-2024-12-17" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/o1-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 8.25, "input": 16.5, "output": 66 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o1-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 8.25, "input": 16.5, "output": 66 } }, { "source": "litellm", "provider": "openai", "model": "o1-2024-12-17", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/o1-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o1-2024-12-17", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o1-2024-12-17", "mode": "chat" } ] }, { "id": "openai/o1-mini", "provider": "openai", "model": "o1-mini", "displayName": "o1-mini", "family": "o-mini", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "github-models", "helicone", "replicate" ], "aliases": [ "azure-cognitive-services/o1-mini", "azure/o1-mini", "github-models/openai/o1-mini", "helicone/o1-mini", "replicate/openai/o1-mini" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "vision": false, "supports1MContext": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "o1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "azure", "model": "o1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/o1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "o1-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.605, "input": 1.21, "output": 4.84 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/o1-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 4.4, "reasoningOutput": 4.4 } } ] }, "metadata": { "displayNames": [ "OpenAI o1-mini", "OpenAI: o1-mini", "o1-mini" ], "families": [ "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-09-12", "lastUpdated": "2024-09-12", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o1-mini", "modelKey": "o1-mini", "displayName": "o1-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-09-12", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o1-mini", "modelKey": "o1-mini", "displayName": "o1-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2024-09-12", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o1-mini", "modelKey": "openai/o1-mini", "displayName": "OpenAI o1-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-12-17", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o1-mini", "modelKey": "o1-mini", "displayName": "OpenAI: o1-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-01", "openWeights": false, "releaseDate": "2025-01-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/o1-mini", "mode": "chat" } ] }, { "id": "openai/o1-mini-2024-09-12", "provider": "openai", "model": "o1-mini-2024-09-12", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/eu/o1-mini-2024-09-12", "azure/o1-mini-2024-09-12", "azure/us/o1-mini-2024-09-12" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false, "reasoning": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/o1-mini-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.605, "input": 1.21, "output": 4.84 }, "extra": { "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token_batches": 0.00000242 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1-mini-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o1-mini-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.605, "input": 1.21, "output": 4.84 }, "extra": { "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token_batches": 0.00000242 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/o1-mini-2024-09-12", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1-mini-2024-09-12", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o1-mini-2024-09-12", "mode": "chat" } ] }, { "id": "openai/o1-preview", "provider": "openai", "model": "o1-preview", "displayName": "OpenAI o1-preview", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "github-models", "nano-gpt" ], "aliases": [ "azure/o1-preview", "github-models/openai/o1-preview", "nano-gpt/openai/o1-preview" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "vision": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "openai/o1-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o1-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.993999999999998, "output": 59.993 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } } ] }, "metadata": { "displayNames": [ "OpenAI o1-preview" ], "families": [ "o" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-09-12", "lastUpdated": "2024-09-12", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o1-preview", "modelKey": "openai/o1-preview", "displayName": "OpenAI o1-preview", "family": "o", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2024-09-12", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o1-preview", "modelKey": "openai/o1-preview", "displayName": "OpenAI o1-preview", "family": "o", "metadata": { "lastUpdated": "2024-09-12", "openWeights": false, "releaseDate": "2024-09-12" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1-preview", "mode": "chat" } ] }, { "id": "openai/o1-preview-2024-09-12", "provider": "openai", "model": "o1-preview-2024-09-12", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure" ], "aliases": [ "azure/eu/o1-preview-2024-09-12", "azure/o1-preview-2024-09-12", "azure/us/o1-preview-2024-09-12" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false, "reasoning": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/o1-preview-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 8.25, "input": 16.5, "output": 66 } }, { "source": "litellm", "provider": "azure", "model": "azure/o1-preview-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 7.5, "input": 15, "output": 60 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o1-preview-2024-09-12", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 8.25, "input": 16.5, "output": 66 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/o1-preview-2024-09-12", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o1-preview-2024-09-12", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o1-preview-2024-09-12", "mode": "chat" } ] }, { "id": "openai/o1-pro", "provider": "openai", "model": "o1-pro", "displayName": "o1-pro", "family": "o-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openai", "openrouter", "poe" ], "aliases": [ "kilo/openai/o1-pro", "nano-gpt/openai/o1-pro", "openai/o1-pro", "openrouter/openai/o1-pro", "poe/openai/o1-pro" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/o1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 150, "output": 600 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 150, "output": 600 } }, { "source": "models.dev", "provider": "openai", "model": "o1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 150, "output": 600 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 150, "output": 600 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o1-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 140, "output": 540 } }, { "source": "litellm", "provider": "openai", "model": "o1-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 150, "output": 600 }, "extra": { "input_cost_per_token_batches": 0.000075, "output_cost_per_token_batches": 0.0003 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o1-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 150, "output": 600 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o1 Pro", "OpenAI: o1-pro", "o1-pro" ], "families": [ "o-pro" ], "modes": [ "responses" ], "knowledgeCutoff": "2023-09", "releaseDate": "2025-03-19", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o1-pro", "modelKey": "openai/o1-pro", "displayName": "OpenAI: o1-pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o1-pro", "modelKey": "openai/o1-pro", "displayName": "OpenAI o1 Pro", "family": "o-pro", "metadata": { "lastUpdated": "2025-01-25", "openWeights": false, "releaseDate": "2025-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o1-pro", "modelKey": "o1-pro", "displayName": "o1-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2025-03-19", "openWeights": false, "releaseDate": "2025-03-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o1-pro", "modelKey": "openai/o1-pro", "displayName": "o1-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2025-03-19", "openWeights": false, "releaseDate": "2025-03-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o1-pro", "modelKey": "openai/o1-pro", "displayName": "o1-pro", "family": "o-pro", "metadata": { "lastUpdated": "2025-03-19", "openWeights": false, "releaseDate": "2025-03-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o1-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o1-pro", "displayName": "OpenAI: o1-pro", "metadata": { "canonicalSlug": "openai/o1-pro", "createdAt": "2025-03-19T22:26:51.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/o1-pro/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o1-pro-2025-03-19", "provider": "openai", "model": "o1-pro-2025-03-19", "mode": "responses", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/o1-pro-2025-03-19" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": false, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "o1-pro-2025-03-19", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 150, "output": 600 }, "extra": { "input_cost_per_token_batches": 0.000075, "output_cost_per_token_batches": 0.0003 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o1-pro-2025-03-19", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } } ] }, { "id": "openai/o3", "provider": "openai", "model": "o3", "displayName": "o3", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "cloudflare-ai-gateway", "github-models", "kilo", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "poe", "vercel", "vercel_ai_gateway" ], "aliases": [ "anyapi/openai/o3", "cloudflare-ai-gateway/openai/o3", "github-models/openai/o3", "kilo/openai/o3", "merge-gateway/openai/o3", "nano-gpt/openai/o3", "nearai/openai/o3", "openai/o3", "openrouter/openai/o3", "poe/openai/o3", "vercel/openai/o3", "vercel_ai_gateway/openai/o3" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openai", "model": "o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.45, "input": 1.8, "output": 7.2 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "openai", "model": "o3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 0, "input": 2, "output": 8 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o3", "OpenAI: o3", "o3" ], "families": [ "o" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions", "/v1/responses" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "OpenAI o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "OpenAI: o3", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "OpenAI o3", "family": "o", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o3", "modelKey": "o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o3", "modelKey": "openai/o3", "displayName": "o3", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o3", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o3", "displayName": "OpenAI: o3", "metadata": { "canonicalSlug": "openai/o3-2025-04-16", "createdAt": "2025-04-16T17:10:57.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o3-2025-04-16", "provider": "openai", "model": "o3-2025-04-16", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/o3-2025-04-16", "azure/us/o3-2025-04-16", "openai/o3-2025-04-16" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/o3-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o3-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 2.2, "output": 8.8 } }, { "source": "litellm", "provider": "openai", "model": "o3-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-04-16", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-2025-04-16", "mode": "chat", "metadata": { "deprecationDate": "2026-04-16", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o3-2025-04-16", "mode": "chat", "metadata": { "deprecationDate": "2026-04-16", "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-2025-04-16", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } } ] }, { "id": "openai/o3-deep-research", "provider": "openai", "model": "o3-deep-research", "displayName": "o3-deep-research", "family": "o", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "azure", "kilo", "nano-gpt", "openai", "openrouter", "poe", "vercel" ], "aliases": [ "azure/o3-deep-research", "kilo/openai/o3-deep-research", "nano-gpt/openai/o3-deep-research", "openai/o3-deep-research", "openrouter/openai/o3-deep-research", "poe/openai/o3-deep-research", "vercel/openai/o3-deep-research" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } }, { "source": "models.dev", "provider": "openai", "model": "o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.2, "input": 9, "output": 36 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o3-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3-deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 } }, { "source": "litellm", "provider": "openai", "model": "o3-deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 }, "extra": { "input_cost_per_token_batches": 0.000005, "output_cost_per_token_batches": 0.00002 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o3-deep-research", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o3 Deep Research", "OpenAI: o3 Deep Research", "o3-deep-research" ], "families": [ "o" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-05", "releaseDate": "2024-06-26", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o3-deep-research", "modelKey": "openai/o3-deep-research", "displayName": "OpenAI: o3 Deep Research", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-06-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3-deep-research", "modelKey": "openai/o3-deep-research", "displayName": "OpenAI o3 Deep Research", "family": "o", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o3-deep-research", "modelKey": "o3-deep-research", "displayName": "o3-deep-research", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-06-26", "openWeights": false, "releaseDate": "2024-06-26", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o3-deep-research", "modelKey": "openai/o3-deep-research", "displayName": "o3-deep-research", "family": "o", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-06-26", "openWeights": false, "releaseDate": "2024-06-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o3-deep-research", "modelKey": "openai/o3-deep-research", "displayName": "o3-deep-research", "family": "o", "metadata": { "lastUpdated": "2025-06-27", "openWeights": false, "releaseDate": "2025-06-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o3-deep-research", "modelKey": "openai/o3-deep-research", "displayName": "o3-deep-research", "family": "o", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-06-26", "openWeights": false, "releaseDate": "2024-06-26", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-deep-research", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-deep-research", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o3-deep-research", "displayName": "OpenAI: o3 Deep Research", "metadata": { "canonicalSlug": "openai/o3-deep-research-2025-06-26", "createdAt": "2025-10-10T20:54:21.000Z", "links": { "details": "/api/v1/models/openai/o3-deep-research-2025-06-26/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o3-deep-research-2025-06-26", "provider": "openai", "model": "o3-deep-research-2025-06-26", "mode": "responses", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/o3-deep-research-2025-06-26" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "o3-deep-research-2025-06-26", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 2.5, "input": 10, "output": 40 }, "extra": { "input_cost_per_token_batches": 0.000005, "output_cost_per_token_batches": 0.00002 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-deep-research-2025-06-26", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/o3-mini", "provider": "openai", "model": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "anyapi", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "github-models", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "poe", "vercel", "vercel_ai_gateway" ], "aliases": [ "abacus/o3-mini", "anyapi/openai/o3-mini", "azure-cognitive-services/o3-mini", "azure/o3-mini", "cloudflare-ai-gateway/openai/o3-mini", "github-models/openai/o3-mini", "helicone/o3-mini", "jiekou/o3-mini", "kilo/openai/o3-mini", "llmgateway/o3-mini", "merge-gateway/openai/o3-mini", "nano-gpt/openai/o3-mini", "nearai/openai/o3-mini", "openai/o3-mini", "openrouter/openai/o3-mini", "poe/openai/o3-mini", "vercel/openai/o3-mini", "vercel_ai_gateway/openai/o3-mini" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": false, "supports1MContext": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "azure", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "jiekou", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "openai", "model": "o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.99, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "openai", "model": "o3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/o3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "cacheWrite": 0, "input": 1.1, "output": 4.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o3-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o3 Mini", "OpenAI o3-mini", "OpenAI: o3 Mini", "o3-mini" ], "families": [ "o", "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05", "releaseDate": "2024-12-20", "lastUpdated": "2025-01-29", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "OpenAI o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "OpenAI o3 Mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2023-10-01", "openWeights": false, "releaseDate": "2023-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "OpenAI: o3 Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-12-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "OpenAI o3-mini", "family": "o-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o3-mini", "modelKey": "o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o3-mini", "modelKey": "openai/o3-mini", "displayName": "o3-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-01-29", "openWeights": false, "releaseDate": "2024-12-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/o3-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o3-mini", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o3-mini", "displayName": "OpenAI: o3 Mini", "metadata": { "canonicalSlug": "openai/o3-mini-2025-01-31", "createdAt": "2025-01-31T19:28:41.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/o3-mini-2025-01-31/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o3-mini-2025-01-31", "provider": "openai", "model": "o3-mini-2025-01-31", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/eu/o3-mini-2025-01-31", "azure/o3-mini-2025-01-31", "azure/us/o3-mini-2025-01-31", "openai/o3-mini-2025-01-31" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/eu/o3-mini-2025-01-31", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.605, "input": 1.21, "output": 4.84 }, "extra": { "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token_batches": 0.00000242 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3-mini-2025-01-31", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o3-mini-2025-01-31", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.605, "input": 1.21, "output": 4.84 }, "extra": { "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token_batches": 0.00000242 } }, { "source": "litellm", "provider": "openai", "model": "o3-mini-2025-01-31", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/eu/o3-mini-2025-01-31", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-mini-2025-01-31", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o3-mini-2025-01-31", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-mini-2025-01-31", "mode": "chat" } ] }, { "id": "openai/o3-mini-high", "provider": "openai", "model": "o3-mini-high", "displayName": "o3 Mini High", "family": "o", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter", "poe" ], "aliases": [ "kilo/openai/o3-mini-high", "nano-gpt/openai/o3-mini-high", "openrouter/openai/o3-mini-high", "poe/openai/o3-mini-high" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 65536, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/o3-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.64, "output": 2.588 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o3-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o3-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.99, "output": 4 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openai/o3-mini-high", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o3-mini-high", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.55, "input": 1.1, "output": 4.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o3-mini (High)", "OpenAI: o3 Mini High", "o3 Mini High", "o3-mini-high" ], "families": [ "o", "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10-31", "releaseDate": "2025-01-31", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o3-mini-high", "modelKey": "openai/o3-mini-high", "displayName": "OpenAI: o3 Mini High", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3-mini-high", "modelKey": "openai/o3-mini-high", "displayName": "OpenAI o3-mini (High)", "family": "o-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o3-mini-high", "modelKey": "openai/o3-mini-high", "displayName": "o3 Mini High", "family": "o", "metadata": { "knowledgeCutoff": "2023-10-31", "lastUpdated": "2025-02-12", "openWeights": false, "releaseDate": "2025-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o3-mini-high", "modelKey": "openai/o3-mini-high", "displayName": "o3-mini-high", "family": "o-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openai/o3-mini-high", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o3-mini-high", "displayName": "OpenAI: o3 Mini High", "metadata": { "canonicalSlug": "openai/o3-mini-high-2025-01-31", "createdAt": "2025-02-12T15:03:31.000Z", "knowledgeCutoff": "2023-10-31", "links": { "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high" ], "default_effort": "high" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o3-mini-low", "provider": "openai", "model": "o3-mini-low", "displayName": "OpenAI o3-mini (Low)", "family": "o-mini", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/openai/o3-mini-low" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3-mini-low", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } } ] }, "metadata": { "displayNames": [ "OpenAI o3-mini (Low)" ], "families": [ "o-mini" ], "releaseDate": "2025-01-31", "lastUpdated": "2025-01-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3-mini-low", "modelKey": "openai/o3-mini-low", "displayName": "OpenAI o3-mini (Low)", "family": "o-mini", "metadata": { "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } } ] }, { "id": "openai/o3-pro", "provider": "openai", "model": "o3-pro", "displayName": "o3-pro", "family": "o-pro", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "azure", "cloudflare-ai-gateway", "helicone", "kilo", "openai", "openrouter", "poe", "vercel" ], "aliases": [ "abacus/o3-pro", "azure/o3-pro", "cloudflare-ai-gateway/openai/o3-pro", "helicone/o3-pro", "kilo/openai/o3-pro", "openai/o3-pro", "openrouter/openai/o3-pro", "poe/openai/o3-pro", "vercel/openai/o3-pro" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 40 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "models.dev", "provider": "helicone", "model": "o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "models.dev", "provider": "openai", "model": "o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 18, "output": 72 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o3-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 20, "output": 80 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 20, "output": 80 }, "extra": { "input_cost_per_token_batches": 0.00001, "output_cost_per_token_batches": 0.00004 } }, { "source": "litellm", "provider": "openai", "model": "o3-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 20, "output": 80 }, "extra": { "input_cost_per_token_batches": 0.00001, "output_cost_per_token_batches": 0.00004 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o3-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 20, "output": 80 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o3 Pro", "OpenAI: o3 Pro", "o3 Pro", "o3-pro" ], "families": [ "o-pro" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-06-10", "lastUpdated": "2025-06-10", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "o3-pro", "modelKey": "o3-pro", "displayName": "o3-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/o3-pro", "modelKey": "openai/o3-pro", "displayName": "o3-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o3-pro", "modelKey": "o3-pro", "displayName": "OpenAI o3 Pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o3-pro", "modelKey": "openai/o3-pro", "displayName": "OpenAI: o3 Pro", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o3-pro", "modelKey": "o3-pro", "displayName": "o3-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o3-pro", "modelKey": "openai/o3-pro", "displayName": "o3-pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o3-pro", "modelKey": "openai/o3-pro", "displayName": "o3-pro", "family": "o-pro", "metadata": { "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o3-pro", "modelKey": "openai/o3-pro", "displayName": "o3 Pro", "family": "o-pro", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-pro", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o3-pro", "displayName": "OpenAI: o3 Pro", "metadata": { "canonicalSlug": "openai/o3-pro-2025-06-10", "createdAt": "2025-06-10T23:32:32.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/o3-pro-2025-06-10/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o3-pro-2025-06-10", "provider": "openai", "model": "o3-pro-2025-06-10", "displayName": "OpenAI o3-pro (2025-06-10)", "family": "o-pro", "mode": "responses", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "nano-gpt", "openai" ], "aliases": [ "azure/o3-pro-2025-06-10", "nano-gpt/openai/o3-pro-2025-06-10", "openai/o3-pro-2025-06-10" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false, "attachments": false, "openWeights": false, "structuredOutput": true, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o3-pro-2025-06-10", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } }, { "source": "litellm", "provider": "azure", "model": "azure/o3-pro-2025-06-10", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 20, "output": 80 }, "extra": { "input_cost_per_token_batches": 0.00001, "output_cost_per_token_batches": 0.00004 } }, { "source": "litellm", "provider": "openai", "model": "o3-pro-2025-06-10", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 20, "output": 80 }, "extra": { "input_cost_per_token_batches": 0.00001, "output_cost_per_token_batches": 0.00004 } } ] }, "metadata": { "displayNames": [ "OpenAI o3-pro (2025-06-10)" ], "families": [ "o-pro" ], "modes": [ "responses" ], "releaseDate": "2025-06-10", "lastUpdated": "2025-06-10", "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o3-pro-2025-06-10", "modelKey": "openai/o3-pro-2025-06-10", "displayName": "OpenAI o3-pro (2025-06-10)", "family": "o-pro", "metadata": { "lastUpdated": "2025-06-10", "openWeights": false, "releaseDate": "2025-06-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o3-pro-2025-06-10", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o3-pro-2025-06-10", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/responses", "/v1/batch" ] } } ] }, { "id": "openai/o4-mini", "provider": "openai", "model": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "abacus", "anyapi", "azure", "azure-cognitive-services", "cloudflare-ai-gateway", "github-models", "helicone", "jiekou", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "nearai", "openai", "openrouter", "poe", "replicate", "requesty", "vercel", "vercel_ai_gateway" ], "aliases": [ "abacus/o4-mini", "anyapi/openai/o4-mini", "azure-cognitive-services/o4-mini", "azure/o4-mini", "cloudflare-ai-gateway/openai/o4-mini", "github-models/openai/o4-mini", "helicone/o4-mini", "jiekou/o4-mini", "kilo/openai/o4-mini", "llmgateway/o4-mini", "merge-gateway/openai/o4-mini", "nano-gpt/openai/o4-mini", "nearai/openai/o4-mini", "openai/o4-mini", "openrouter/openai/o4-mini", "poe/openai/o4-mini", "replicate/openai/o4-mini", "requesty/openai/o4-mini", "vercel/openai/o4-mini", "vercel_ai_gateway/openai/o4-mini" ], "mergedProviderModelRecords": 20, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": false, "promptCaching": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "azure", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.28, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "github-models", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "jiekou", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "kilo", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "openai", "model": "o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 0.99, "output": 4 } }, { "source": "models.dev", "provider": "requesty", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.28, "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "vercel", "model": "openai/o4-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/o4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "openai", "model": "o4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 }, "extra": { "cache_read_input_token_cost_flex": 1.375e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/openai/o4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 4, "reasoningOutput": 4 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o4-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "cacheWrite": 0, "input": 1.1, "output": 4.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o4-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o4 Mini", "OpenAI o4-mini", "OpenAI: o4 Mini", "o4 Mini", "o4-mini" ], "families": [ "o", "o-mini" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-05", "releaseDate": "2025-04-16", "lastUpdated": "2025-04-16", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 20 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "OpenAI o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-31", "openWeights": false, "releaseDate": "2025-01-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "OpenAI o4 Mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "OpenAI: o4 Mini", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "OpenAI o4-mini", "family": "o-mini", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o4-mini", "modelKey": "o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4 Mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/o4-mini", "modelKey": "openai/o4-mini", "displayName": "o4-mini", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o4-mini", "mode": "chat", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o4-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/openai/o4-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/o4-mini", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o4-mini", "displayName": "OpenAI: o4 Mini", "metadata": { "canonicalSlug": "openai/o4-mini-2025-04-16", "createdAt": "2025-04-16T16:29:02.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/o4-mini-2025-04-16/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o4-mini-2025-04-16", "provider": "openai", "model": "o4-mini-2025-04-16", "mode": "chat", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/o4-mini-2025-04-16", "azure/us/o4-mini-2025-04-16", "openai/o4-mini-2025-04-16" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": true, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "serviceTier": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/o4-mini-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "litellm", "provider": "azure", "model": "azure/us/o4-mini-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.31, "input": 1.21, "output": 4.84 } }, { "source": "litellm", "provider": "openai", "model": "o4-mini-2025-04-16", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/o4-mini-2025-04-16", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/us/o4-mini-2025-04-16", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o4-mini-2025-04-16", "mode": "chat" } ] }, { "id": "openai/o4-mini-deep-research", "provider": "openai", "model": "o4-mini-deep-research", "displayName": "o4-mini-deep-research", "family": "o-mini", "mode": "responses", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openai", "openrouter", "poe" ], "aliases": [ "kilo/openai/o4-mini-deep-research", "nano-gpt/openai/o4-mini-deep-research", "openai/o4-mini-deep-research", "openrouter/openai/o4-mini-deep-research", "poe/openai/o4-mini-deep-research" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/o4-mini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o4-mini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 19.992 } }, { "source": "models.dev", "provider": "openai", "model": "o4-mini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o4-mini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "poe", "model": "openai/o4-mini-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.45, "input": 1.8, "output": 7.2 } }, { "source": "litellm", "provider": "openai", "model": "o4-mini-deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000004 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o4-mini-deep-research", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o4-mini Deep Research", "OpenAI: o4 Mini Deep Research", "o4-mini-deep-research" ], "families": [ "o-mini" ], "modes": [ "responses" ], "knowledgeCutoff": "2024-05", "releaseDate": "2024-06-26", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o4-mini-deep-research", "modelKey": "openai/o4-mini-deep-research", "displayName": "OpenAI: o4 Mini Deep Research", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2024-06-26", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o4-mini-deep-research", "modelKey": "openai/o4-mini-deep-research", "displayName": "OpenAI o4-mini Deep Research", "family": "o-mini", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "o4-mini-deep-research", "modelKey": "o4-mini-deep-research", "displayName": "o4-mini-deep-research", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-06-26", "openWeights": false, "releaseDate": "2024-06-26", "reasoningOptions": [ { "type": "effort", "values": [ "medium" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o4-mini-deep-research", "modelKey": "openai/o4-mini-deep-research", "displayName": "o4-mini-deep-research", "family": "o-mini", "metadata": { "knowledgeCutoff": "2024-05", "lastUpdated": "2024-06-26", "openWeights": false, "releaseDate": "2024-06-26" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/o4-mini-deep-research", "modelKey": "openai/o4-mini-deep-research", "displayName": "o4-mini-deep-research", "family": "o-mini", "metadata": { "lastUpdated": "2025-06-27", "openWeights": false, "releaseDate": "2025-06-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o4-mini-deep-research", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o4-mini-deep-research", "displayName": "OpenAI: o4 Mini Deep Research", "metadata": { "canonicalSlug": "openai/o4-mini-deep-research-2025-06-26", "createdAt": "2025-10-10T20:54:02.000Z", "links": { "details": "/api/v1/models/openai/o4-mini-deep-research-2025-06-26/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/o4-mini-deep-research-2025-06-26", "provider": "openai", "model": "o4-mini-deep-research-2025-06-26", "mode": "responses", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/o4-mini-deep-research-2025-06-26" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 100000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "nativeStreaming": true, "parallelFunctionCalling": true, "pdfInput": true, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "o4-mini-deep-research-2025-06-26", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000004 } } ] }, "metadata": { "modes": [ "responses" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "o4-mini-deep-research-2025-06-26", "mode": "responses", "metadata": { "supportedEndpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ] } } ] }, { "id": "openai/o4-mini-high", "provider": "openai", "model": "o4-mini-high", "displayName": "OpenAI: o4 Mini High", "family": "o-mini", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/openai/o4-mini-high", "nano-gpt/openai/o4-mini-high", "openrouter/openai/o4-mini-high" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "temperature": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "openai/o4-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "openai/o4-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 4.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "openai/o4-mini-high", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "openai/o4-mini-high", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.275, "input": 1.1, "output": 4.4 }, "other": { "webSearch": 0.01 } } ] }, "metadata": { "displayNames": [ "OpenAI o4-mini high", "OpenAI: o4 Mini High", "o4 Mini High" ], "families": [ "o", "o-mini" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-04-17", "lastUpdated": "2026-03-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "openai/o4-mini-high", "modelKey": "openai/o4-mini-high", "displayName": "OpenAI: o4 Mini High", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-04-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "openai/o4-mini-high", "modelKey": "openai/o4-mini-high", "displayName": "OpenAI o4-mini high", "family": "o-mini", "metadata": { "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openai/o4-mini-high", "modelKey": "openai/o4-mini-high", "displayName": "o4 Mini High", "family": "o", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-04-16", "openWeights": false, "releaseDate": "2025-04-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openai/o4-mini-high", "displayName": "OpenAI: o4 Mini High", "metadata": { "canonicalSlug": "openai/o4-mini-high-2025-04-16", "createdAt": "2025-04-16T17:23:32.000Z", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high" ], "default_effort": "high" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], "tokenizer": "GPT", "topProvider": { "context_length": 200000, "max_completion_tokens": 100000, "is_moderated": true } } } ] }, { "id": "openai/omni-moderation-2024-09-26", "provider": "openai", "model": "omni-moderation-2024-09-26", "mode": "moderation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/omni-moderation-2024-09-26" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "omni-moderation-2024-09-26", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "moderation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "omni-moderation-2024-09-26", "mode": "moderation" } ] }, { "id": "openai/omni-moderation-latest", "provider": "openai", "model": "omni-moderation-latest", "mode": "moderation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/omni-moderation-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "omni-moderation-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "moderation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "omni-moderation-latest", "mode": "moderation" } ] }, { "id": "openai/sora-2", "provider": "openai", "model": "sora-2", "displayName": "Sora-2", "family": "sora", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "openai", "poe" ], "aliases": [ "openai/sora-2", "poe/openai/sora-2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": false, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "openai/sora-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.1 } }, { "source": "litellm", "provider": "openai", "model": "sora-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Sora-2" ], "families": [ "sora" ], "modes": [ "video_generation" ], "releaseDate": "2025-10-06", "lastUpdated": "2025-10-06", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/sora-2", "modelKey": "openai/sora-2", "displayName": "Sora-2", "family": "sora", "metadata": { "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "openai/sora-2", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "sora-2", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } } ] }, { "id": "openai/sora-2-pro", "provider": "openai", "model": "sora-2-pro", "displayName": "Sora-2-Pro", "family": "sora", "mode": "video_generation", "sources": [ "litellm", "models.dev" ], "providers": [ "openai", "poe" ], "aliases": [ "openai/sora-2-pro", "poe/openai/sora-2-pro" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text", "video" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false, "attachments": true, "openWeights": false, "reasoning": false, "temperature": false, "toolCalling": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "openai/sora-2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.3 } }, { "source": "litellm", "provider": "openai", "model": "sora-2-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Sora-2-Pro" ], "families": [ "sora" ], "modes": [ "video_generation" ], "releaseDate": "2025-10-06", "lastUpdated": "2025-10-06", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "openai/sora-2-pro", "modelKey": "openai/sora-2-pro", "displayName": "Sora-2-Pro", "family": "sora", "metadata": { "lastUpdated": "2025-10-06", "openWeights": false, "releaseDate": "2025-10-06" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "openai/sora-2-pro", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "sora-2-pro", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } } ] }, { "id": "openai/sora-2-pro-high-res", "provider": "openai", "model": "sora-2-pro-high-res", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/sora-2-pro-high-res" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "openai/sora-2-pro-high-res", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.5 } }, { "source": "litellm", "provider": "openai", "model": "sora-2-pro-high-res", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.5 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "openai/sora-2-pro-high-res", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "sora-2-pro-high-res", "mode": "video_generation", "metadata": { "source": "https://platform.openai.com/docs/api-reference/videos" } } ] }, { "id": "openai/text-embedding-004", "provider": "openai", "model": "text-embedding-004", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/text-embedding-004" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "text-embedding-004", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "perCharacter": { "input": 2.5e-8 } } ] }, "metadata": { "modes": [ "embedding" ], "deprecationDate": "2026-01-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "text-embedding-004", "mode": "embedding", "metadata": { "deprecationDate": "2026-01-14", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } } ] }, { "id": "openai/text-embedding-005", "provider": "openai", "model": "text-embedding-005", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/text-embedding-005" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "text-embedding-005", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "perCharacter": { "input": 2.5e-8 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "text-embedding-005", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } } ] }, { "id": "openai/text-embedding-3-large", "provider": "openai", "model": "text-embedding-3-large", "displayName": "text-embedding-3-large", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "openai", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/text-embedding-3-large", "azure/text-embedding-3-large", "openai/text-embedding-3-large", "vercel/openai/text-embedding-3-large", "vercel_ai_gateway/openai/text-embedding-3-large" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 8192, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "text-embedding-3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0 } }, { "source": "models.dev", "provider": "azure", "model": "text-embedding-3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0 } }, { "source": "models.dev", "provider": "openai", "model": "text-embedding-3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/text-embedding-3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0 } }, { "source": "litellm", "provider": "openai", "model": "text-embedding-3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0 }, "extra": { "input_cost_per_token_batches": 6.5e-8, "output_cost_per_token_batches": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0 } } ] }, "metadata": { "displayNames": [ "text-embedding-3-large" ], "families": [ "text-embedding" ], "modes": [ "embedding" ], "knowledgeCutoff": "2024-01", "releaseDate": "2024-01-25", "lastUpdated": "2024-01-25", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-3-large", "modelKey": "text-embedding-3-large", "displayName": "text-embedding-3-large", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-3-large", "modelKey": "text-embedding-3-large", "displayName": "text-embedding-3-large", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "text-embedding-3-large", "modelKey": "text-embedding-3-large", "displayName": "text-embedding-3-large", "family": "text-embedding", "metadata": { "knowledgeCutoff": "2024-01", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/text-embedding-3-large", "modelKey": "openai/text-embedding-3-large", "displayName": "text-embedding-3-large", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/text-embedding-3-large", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-embedding-3-large", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-3-large", "mode": "embedding" } ] }, { "id": "openai/text-embedding-3-small", "provider": "openai", "model": "text-embedding-3-small", "displayName": "text-embedding-3-small", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "github_copilot", "openai", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/text-embedding-3-small", "azure/text-embedding-3-small", "github_copilot/text-embedding-3-small", "openai/text-embedding-3-small", "vercel/openai/text-embedding-3-small", "vercel_ai_gateway/openai/text-embedding-3-small" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 8192, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "text-embedding-3-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } }, { "source": "models.dev", "provider": "azure", "model": "text-embedding-3-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } }, { "source": "models.dev", "provider": "openai", "model": "text-embedding-3-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/text-embedding-3-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/text-embedding-3-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "text-embedding-3-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 }, "extra": { "input_cost_per_token_batches": 1e-8, "output_cost_per_token_batches": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-3-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "displayNames": [ "text-embedding-3-small" ], "families": [ "text-embedding" ], "modes": [ "embedding" ], "knowledgeCutoff": "2024-01", "releaseDate": "2024-01-25", "lastUpdated": "2024-01-25", "deprecationDate": "2026-04-30", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-3-small", "modelKey": "text-embedding-3-small", "displayName": "text-embedding-3-small", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-3-small", "modelKey": "text-embedding-3-small", "displayName": "text-embedding-3-small", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "text-embedding-3-small", "modelKey": "text-embedding-3-small", "displayName": "text-embedding-3-small", "family": "text-embedding", "metadata": { "knowledgeCutoff": "2024-01", "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/text-embedding-3-small", "modelKey": "openai/text-embedding-3-small", "displayName": "text-embedding-3-small", "family": "text-embedding", "metadata": { "lastUpdated": "2024-01-25", "openWeights": false, "releaseDate": "2024-01-25" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/text-embedding-3-small", "mode": "embedding", "metadata": { "deprecationDate": "2026-04-30" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/text-embedding-3-small", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-embedding-3-small", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-3-small", "mode": "embedding" } ] }, { "id": "openai/text-embedding-3-small-inference", "provider": "openai", "model": "text-embedding-3-small-inference", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "github_copilot" ], "aliases": [ "github_copilot/text-embedding-3-small-inference" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/text-embedding-3-small-inference", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/text-embedding-3-small-inference", "mode": "embedding" } ] }, { "id": "openai/text-embedding-ada-002", "provider": "openai", "model": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "family": "text-embedding", "mode": "embedding", "sources": [ "litellm", "models.dev" ], "providers": [ "azure", "azure-cognitive-services", "github_copilot", "openai", "vercel", "vercel_ai_gateway" ], "aliases": [ "azure-cognitive-services/text-embedding-ada-002", "azure/text-embedding-ada-002", "github_copilot/text-embedding-ada-002", "openai/text-embedding-ada-002", "vercel/openai/text-embedding-ada-002", "vercel_ai_gateway/openai/text-embedding-ada-002" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 8192, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "outputVectorSize": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding", "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure-cognitive-services", "model": "text-embedding-ada-002", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "models.dev", "provider": "azure", "model": "text-embedding-ada-002", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "models.dev", "provider": "openai", "model": "text-embedding-ada-002", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "azure", "model": "azure/text-embedding-ada-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "github_copilot", "model": "github_copilot/text-embedding-ada-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "openai", "model": "text-embedding-ada-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-ada-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "text-embedding-ada-002" ], "families": [ "text-embedding" ], "modes": [ "embedding" ], "knowledgeCutoff": "2022-12", "releaseDate": "2022-12-15", "lastUpdated": "2022-12-15", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-ada-002", "modelKey": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "family": "text-embedding", "metadata": { "lastUpdated": "2022-12-15", "openWeights": false, "releaseDate": "2022-12-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "text-embedding-ada-002", "modelKey": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "family": "text-embedding", "metadata": { "lastUpdated": "2022-12-15", "openWeights": false, "releaseDate": "2022-12-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openai", "providerName": "OpenAI", "providerDoc": "https://platform.openai.com/docs/models", "model": "text-embedding-ada-002", "modelKey": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "family": "text-embedding", "metadata": { "knowledgeCutoff": "2022-12", "lastUpdated": "2022-12-15", "openWeights": false, "releaseDate": "2022-12-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "openai/text-embedding-ada-002", "modelKey": "openai/text-embedding-ada-002", "displayName": "text-embedding-ada-002", "family": "text-embedding", "metadata": { "lastUpdated": "2022-12-15", "openWeights": false, "releaseDate": "2022-12-15" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/text-embedding-ada-002", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "github_copilot", "model": "github_copilot/text-embedding-ada-002", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-embedding-ada-002", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/openai/text-embedding-ada-002", "mode": "embedding" } ] }, { "id": "openai/text-embedding-ada-002-v2", "provider": "openai", "model": "text-embedding-ada-002-v2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/text-embedding-ada-002-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "inputTokens": 8191, "maxTokens": 8191, "outputTokens": 8191, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "text-embedding-ada-002-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "extra": { "input_cost_per_token_batches": 5e-8, "output_cost_per_token_batches": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-embedding-ada-002-v2", "mode": "embedding" } ] }, { "id": "openai/text-embedding-large-exp-03-07", "provider": "openai", "model": "text-embedding-large-exp-03-07", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/text-embedding-large-exp-03-07" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "outputVectorSize": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "text-embedding-large-exp-03-07", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "perCharacter": { "input": 2.5e-8 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "text-embedding-large-exp-03-07", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } } ] }, { "id": "openai/text-embedding-preview-0409", "provider": "openai", "model": "text-embedding-preview-0409", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/text-embedding-preview-0409" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 3072, "inputTokens": 3072, "maxTokens": 3072, "outputTokens": 3072, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "text-embedding-preview-0409", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.00625, "output": 0 }, "extra": { "input_cost_per_token_batch_requests": 5e-9 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "text-embedding-preview-0409", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "openai/text-moderation-007", "provider": "openai", "model": "text-moderation-007", "mode": "moderation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/text-moderation-007" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "text-moderation-007", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "moderation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-moderation-007", "mode": "moderation" } ] }, { "id": "openai/text-moderation-latest", "provider": "openai", "model": "text-moderation-latest", "mode": "moderation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/text-moderation-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "text-moderation-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "moderation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-moderation-latest", "mode": "moderation" } ] }, { "id": "openai/text-moderation-stable", "provider": "openai", "model": "text-moderation-stable", "mode": "moderation", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/text-moderation-stable" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "text-moderation-stable", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "moderation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "text-moderation-stable", "mode": "moderation" } ] }, { "id": "openai/tts-1", "provider": "openai", "model": "tts-1", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/tts-1", "openai/tts-1" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/tts-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000015 } }, { "source": "litellm", "provider": "openai", "model": "tts-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000015 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/tts-1", "mode": "audio_speech" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "tts-1", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/tts-1-1106", "provider": "openai", "model": "tts-1-1106", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/tts-1-1106" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "tts-1-1106", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000015 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "tts-1-1106", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/tts-1-hd", "provider": "openai", "model": "tts-1-hd", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/tts-1-hd", "openai/tts-1-hd" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/tts-1-hd", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } }, { "source": "litellm", "provider": "openai", "model": "tts-1-hd", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/tts-1-hd", "mode": "audio_speech" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "tts-1-hd", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/tts-1-hd-1106", "provider": "openai", "model": "tts-1-hd-1106", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "openai" ], "aliases": [ "openai/tts-1-hd-1106" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openai", "model": "tts-1-hd-1106", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "tts-1-hd-1106", "mode": "audio_speech", "metadata": { "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "openai/whisper-1", "provider": "openai", "model": "whisper-1", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "azure", "openai" ], "aliases": [ "azure/whisper-1", "openai/whisper-1" ], "mergedProviderModelRecords": 2, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "azure", "model": "azure/whisper-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0001 }, "extra": { "input_cost_per_second": 0.0001 } }, { "source": "litellm", "provider": "openai", "model": "whisper-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0001 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure", "model": "azure/whisper-1", "mode": "audio_transcription" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openai", "model": "whisper-1", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-base", "provider": "openai", "model": "whisper-base", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper-base" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper-base", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper-base", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-large", "provider": "openai", "model": "whisper-large", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper-large" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper-large", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-large-v3", "provider": "openai", "model": "whisper-large-v3", "displayName": "Whisper", "family": "whisper", "mode": "audio_transcription", "sources": [ "litellm", "models.dev" ], "providers": [ "evroc", "groq", "nearai", "nvidia", "privatemode-ai", "scaleway" ], "aliases": [ "evroc/openai/whisper-large-v3", "groq/whisper-large-v3", "nearai/openai/whisper-large-v3", "nvidia/openai/whisper-large-v3", "privatemode-ai/whisper-large-v3", "scaleway/whisper-large-v3" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 448, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": true, "supports1MContext": false, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "evroc", "model": "openai/whisper-large-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.00236, "output": 0.00236, "outputAudio": 2.36 } }, { "source": "models.dev", "provider": "nearai", "model": "openai/whisper-large-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.01, "output": 0 } }, { "source": "models.dev", "provider": "nvidia", "model": "openai/whisper-large-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "privatemode-ai", "model": "whisper-large-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "scaleway", "model": "whisper-large-v3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.003, "output": 0 } }, { "source": "litellm", "provider": "groq", "model": "groq/whisper-large-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00003083 } } ] }, "metadata": { "displayNames": [ "Whisper", "Whisper 3 Large", "Whisper Large v3", "Whisper large-v3" ], "families": [ "whisper" ], "modes": [ "audio_transcription" ], "knowledgeCutoff": "2023-09", "releaseDate": "2024-10-01", "lastUpdated": "2024-10-01", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "evroc", "providerName": "evroc", "providerApi": "https://models.think.evroc.com/v1", "providerDoc": "https://docs.evroc.com/products/think/overview.html", "model": "openai/whisper-large-v3", "modelKey": "openai/whisper-large-v3", "displayName": "Whisper 3 Large", "family": "whisper", "metadata": { "lastUpdated": "2024-10-01", "openWeights": true, "releaseDate": "2024-10-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "whisper-large-v3", "modelKey": "whisper-large-v3", "displayName": "Whisper", "family": "whisper", "metadata": { "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2023-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "openai/whisper-large-v3", "modelKey": "openai/whisper-large-v3", "displayName": "Whisper Large v3", "family": "whisper", "metadata": { "lastUpdated": "2023-11-06", "openWeights": true, "releaseDate": "2023-11-06" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "openai/whisper-large-v3", "modelKey": "openai/whisper-large-v3", "displayName": "Whisper Large v3", "family": "whisper", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2025-09-05", "openWeights": true, "releaseDate": "2023-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "privatemode-ai", "providerName": "Privatemode AI", "providerApi": "http://localhost:8080/v1", "providerDoc": "https://docs.privatemode.ai/api/overview", "model": "whisper-large-v3", "modelKey": "whisper-large-v3", "displayName": "Whisper large-v3", "family": "whisper", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2023-09-01", "openWeights": true, "releaseDate": "2023-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "whisper-large-v3", "modelKey": "whisper-large-v3", "displayName": "Whisper Large v3", "family": "whisper", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2026-03-17", "openWeights": true, "releaseDate": "2023-09-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/whisper-large-v3", "mode": "audio_transcription" } ] }, { "id": "openai/whisper-large-v3-turbo", "provider": "openai", "model": "whisper-large-v3-turbo", "displayName": "Whisper Large V3 Turbo", "family": "whisper", "mode": "audio_transcription", "sources": [ "litellm", "models.dev" ], "providers": [ "groq", "watsonx" ], "aliases": [ "groq/whisper-large-v3-turbo", "watsonx/whisper-large-v3-turbo" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": true, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "groq", "model": "groq/whisper-large-v3-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.00001111 } }, { "source": "litellm", "provider": "watsonx", "model": "watsonx/whisper-large-v3-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0001 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "displayNames": [ "Whisper Large V3 Turbo" ], "families": [ "whisper" ], "modes": [ "audio_transcription" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10-01", "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "groq", "providerName": "Groq", "providerDoc": "https://console.groq.com/docs/models", "model": "whisper-large-v3-turbo", "modelKey": "whisper-large-v3-turbo", "displayName": "Whisper Large V3 Turbo", "family": "whisper", "metadata": { "lastUpdated": "2024-10-01", "openWeights": true, "releaseDate": "2024-10-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "groq", "model": "groq/whisper-large-v3-turbo", "mode": "audio_transcription" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/whisper-large-v3-turbo", "mode": "audio_transcription", "metadata": { "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-medium", "provider": "openai", "model": "whisper-medium", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper-medium" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper-medium", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-small", "provider": "openai", "model": "whisper-small", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper-small" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper-small", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-tiny", "provider": "openai", "model": "whisper-tiny", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "deepgram" ], "aliases": [ "deepgram/whisper-tiny" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "deepgram", "model": "deepgram/whisper-tiny", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0 }, "extra": { "input_cost_per_second": 0.0001 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepgram", "model": "deepgram/whisper-tiny", "mode": "audio_transcription", "metadata": { "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "source": "https://deepgram.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "openai/whisper-v3", "provider": "openai", "model": "whisper-v3", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/whisper-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/whisper-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/whisper-v3", "mode": "audio_transcription" } ] }, { "id": "openai/whisper-v3-turbo", "provider": "openai", "model": "whisper-v3-turbo", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/whisper-v3-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/whisper-v3-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/whisper-v3-turbo", "mode": "audio_transcription" } ] }, { "id": "opencode-go/mimo-v2-omni", "provider": "opencode-go", "model": "mimo-v2-omni", "displayName": "MiMo V2 Omni", "family": "mimo-v2-omni", "sources": [ "models.dev" ], "providers": [ "opencode-go" ], "aliases": [ "opencode-go/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode-go", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Omni" ], "families": [ "mimo-v2-omni" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo V2 Omni", "family": "mimo-v2-omni", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "opencode-go/mimo-v2-pro", "provider": "opencode-go", "model": "mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo-v2-pro", "sources": [ "models.dev" ], "providers": [ "opencode-go" ], "aliases": [ "opencode-go/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode-go", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo V2 Pro" ], "families": [ "mimo-v2-pro" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo-v2-pro", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "opencode-go/mimo-v2.5", "provider": "opencode-go", "model": "mimo-v2.5", "displayName": "MiMo V2.5", "family": "mimo-v2.5", "sources": [ "models.dev" ], "providers": [ "opencode-go" ], "aliases": [ "opencode-go/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode-go", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5" ], "families": [ "mimo-v2.5" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo V2.5", "family": "mimo-v2.5", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "opencode-go/mimo-v2.5-pro", "provider": "opencode-go", "model": "mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo-v2.5-pro", "sources": [ "models.dev" ], "providers": [ "opencode-go" ], "aliases": [ "opencode-go/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode-go", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0145, "input": 1.74, "output": 3.48 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Pro" ], "families": [ "mimo-v2.5-pro" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo-v2.5-pro", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "opencode/big-pickle", "provider": "opencode", "model": "big-pickle", "displayName": "Big Pickle", "family": "big-pickle", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/big-pickle" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 160000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "big-pickle", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Big Pickle" ], "families": [ "big-pickle" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-10-17", "lastUpdated": "2025-10-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "big-pickle", "modelKey": "big-pickle", "displayName": "Big Pickle", "family": "big-pickle", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-10-17", "openWeights": false, "releaseDate": "2025-10-17" } } ] }, { "id": "opencode/hy3-preview-free", "provider": "opencode", "model": "hy3-preview-free", "displayName": "Hy3 preview Free", "family": "hy3-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/hy3-preview-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "hy3-preview-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Hy3 preview Free" ], "families": [ "hy3-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "hy3-preview-free", "modelKey": "hy3-preview-free", "displayName": "Hy3 preview Free", "family": "hy3-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20" } } ] }, { "id": "opencode/ling-2.6-flash-free", "provider": "opencode", "model": "ling-2.6-flash-free", "displayName": "Ling 2.6 Flash Free", "family": "ling-flash-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/ling-2.6-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262100, "outputTokens": 32800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "ling-2.6-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Ling 2.6 Flash Free" ], "families": [ "ling-flash-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "ling-2.6-flash-free", "modelKey": "ling-2.6-flash-free", "displayName": "Ling 2.6 Flash Free", "family": "ling-flash-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-04-21", "openWeights": true, "releaseDate": "2026-04-21" } } ] }, { "id": "opencode/mimo-v2-flash-free", "provider": "opencode", "model": "mimo-v2-flash-free", "displayName": "MiMo V2 Flash Free", "family": "mimo-flash-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/mimo-v2-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "mimo-v2-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash Free" ], "families": [ "mimo-flash-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2-flash-free", "modelKey": "mimo-v2-flash-free", "displayName": "MiMo V2 Flash Free", "family": "mimo-flash-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "openWeights": true, "releaseDate": "2025-12-16" } } ] }, { "id": "opencode/mimo-v2-omni-free", "provider": "opencode", "model": "mimo-v2-omni-free", "displayName": "MiMo V2 Omni Free", "family": "mimo-omni-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/mimo-v2-omni-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "mimo-v2-omni-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Omni Free" ], "families": [ "mimo-omni-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2-omni-free", "modelKey": "mimo-v2-omni-free", "displayName": "MiMo V2 Omni Free", "family": "mimo-omni-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "opencode/mimo-v2-pro-free", "provider": "opencode", "model": "mimo-v2-pro-free", "displayName": "MiMo V2 Pro Free", "family": "mimo-pro-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/mimo-v2-pro-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "mimo-v2-pro-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Pro Free" ], "families": [ "mimo-pro-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2-pro-free", "modelKey": "mimo-v2-pro-free", "displayName": "MiMo V2 Pro Free", "family": "mimo-pro-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "opencode/mimo-v2.5-free", "provider": "opencode", "model": "mimo-v2.5-free", "displayName": "MiMo V2.5 Free", "family": "mimo-v2.5-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/mimo-v2.5-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "mimo-v2.5-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Free" ], "families": [ "mimo-v2.5-free" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-24", "lastUpdated": "2026-04-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "mimo-v2.5-free", "modelKey": "mimo-v2.5-free", "displayName": "MiMo V2.5 Free", "family": "mimo-v2.5-free", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-24", "openWeights": true, "releaseDate": "2026-04-24" } } ] }, { "id": "opencode/nemotron-3-super-free", "provider": "opencode", "model": "nemotron-3-super-free", "displayName": "Nemotron 3 Super Free", "family": "nemotron-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/nemotron-3-super-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "nemotron-3-super-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super Free" ], "families": [ "nemotron-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "nemotron-3-super-free", "modelKey": "nemotron-3-super-free", "displayName": "Nemotron 3 Super Free", "family": "nemotron-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "opencode/nemotron-3-ultra-free", "provider": "opencode", "model": "nemotron-3-ultra-free", "displayName": "Nemotron 3 Ultra Free", "family": "nemotron-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/nemotron-3-ultra-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "nemotron-3-ultra-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Ultra Free" ], "families": [ "nemotron-free" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "nemotron-3-ultra-free", "modelKey": "nemotron-3-ultra-free", "displayName": "Nemotron 3 Ultra Free", "family": "nemotron-free", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04" } } ] }, { "id": "opencode/north-mini-code-free", "provider": "opencode", "model": "north-mini-code-free", "displayName": "North Mini Code Free", "family": "north-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/north-mini-code-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "north-mini-code-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "North Mini Code Free" ], "families": [ "north-free" ], "knowledgeCutoff": "2025-09-23", "releaseDate": "2026-06-09", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "north-mini-code-free", "modelKey": "north-mini-code-free", "displayName": "North Mini Code Free", "family": "north-free", "metadata": { "knowledgeCutoff": "2025-09-23", "lastUpdated": "2026-06-09", "openWeights": true, "releaseDate": "2026-06-09", "reasoningOptions": [ { "type": "effort", "values": [ "none", "high" ] } ] } } ] }, { "id": "opencode/ring-2.6-1t-free", "provider": "opencode", "model": "ring-2.6-1t-free", "displayName": "Ring 2.6 1T Free", "family": "ring-1t-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/ring-2.6-1t-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 66000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "ring-2.6-1t-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Ring 2.6 1T Free" ], "families": [ "ring-1t-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-05-08", "lastUpdated": "2026-05-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "ring-2.6-1t-free", "modelKey": "ring-2.6-1t-free", "displayName": "Ring 2.6 1T Free", "family": "ring-1t-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-05-08", "openWeights": true, "releaseDate": "2026-05-08" } } ] }, { "id": "opencode/trinity-large-preview-free", "provider": "opencode", "model": "trinity-large-preview-free", "displayName": "Trinity Large Preview", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/trinity-large-preview-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "trinity-large-preview-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Trinity Large Preview" ], "families": [ "trinity" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-01-28", "lastUpdated": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "trinity-large-preview-free", "modelKey": "trinity-large-preview-free", "displayName": "Trinity Large Preview", "family": "trinity", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-28", "openWeights": true, "releaseDate": "2026-01-28" } } ] }, { "id": "openrouter/aion-1.0", "provider": "openrouter", "model": "aion-1.0", "displayName": "Aion-1.0", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/aion-labs/aion-1.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "aion-labs/aion-1.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 4, "output": 8 } }, { "source": "openrouter", "provider": "openrouter", "model": "aion-labs/aion-1.0", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 4, "output": 8 } } ] }, "metadata": { "displayNames": [ "Aion-1.0", "AionLabs: Aion-1.0" ], "releaseDate": "2025-02-04", "lastUpdated": "2025-02-04", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "aion-labs/aion-1.0", "modelKey": "aion-labs/aion-1.0", "displayName": "Aion-1.0", "metadata": { "lastUpdated": "2025-02-04", "openWeights": false, "releaseDate": "2025-02-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "aion-labs/aion-1.0", "displayName": "AionLabs: Aion-1.0", "metadata": { "canonicalSlug": "aion-labs/aion-1.0", "createdAt": "2025-02-04T19:32:37.000Z", "links": { "details": "/api/v1/models/aion-labs/aion-1.0/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/aion-1.0-mini", "provider": "openrouter", "model": "aion-1.0-mini", "displayName": "Aion-1.0-Mini", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/aion-labs/aion-1.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "aion-labs/aion-1.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 1.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "aion-labs/aion-1.0-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "Aion-1.0-Mini", "AionLabs: Aion-1.0-Mini" ], "releaseDate": "2025-02-04", "lastUpdated": "2025-02-04", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "aion-labs/aion-1.0-mini", "modelKey": "aion-labs/aion-1.0-mini", "displayName": "Aion-1.0-Mini", "metadata": { "lastUpdated": "2025-02-04", "openWeights": true, "releaseDate": "2025-02-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "aion-labs/aion-1.0-mini", "displayName": "AionLabs: Aion-1.0-Mini", "metadata": { "canonicalSlug": "aion-labs/aion-1.0-mini", "createdAt": "2025-02-04T19:25:07.000Z", "huggingFaceId": "FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview", "links": { "details": "/api/v1/models/aion-labs/aion-1.0-mini/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/aion-2.0", "provider": "openrouter", "model": "aion-2.0", "displayName": "Aion-2.0", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/aion-labs/aion-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "aion-labs/aion-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.8, "output": 1.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "aion-labs/aion-2.0", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "Aion-2.0", "AionLabs: Aion-2.0" ], "releaseDate": "2026-02-23", "lastUpdated": "2026-02-23", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "aion-labs/aion-2.0", "modelKey": "aion-labs/aion-2.0", "displayName": "Aion-2.0", "metadata": { "lastUpdated": "2026-02-23", "openWeights": false, "releaseDate": "2026-02-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "aion-labs/aion-2.0", "displayName": "AionLabs: Aion-2.0", "metadata": { "canonicalSlug": "aion-labs/aion-2.0-20260223", "createdAt": "2026-02-23T21:15:06.000Z", "links": { "details": "/api/v1/models/aion-labs/aion-2.0-20260223/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/aion-rp-llama-3.1-8b", "provider": "openrouter", "model": "aion-rp-llama-3.1-8b", "displayName": "Aion-RP 1.0 (8B)", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/aion-labs/aion-rp-llama-3.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "aion-labs/aion-rp-llama-3.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "aion-labs/aion-rp-llama-3.1-8b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 1.6 } } ] }, "metadata": { "displayNames": [ "Aion-RP 1.0 (8B)", "AionLabs: Aion-RP 1.0 (8B)" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2025-02-04", "lastUpdated": "2025-02-04", "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "aion-labs/aion-rp-llama-3.1-8b", "modelKey": "aion-labs/aion-rp-llama-3.1-8b", "displayName": "Aion-RP 1.0 (8B)", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2025-02-04", "openWeights": false, "releaseDate": "2025-02-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "aion-labs/aion-rp-llama-3.1-8b", "displayName": "AionLabs: Aion-RP 1.0 (8B)", "metadata": { "canonicalSlug": "aion-labs/aion-rp-llama-3.1-8b", "createdAt": "2025-02-04T19:18:38.000Z", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/aion-labs/aion-rp-llama-3.1-8b/endpoints" }, "supportedParameters": [ "max_tokens", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/auto", "provider": "openrouter", "model": "auto", "displayName": "Auto Router", "family": "auto", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/auto", "openrouter/openrouter/auto" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "file", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openrouter", "model": "openrouter/openrouter/auto", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openrouter/auto", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Auto Router" ], "families": [ "auto" ], "modes": [ "chat" ], "releaseDate": "2023-11-08", "lastUpdated": "2023-11-08", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p", "web_search_options" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/auto", "modelKey": "openrouter/auto", "displayName": "Auto Router", "family": "auto", "metadata": { "lastUpdated": "2023-11-08", "openWeights": false, "releaseDate": "2023-11-08" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openrouter/auto", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/auto", "displayName": "Auto Router", "metadata": { "canonicalSlug": "openrouter/auto", "createdAt": "2023-11-08T00:00:00.000Z", "links": { "details": "/api/v1/models/openrouter/auto/endpoints" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p", "web_search_options" ], "tokenizer": "Router", "topProvider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/bodybuilder", "provider": "openrouter", "model": "bodybuilder", "displayName": "Body Builder (beta)", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bodybuilder", "openrouter/openrouter/bodybuilder" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openrouter", "model": "openrouter/openrouter/bodybuilder", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openrouter/bodybuilder", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Body Builder (beta)" ], "modes": [ "chat" ], "releaseDate": "2025-12-05", "lastUpdated": "2025-12-05", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/bodybuilder", "modelKey": "openrouter/bodybuilder", "displayName": "Body Builder (beta)", "metadata": { "lastUpdated": "2025-12-05", "openWeights": false, "releaseDate": "2025-12-05" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openrouter/bodybuilder", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/bodybuilder", "displayName": "Body Builder (beta)", "metadata": { "canonicalSlug": "openrouter/bodybuilder", "createdAt": "2025-12-05T03:00:53.000Z", "links": { "details": "/api/v1/models/openrouter/bodybuilder/endpoints" }, "tokenizer": "Router", "topProvider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/coder-large", "provider": "openrouter", "model": "coder-large", "displayName": "Coder Large", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/arcee-ai/coder-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "arcee-ai/coder-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 0.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "arcee-ai/coder-large", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.5, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Coder Large", "Coder Large" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-05", "lastUpdated": "2025-05-05", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "arcee-ai/coder-large", "modelKey": "arcee-ai/coder-large", "displayName": "Coder Large", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-05", "openWeights": false, "releaseDate": "2025-05-05" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "arcee-ai/coder-large", "displayName": "Arcee AI: Coder Large", "metadata": { "canonicalSlug": "arcee-ai/coder-large", "createdAt": "2025-05-05T20:57:43.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/arcee-ai/coder-large/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/cogito-v2.1-671b", "provider": "openrouter", "model": "cogito-v2.1-671b", "displayName": "Cogito v2.1 671B", "family": "cogito", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/deepcogito/cogito-v2.1-671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "deepcogito/cogito-v2.1-671b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 1.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "deepcogito/cogito-v2.1-671b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.25, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Cogito v2.1 671B", "Deep Cogito: Cogito v2.1 671B" ], "families": [ "cogito" ], "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "deepcogito/cogito-v2.1-671b", "modelKey": "deepcogito/cogito-v2.1-671b", "displayName": "Cogito v2.1 671B", "family": "cogito", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "deepcogito/cogito-v2.1-671b", "displayName": "Deep Cogito: Cogito v2.1 671B", "metadata": { "canonicalSlug": "deepcogito/cogito-v2.1-671b-20251118", "createdAt": "2025-11-13T22:00:33.000Z", "links": { "details": "/api/v1/models/deepcogito/cogito-v2.1-671b-20251118/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/cydonia-24b-v4.1", "provider": "openrouter", "model": "cydonia-24b-v4.1", "displayName": "Cydonia 24B V4.1", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/thedrummer/cydonia-24b-v4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "thedrummer/cydonia-24b-v4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 0.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "thedrummer/cydonia-24b-v4.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Cydonia 24B V4.1", "TheDrummer: Cydonia 24B V4.1" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2025-09-27", "lastUpdated": "2025-09-27", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "thedrummer/cydonia-24b-v4.1", "modelKey": "thedrummer/cydonia-24b-v4.1", "displayName": "Cydonia 24B V4.1", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2025-09-27", "openWeights": true, "releaseDate": "2025-09-27" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "thedrummer/cydonia-24b-v4.1", "displayName": "TheDrummer: Cydonia 24B V4.1", "metadata": { "canonicalSlug": "thedrummer/cydonia-24b-v4.1", "createdAt": "2025-09-27T00:11:18.000Z", "huggingFaceId": "thedrummer/cydonia-24b-v4.1", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/dolphin-mistral-24b-venice-edition:free", "provider": "openrouter", "model": "dolphin-mistral-24b-venice-edition:free", "displayName": "Uncensored (free)", "family": "mistral", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Uncensored (free)", "Venice: Uncensored (free)" ], "families": [ "mistral" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "modelKey": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "displayName": "Uncensored (free)", "family": "mistral", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2025-07-09", "openWeights": true, "releaseDate": "2025-07-09" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "displayName": "Venice: Uncensored (free)", "metadata": { "canonicalSlug": "venice/uncensored", "createdAt": "2025-07-09T21:02:46.000Z", "huggingFaceId": "cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/venice/uncensored/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/ernie-4.5-vl-424b-a47b", "provider": "openrouter", "model": "ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "family": "ernie", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/baidu/ernie-4.5-vl-424b-a47b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.42, "output": 1.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "baidu/ernie-4.5-vl-424b-a47b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.42, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Baidu: ERNIE 4.5 VL 424B A47B", "ERNIE 4.5 VL 424B A47B" ], "families": [ "ernie" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-06-30", "lastUpdated": "2025-06-30", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "baidu/ernie-4.5-vl-424b-a47b", "modelKey": "baidu/ernie-4.5-vl-424b-a47b", "displayName": "ERNIE 4.5 VL 424B A47B", "family": "ernie", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-06-30", "openWeights": true, "releaseDate": "2025-06-30" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "baidu/ernie-4.5-vl-424b-a47b", "displayName": "Baidu: ERNIE 4.5 VL 424B A47B", "metadata": { "canonicalSlug": "baidu/ernie-4.5-vl-424b-a47b", "createdAt": "2025-06-30T16:28:23.000Z", "huggingFaceId": "baidu/ERNIE-4.5-VL-424B-A47B-PT", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 123000, "max_completion_tokens": 16000, "is_moderated": false } } } ] }, { "id": "openrouter/free", "provider": "openrouter", "model": "free", "displayName": "Free Models Router", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/free", "openrouter/openrouter/free" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 200000, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "openrouter/free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/openrouter/free", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openrouter/free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Free Models Router" ], "modes": [ "chat" ], "releaseDate": "2026-02-01", "lastUpdated": "2026-02-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/free", "modelKey": "openrouter/free", "displayName": "Free Models Router", "metadata": { "lastUpdated": "2026-02-01", "openWeights": false, "releaseDate": "2026-02-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/openrouter/free", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/free", "displayName": "Free Models Router", "metadata": { "canonicalSlug": "openrouter/free", "createdAt": "2026-02-01T03:43:47.000Z", "links": { "details": "/api/v1/models/openrouter/free/endpoints" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_p" ], "tokenizer": "Router", "topProvider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/fusion", "provider": "openrouter", "model": "fusion", "displayName": "Fusion", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/fusion" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "openrouter", "provider": "openrouter", "model": "openrouter/fusion", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Fusion", "OpenRouter: Fusion" ], "releaseDate": "2026-06-13", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/fusion", "modelKey": "openrouter/fusion", "displayName": "Fusion", "metadata": { "lastUpdated": "2026-06-13", "openWeights": false, "releaseDate": "2026-06-13" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/fusion", "displayName": "OpenRouter: Fusion", "metadata": { "canonicalSlug": "openrouter/fusion", "createdAt": "2026-06-13T17:27:27.000Z", "links": { "details": "/api/v1/models/openrouter/fusion/endpoints" }, "tokenizer": "Router", "topProvider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/granite-4.0-h-micro", "provider": "openrouter", "model": "granite-4.0-h-micro", "displayName": "Granite 4.0 Micro", "family": "granite", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/ibm-granite/granite-4.0-h-micro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "ibm-granite/granite-4.0-h-micro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.017, "output": 0.112 } }, { "source": "openrouter", "provider": "openrouter", "model": "ibm-granite/granite-4.0-h-micro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.017, "output": 0.112 } } ] }, "metadata": { "displayNames": [ "Granite 4.0 Micro", "IBM: Granite 4.0 Micro" ], "families": [ "granite" ], "releaseDate": "2025-10-20", "lastUpdated": "2025-10-20", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "ibm-granite/granite-4.0-h-micro", "modelKey": "ibm-granite/granite-4.0-h-micro", "displayName": "Granite 4.0 Micro", "family": "granite", "metadata": { "lastUpdated": "2025-10-20", "openWeights": true, "releaseDate": "2025-10-20" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "ibm-granite/granite-4.0-h-micro", "displayName": "IBM: Granite 4.0 Micro", "metadata": { "canonicalSlug": "ibm-granite/granite-4.0-h-micro", "createdAt": "2025-10-20T02:34:55.000Z", "huggingFaceId": "ibm-granite/granite-4.0-h-micro", "links": { "details": "/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131000, "max_completion_tokens": 131000, "is_moderated": false } } } ] }, { "id": "openrouter/granite-4.1-8b", "provider": "openrouter", "model": "granite-4.1-8b", "displayName": "Granite 4.1 8B", "family": "granite", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/ibm-granite/granite-4.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "ibm-granite/granite-4.1-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "ibm-granite/granite-4.1-8b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.05, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Granite 4.1 8B", "IBM: Granite 4.1 8B" ], "families": [ "granite" ], "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "ibm-granite/granite-4.1-8b", "modelKey": "ibm-granite/granite-4.1-8b", "displayName": "Granite 4.1 8B", "family": "granite", "metadata": { "lastUpdated": "2026-04-30", "openWeights": true, "releaseDate": "2026-04-30" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "ibm-granite/granite-4.1-8b", "displayName": "IBM: Granite 4.1 8B", "metadata": { "canonicalSlug": "ibm-granite/granite-4.1-8b-20260429", "createdAt": "2026-04-30T19:24:31.000Z", "huggingFaceId": "ibm-granite/granite-4.1-8b", "links": { "details": "/api/v1/models/ibm-granite/granite-4.1-8b-20260429/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/hermes-3-llama-3.1-405b", "provider": "openrouter", "model": "hermes-3-llama-3.1-405b", "displayName": "Hermes 3 405B Instruct", "family": "nousresearch", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nousresearch/hermes-3-llama-3.1-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "openrouter", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "Hermes 3 405B Instruct", "Nous: Hermes 3 405B Instruct" ], "families": [ "nousresearch" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-16", "lastUpdated": "2024-08-16", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nousresearch/hermes-3-llama-3.1-405b", "modelKey": "nousresearch/hermes-3-llama-3.1-405b", "displayName": "Hermes 3 405B Instruct", "family": "nousresearch", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-08-16", "openWeights": true, "releaseDate": "2024-08-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b", "displayName": "Nous: Hermes 3 405B Instruct", "metadata": { "canonicalSlug": "nousresearch/hermes-3-llama-3.1-405b", "createdAt": "2024-08-16T00:00:00.000Z", "huggingFaceId": "NousResearch/Hermes-3-Llama-3.1-405B", "instructType": "chatml", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/hermes-3-llama-3.1-405b:free", "provider": "openrouter", "model": "hermes-3-llama-3.1-405b:free", "displayName": "Hermes 3 405B Instruct (free)", "family": "hermes", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nousresearch/hermes-3-llama-3.1-405b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Hermes 3 405B Instruct (free)", "Nous: Hermes 3 405B Instruct (free)" ], "families": [ "hermes" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-16", "lastUpdated": "2024-08-16", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nousresearch/hermes-3-llama-3.1-405b:free", "modelKey": "nousresearch/hermes-3-llama-3.1-405b:free", "displayName": "Hermes 3 405B Instruct (free)", "family": "hermes", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-08-16", "openWeights": true, "releaseDate": "2024-08-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-405b:free", "displayName": "Nous: Hermes 3 405B Instruct (free)", "metadata": { "canonicalSlug": "nousresearch/hermes-3-llama-3.1-405b", "createdAt": "2024-08-16T00:00:00.000Z", "huggingFaceId": "NousResearch/Hermes-3-Llama-3.1-405B", "instructType": "chatml", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/hermes-3-llama-3.1-70b", "provider": "openrouter", "model": "hermes-3-llama-3.1-70b", "displayName": "Hermes 3 70B Instruct", "family": "nousresearch", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nousresearch/hermes-3-llama-3.1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } }, { "source": "openrouter", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-70b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "Hermes 3 70B Instruct", "Nous: Hermes 3 70B Instruct" ], "families": [ "nousresearch" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-18", "lastUpdated": "2024-08-18", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nousresearch/hermes-3-llama-3.1-70b", "modelKey": "nousresearch/hermes-3-llama-3.1-70b", "displayName": "Hermes 3 70B Instruct", "family": "nousresearch", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-08-18", "openWeights": true, "releaseDate": "2024-08-18" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nousresearch/hermes-3-llama-3.1-70b", "displayName": "Nous: Hermes 3 70B Instruct", "metadata": { "canonicalSlug": "nousresearch/hermes-3-llama-3.1-70b", "createdAt": "2024-08-18T00:00:00.000Z", "huggingFaceId": "NousResearch/Hermes-3-Llama-3.1-70B", "instructType": "chatml", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/hermes-4-405b", "provider": "openrouter", "model": "hermes-4-405b", "displayName": "Hermes 4 405B", "family": "hermes", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nousresearch/hermes-4-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nousresearch/hermes-4-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "nousresearch/hermes-4-405b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Hermes 4 405B", "Nous: Hermes 4 405B" ], "families": [ "hermes" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-08-26", "lastUpdated": "2025-08-26", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nousresearch/hermes-4-405b", "modelKey": "nousresearch/hermes-4-405b", "displayName": "Hermes 4 405B", "family": "hermes", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-08-26", "openWeights": true, "releaseDate": "2025-08-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nousresearch/hermes-4-405b", "displayName": "Nous: Hermes 4 405B", "metadata": { "canonicalSlug": "nousresearch/hermes-4-405b", "createdAt": "2025-08-26T19:11:03.000Z", "huggingFaceId": "NousResearch/Hermes-4-405B", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/nousresearch/hermes-4-405b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/hermes-4-70b", "provider": "openrouter", "model": "hermes-4-70b", "displayName": "Hermes 4 70B", "family": "hermes", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nousresearch/hermes-4-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nousresearch/hermes-4-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "nousresearch/hermes-4-70b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Hermes 4 70B", "Nous: Hermes 4 70B" ], "families": [ "hermes" ], "knowledgeCutoff": "2024-08-31", "releaseDate": "2025-08-26", "lastUpdated": "2025-08-26", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nousresearch/hermes-4-70b", "modelKey": "nousresearch/hermes-4-70b", "displayName": "Hermes 4 70B", "family": "hermes", "metadata": { "knowledgeCutoff": "2024-08-31", "lastUpdated": "2025-08-26", "openWeights": true, "releaseDate": "2025-08-26", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nousresearch/hermes-4-70b", "displayName": "Nous: Hermes 4 70B", "metadata": { "canonicalSlug": "nousresearch/hermes-4-70b", "createdAt": "2025-08-26T19:23:02.000Z", "huggingFaceId": "NousResearch/Hermes-4-70B", "knowledgeCutoff": "2024-08-31", "links": { "details": "/api/v1/models/nousresearch/hermes-4-70b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/hunyuan-a13b-instruct", "provider": "openrouter", "model": "hunyuan-a13b-instruct", "displayName": "Hunyuan A13B Instruct", "family": "hunyuan", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/tencent/hunyuan-a13b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "tencent/hunyuan-a13b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } }, { "source": "openrouter", "provider": "openrouter", "model": "tencent/hunyuan-a13b-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "Hunyuan A13B Instruct", "Tencent: Hunyuan A13B Instruct" ], "families": [ "hunyuan" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-07-08", "lastUpdated": "2025-07-08", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "tencent/hunyuan-a13b-instruct", "modelKey": "tencent/hunyuan-a13b-instruct", "displayName": "Hunyuan A13B Instruct", "family": "hunyuan", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-07-08", "openWeights": true, "releaseDate": "2025-07-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "tencent/hunyuan-a13b-instruct", "displayName": "Tencent: Hunyuan A13B Instruct", "metadata": { "canonicalSlug": "tencent/hunyuan-a13b-instruct", "createdAt": "2025-07-08T15:14:24.000Z", "huggingFaceId": "tencent/Hunyuan-A13B-Instruct", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/hy3-preview", "provider": "openrouter", "model": "hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/tencent/hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "tencent/hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.029, "input": 0.066, "output": 0.26 } }, { "source": "openrouter", "provider": "openrouter", "model": "tencent/hy3-preview", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.021, "input": 0.063, "output": 0.21 } } ] }, "metadata": { "displayNames": [ "Hy3 preview", "Tencent: Hy3 preview" ], "families": [ "Hy" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "tencent/hy3-preview", "modelKey": "tencent/hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "metadata": { "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "tencent/hy3-preview", "displayName": "Tencent: Hy3 preview", "metadata": { "canonicalSlug": "tencent/hy3-preview-20260421", "createdAt": "2026-04-22T17:15:50.000Z", "huggingFaceId": "tencent/Hy3-preview", "links": { "details": "/api/v1/models/tencent/hy3-preview-20260421/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "low", "none" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/inflection-3-pi", "provider": "openrouter", "model": "inflection-3-pi", "displayName": "Inflection 3 Pi", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inflection/inflection-3-pi" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inflection/inflection-3-pi", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "inflection/inflection-3-pi", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Inflection 3 Pi", "Inflection: Inflection 3 Pi" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-10-11", "lastUpdated": "2024-10-11", "supportedParameters": [ "max_tokens", "stop", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inflection/inflection-3-pi", "modelKey": "inflection/inflection-3-pi", "displayName": "Inflection 3 Pi", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2024-10-11", "openWeights": false, "releaseDate": "2024-10-11" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inflection/inflection-3-pi", "displayName": "Inflection: Inflection 3 Pi", "metadata": { "canonicalSlug": "inflection/inflection-3-pi", "createdAt": "2024-10-11T00:00:00.000Z", "knowledgeCutoff": "2024-10-31", "links": { "details": "/api/v1/models/inflection/inflection-3-pi/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 8000, "max_completion_tokens": 1024, "is_moderated": false } } } ] }, { "id": "openrouter/inflection-3-productivity", "provider": "openrouter", "model": "inflection-3-productivity", "displayName": "Inflection 3 Productivity", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inflection/inflection-3-productivity" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inflection/inflection-3-productivity", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.5, "output": 10 } }, { "source": "openrouter", "provider": "openrouter", "model": "inflection/inflection-3-productivity", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.5, "output": 10 } } ] }, "metadata": { "displayNames": [ "Inflection 3 Productivity", "Inflection: Inflection 3 Productivity" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2024-10-11", "lastUpdated": "2024-10-11", "supportedParameters": [ "max_tokens", "stop", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inflection/inflection-3-productivity", "modelKey": "inflection/inflection-3-productivity", "displayName": "Inflection 3 Productivity", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2024-10-11", "openWeights": false, "releaseDate": "2024-10-11" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inflection/inflection-3-productivity", "displayName": "Inflection: Inflection 3 Productivity", "metadata": { "canonicalSlug": "inflection/inflection-3-productivity", "createdAt": "2024-10-11T00:00:00.000Z", "knowledgeCutoff": "2024-10-31", "links": { "details": "/api/v1/models/inflection/inflection-3-productivity/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 8000, "max_completion_tokens": 1024, "is_moderated": false } } } ] }, { "id": "openrouter/intellect-3", "provider": "openrouter", "model": "intellect-3", "displayName": "INTELLECT-3", "family": "glm", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/prime-intellect/intellect-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "prime-intellect/intellect-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "prime-intellect/intellect-3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "INTELLECT-3", "Prime Intellect: INTELLECT-3" ], "families": [ "glm" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-11-27", "lastUpdated": "2025-11-27", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "prime-intellect/intellect-3", "modelKey": "prime-intellect/intellect-3", "displayName": "INTELLECT-3", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-11-27", "openWeights": true, "releaseDate": "2025-11-27" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "prime-intellect/intellect-3", "displayName": "Prime Intellect: INTELLECT-3", "metadata": { "canonicalSlug": "prime-intellect/intellect-3-20251126", "createdAt": "2025-11-27T03:02:14.000Z", "huggingFaceId": "PrimeIntellect/INTELLECT-3-FP8", "links": { "details": "/api/v1/models/prime-intellect/intellect-3-20251126/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/kat-coder-pro-v2", "provider": "openrouter", "model": "kat-coder-pro-v2", "displayName": "KAT-Coder-Pro V2", "family": "kat-coder", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/kwaipilot/kat-coder-pro-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "kwaipilot/kat-coder-pro-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "kwaipilot/kat-coder-pro-v2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "KAT-Coder-Pro V2", "Kwaipilot: KAT-Coder-Pro V2" ], "families": [ "kat-coder" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-27", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "kwaipilot/kat-coder-pro-v2", "modelKey": "kwaipilot/kat-coder-pro-v2", "displayName": "KAT-Coder-Pro V2", "family": "kat-coder", "metadata": { "lastUpdated": "2026-03-27", "openWeights": false, "releaseDate": "2026-03-27" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "kwaipilot/kat-coder-pro-v2", "displayName": "Kwaipilot: KAT-Coder-Pro V2", "metadata": { "canonicalSlug": "kwaipilot/kat-coder-pro-v2-20260327", "createdAt": "2026-03-27T22:08:30.000Z", "links": { "details": "/api/v1/models/kwaipilot/kat-coder-pro-v2-20260327/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 80000, "is_moderated": false } } } ] }, { "id": "openrouter/l3-lunaris-8b", "provider": "openrouter", "model": "l3-lunaris-8b", "displayName": "Llama 3 8B Lunaris", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/sao10k/l3-lunaris-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "sao10k/l3-lunaris-8b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.04, "output": 0.05 } }, { "source": "openrouter", "provider": "openrouter", "model": "sao10k/l3-lunaris-8b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.04, "output": 0.05 } } ] }, "metadata": { "displayNames": [ "Llama 3 8B Lunaris", "Sao10K: Llama 3 8B Lunaris" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-13", "lastUpdated": "2024-08-13", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "sao10k/l3-lunaris-8b", "modelKey": "sao10k/l3-lunaris-8b", "displayName": "Llama 3 8B Lunaris", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-08-13", "openWeights": true, "releaseDate": "2024-08-13" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "sao10k/l3-lunaris-8b", "displayName": "Sao10K: Llama 3 8B Lunaris", "metadata": { "canonicalSlug": "sao10k/l3-lunaris-8b", "createdAt": "2024-08-13T00:00:00.000Z", "huggingFaceId": "Sao10K/L3-8B-Lunaris-v1", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/sao10k/l3-lunaris-8b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 8192, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/l3.1-70b-hanami-x1", "provider": "openrouter", "model": "l3.1-70b-hanami-x1", "displayName": "Llama 3.1 70B Hanami x1", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/sao10k/l3.1-70b-hanami-x1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "sao10k/l3.1-70b-hanami-x1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "sao10k/l3.1-70b-hanami-x1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 3 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 70B Hanami x1", "Sao10K: Llama 3.1 70B Hanami x1" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2025-01-08", "lastUpdated": "2025-01-08", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "sao10k/l3.1-70b-hanami-x1", "modelKey": "sao10k/l3.1-70b-hanami-x1", "displayName": "Llama 3.1 70B Hanami x1", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2025-01-08", "openWeights": true, "releaseDate": "2025-01-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "sao10k/l3.1-70b-hanami-x1", "displayName": "Sao10K: Llama 3.1 70B Hanami x1", "metadata": { "canonicalSlug": "sao10k/l3.1-70b-hanami-x1", "createdAt": "2025-01-08T02:20:54.000Z", "huggingFaceId": "Sao10K/L3.1-70B-Hanami-x1", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/sao10k/l3.1-70b-hanami-x1/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 16000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/l3.1-euryale-70b", "provider": "openrouter", "model": "l3.1-euryale-70b", "displayName": "Llama 3.1 Euryale 70B v2.2", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/sao10k/l3.1-euryale-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "sao10k/l3.1-euryale-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 0.85 } }, { "source": "openrouter", "provider": "openrouter", "model": "sao10k/l3.1-euryale-70b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.85, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "Llama 3.1 Euryale 70B v2.2", "Sao10K: Llama 3.1 Euryale 70B v2.2" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-08-28", "lastUpdated": "2024-08-28", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "sao10k/l3.1-euryale-70b", "modelKey": "sao10k/l3.1-euryale-70b", "displayName": "Llama 3.1 Euryale 70B v2.2", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-08-28", "openWeights": true, "releaseDate": "2024-08-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "sao10k/l3.1-euryale-70b", "displayName": "Sao10K: Llama 3.1 Euryale 70B v2.2", "metadata": { "canonicalSlug": "sao10k/l3.1-euryale-70b", "createdAt": "2024-08-28T00:00:00.000Z", "huggingFaceId": "Sao10K/L3.1-70B-Euryale-v2.2", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/sao10k/l3.1-euryale-70b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/l3.3-euryale-70b", "provider": "openrouter", "model": "l3.3-euryale-70b", "displayName": "Llama 3.3 Euryale 70B", "family": "llama", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/sao10k/l3.3-euryale-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "sao10k/l3.3-euryale-70b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.65, "output": 0.75 } }, { "source": "openrouter", "provider": "openrouter", "model": "sao10k/l3.3-euryale-70b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.65, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Llama 3.3 Euryale 70B", "Sao10K: Llama 3.3 Euryale 70B" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12-31", "releaseDate": "2024-12-18", "lastUpdated": "2024-12-18", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "sao10k/l3.3-euryale-70b", "modelKey": "sao10k/l3.3-euryale-70b", "displayName": "Llama 3.3 Euryale 70B", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12-31", "lastUpdated": "2024-12-18", "openWeights": true, "releaseDate": "2024-12-18" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "sao10k/l3.3-euryale-70b", "displayName": "Sao10K: Llama 3.3 Euryale 70B", "metadata": { "canonicalSlug": "sao10k/l3.3-euryale-70b-v2.3", "createdAt": "2024-12-18T15:32:08.000Z", "huggingFaceId": "Sao10K/L3.3-70B-Euryale-v2.3", "instructType": "llama3", "knowledgeCutoff": "2023-12-31", "links": { "details": "/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "tokenizer": "Llama3", "topProvider": { "context_length": 131072, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/laguna-m.1", "provider": "openrouter", "model": "laguna-m.1", "displayName": "Laguna M.1", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/poolside/laguna-m.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "poolside/laguna-m.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.2, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "poolside/laguna-m.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.2, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "Laguna M.1", "Poolside: Laguna M.1" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "poolside/laguna-m.1", "modelKey": "poolside/laguna-m.1", "displayName": "Laguna M.1", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "poolside/laguna-m.1", "displayName": "Poolside: Laguna M.1", "metadata": { "canonicalSlug": "poolside/laguna-m.1-20260312", "createdAt": "2026-04-28T15:01:44.000Z", "huggingFaceId": "poolside/Laguna-M.1", "links": { "details": "/api/v1/models/poolside/laguna-m.1-20260312/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/laguna-m.1:free", "provider": "openrouter", "model": "laguna-m.1:free", "displayName": "Laguna M.1 (free)", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/poolside/laguna-m.1:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "poolside/laguna-m.1:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "poolside/laguna-m.1:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Laguna M.1 (free)", "Poolside: Laguna M.1 (free)" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "poolside/laguna-m.1:free", "modelKey": "poolside/laguna-m.1:free", "displayName": "Laguna M.1 (free)", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "poolside/laguna-m.1:free", "displayName": "Poolside: Laguna M.1 (free)", "metadata": { "canonicalSlug": "poolside/laguna-m.1-20260312", "createdAt": "2026-04-28T15:01:44.000Z", "huggingFaceId": "poolside/Laguna-M.1", "links": { "details": "/api/v1/models/poolside/laguna-m.1-20260312/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/laguna-xs.2", "provider": "openrouter", "model": "laguna-xs.2", "displayName": "Laguna XS.2", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/poolside/laguna-xs.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "poolside/laguna-xs.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.1, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "poolside/laguna-xs.2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Laguna XS.2", "Poolside: Laguna XS.2" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "poolside/laguna-xs.2", "modelKey": "poolside/laguna-xs.2", "displayName": "Laguna XS.2", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "poolside/laguna-xs.2", "displayName": "Poolside: Laguna XS.2", "metadata": { "canonicalSlug": "poolside/laguna-xs.2-20260421", "createdAt": "2026-04-28T15:20:04.000Z", "huggingFaceId": "poolside/Laguna-XS.2", "links": { "details": "/api/v1/models/poolside/laguna-xs.2-20260421/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/laguna-xs.2:free", "provider": "openrouter", "model": "laguna-xs.2:free", "displayName": "Laguna XS.2 (free)", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/poolside/laguna-xs.2:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "poolside/laguna-xs.2:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "poolside/laguna-xs.2:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Laguna XS.2 (free)", "Poolside: Laguna XS.2 (free)" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "poolside/laguna-xs.2:free", "modelKey": "poolside/laguna-xs.2:free", "displayName": "Laguna XS.2 (free)", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "poolside/laguna-xs.2:free", "displayName": "Poolside: Laguna XS.2 (free)", "metadata": { "canonicalSlug": "poolside/laguna-xs.2-20260421", "createdAt": "2026-04-28T15:20:04.000Z", "huggingFaceId": "poolside/Laguna-XS.2", "links": { "details": "/api/v1/models/poolside/laguna-xs.2-20260421/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/lfm-2-24b-a2b", "provider": "openrouter", "model": "lfm-2-24b-a2b", "displayName": "LFM2-24B-A2B", "family": "liquid", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/liquid/lfm-2-24b-a2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "liquid/lfm-2-24b-a2b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.12 } }, { "source": "openrouter", "provider": "openrouter", "model": "liquid/lfm-2-24b-a2b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "LFM2-24B-A2B", "LiquidAI: LFM2-24B-A2B" ], "families": [ "liquid" ], "releaseDate": "2026-02-25", "lastUpdated": "2026-02-25", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "liquid/lfm-2-24b-a2b", "modelKey": "liquid/lfm-2-24b-a2b", "displayName": "LFM2-24B-A2B", "family": "liquid", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2026-02-25" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "liquid/lfm-2-24b-a2b", "displayName": "LiquidAI: LFM2-24B-A2B", "metadata": { "canonicalSlug": "liquid/lfm-2-24b-a2b-20260224", "createdAt": "2026-02-25T19:45:11.000Z", "huggingFaceId": "LiquidAI/LFM2-24B-A2B", "links": { "details": "/api/v1/models/liquid/lfm-2-24b-a2b-20260224/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/lfm-2.5-1.2b-instruct:free", "provider": "openrouter", "model": "lfm-2.5-1.2b-instruct:free", "displayName": "LFM2.5-1.2B-Instruct (free)", "family": "liquid", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/liquid/lfm-2.5-1.2b-instruct:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-instruct:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-instruct:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "LFM2.5-1.2B-Instruct (free)", "LiquidAI: LFM2.5-1.2B-Instruct (free)" ], "families": [ "liquid" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-01-20", "lastUpdated": "2026-01-20", "supportedParameters": [ "frequency_penalty", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "liquid/lfm-2.5-1.2b-instruct:free", "modelKey": "liquid/lfm-2.5-1.2b-instruct:free", "displayName": "LFM2.5-1.2B-Instruct (free)", "family": "liquid", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-20", "openWeights": true, "releaseDate": "2026-01-20" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-instruct:free", "displayName": "LiquidAI: LFM2.5-1.2B-Instruct (free)", "metadata": { "canonicalSlug": "liquid/lfm-2.5-1.2b-instruct-20260120", "createdAt": "2026-01-20T16:45:21.000Z", "huggingFaceId": "LiquidAI/LFM2.5-1.2B-Instruct", "links": { "details": "/api/v1/models/liquid/lfm-2.5-1.2b-instruct-20260120/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/lfm-2.5-1.2b-thinking:free", "provider": "openrouter", "model": "lfm-2.5-1.2b-thinking:free", "displayName": "LFM2.5-1.2B-Thinking (free)", "family": "liquid", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/liquid/lfm-2.5-1.2b-thinking:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-thinking:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-thinking:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "LFM2.5-1.2B-Thinking (free)", "LiquidAI: LFM2.5-1.2B-Thinking (free)" ], "families": [ "liquid" ], "knowledgeCutoff": "2025-06", "releaseDate": "2026-01-20", "lastUpdated": "2026-01-20", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "liquid/lfm-2.5-1.2b-thinking:free", "modelKey": "liquid/lfm-2.5-1.2b-thinking:free", "displayName": "LFM2.5-1.2B-Thinking (free)", "family": "liquid", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-20", "openWeights": true, "releaseDate": "2026-01-20" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "liquid/lfm-2.5-1.2b-thinking:free", "displayName": "LiquidAI: LFM2.5-1.2B-Thinking (free)", "metadata": { "canonicalSlug": "liquid/lfm-2.5-1.2b-thinking-20260120", "createdAt": "2026-01-20T16:45:27.000Z", "huggingFaceId": "LiquidAI/LFM2.5-1.2B-Thinking", "links": { "details": "/api/v1/models/liquid/lfm-2.5-1.2b-thinking-20260120/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/ling-2.6-1t", "provider": "openrouter", "model": "ling-2.6-1t", "displayName": "Ling-2.6-1T", "family": "ling", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inclusionai/ling-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inclusionai/ling-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.075, "output": 0.625 } }, { "source": "openrouter", "provider": "openrouter", "model": "inclusionai/ling-2.6-1t", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.015, "input": 0.075, "output": 0.625 } } ] }, "metadata": { "displayNames": [ "Ling-2.6-1T", "inclusionAI: Ling-2.6-1T" ], "families": [ "ling" ], "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inclusionai/ling-2.6-1t", "modelKey": "inclusionai/ling-2.6-1t", "displayName": "Ling-2.6-1T", "family": "ling", "metadata": { "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inclusionai/ling-2.6-1t", "displayName": "inclusionAI: Ling-2.6-1T", "metadata": { "canonicalSlug": "inclusionai/ling-2.6-1t-20260423", "createdAt": "2026-04-23T12:43:58.000Z", "links": { "details": "/api/v1/models/inclusionai/ling-2.6-1t-20260423/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/ling-2.6-flash", "provider": "openrouter", "model": "ling-2.6-flash", "displayName": "Ling-2.6-flash", "family": "ling", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inclusionai/ling-2.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inclusionai/ling-2.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.002, "input": 0.01, "output": 0.03 } }, { "source": "openrouter", "provider": "openrouter", "model": "inclusionai/ling-2.6-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.002, "input": 0.01, "output": 0.03 } } ] }, "metadata": { "displayNames": [ "Ling-2.6-flash", "inclusionAI: Ling-2.6-flash" ], "families": [ "ling" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inclusionai/ling-2.6-flash", "modelKey": "inclusionai/ling-2.6-flash", "displayName": "Ling-2.6-flash", "family": "ling", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inclusionai/ling-2.6-flash", "displayName": "inclusionAI: Ling-2.6-flash", "metadata": { "canonicalSlug": "inclusionai/ling-2.6-flash-20260421", "createdAt": "2026-04-21T18:24:46.000Z", "links": { "details": "/api/v1/models/inclusionai/ling-2.6-flash-20260421/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/magnum-v4-72b", "provider": "openrouter", "model": "magnum-v4-72b", "displayName": "Magnum v4 72B", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/anthracite-org/magnum-v4-72b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "anthracite-org/magnum-v4-72b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 5 } }, { "source": "openrouter", "provider": "openrouter", "model": "anthracite-org/magnum-v4-72b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 5 } } ] }, "metadata": { "displayNames": [ "Magnum v4 72B" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "anthracite-org/magnum-v4-72b", "modelKey": "anthracite-org/magnum-v4-72b", "displayName": "Magnum v4 72B", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2024-10-22", "openWeights": true, "releaseDate": "2024-10-22" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "anthracite-org/magnum-v4-72b", "displayName": "Magnum v4 72B", "metadata": { "canonicalSlug": "anthracite-org/magnum-v4-72b", "createdAt": "2024-10-22T00:00:00.000Z", "huggingFaceId": "anthracite-org/magnum-v4-72b", "instructType": "chatml", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/anthracite-org/magnum-v4-72b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 16384, "max_completion_tokens": 2048, "is_moderated": false } } } ] }, { "id": "openrouter/mercury-2", "provider": "openrouter", "model": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inception/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inception/mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } }, { "source": "openrouter", "provider": "openrouter", "model": "inception/mercury-2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Inception: Mercury 2", "Mercury 2" ], "families": [ "mercury" ], "releaseDate": "2026-03-04", "lastUpdated": "2026-03-04", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inception/mercury-2", "modelKey": "inception/mercury-2", "displayName": "Mercury 2", "family": "mercury", "metadata": { "lastUpdated": "2026-03-04", "openWeights": false, "releaseDate": "2026-03-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inception/mercury-2", "displayName": "Inception: Mercury 2", "metadata": { "canonicalSlug": "inception/mercury-2-20260304", "createdAt": "2026-03-04T14:57:55.000Z", "links": { "details": "/api/v1/models/inception/mercury-2-20260304/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "none" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": 50000, "is_moderated": false } } } ] }, { "id": "openrouter/mimo-v2-flash", "provider": "openrouter", "model": "mimo-v2-flash", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 262144, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2-flash", "mode": "chat" } ] }, { "id": "openrouter/mimo-v2.5", "provider": "openrouter", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 0, "input": 0.4, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5", "Xiaomi: MiMo-V2.5" ], "families": [ "mimo" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "xiaomi/mimo-v2.5", "modelKey": "xiaomi/mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2.5", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "xiaomi/mimo-v2.5", "displayName": "Xiaomi: MiMo-V2.5", "metadata": { "canonicalSlug": "xiaomi/mimo-v2.5-20260422", "createdAt": "2026-04-22T16:11:09.000Z", "huggingFaceId": "XiaomiMiMo/MiMo-V2.5", "links": { "details": "/api/v1/models/xiaomi/mimo-v2.5-20260422/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048576, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/mimo-v2.5-pro", "provider": "openrouter", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "inputTokens": 1048576, "maxTokens": 16384, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": false, "parallelFunctionCalling": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0036, "input": 0.435, "output": 0.87 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.0036, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro", "Xiaomi: MiMo-V2.5-Pro" ], "families": [ "mimo" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "xiaomi/mimo-v2.5-pro", "modelKey": "xiaomi/mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/xiaomi/mimo-v2.5-pro", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "xiaomi/mimo-v2.5-pro", "displayName": "Xiaomi: MiMo-V2.5-Pro", "metadata": { "canonicalSlug": "xiaomi/mimo-v2.5-pro-20260422", "createdAt": "2026-04-22T16:11:13.000Z", "huggingFaceId": "XiaomiMiMo/MiMo-V2.5-Pro", "links": { "details": "/api/v1/models/xiaomi/mimo-v2.5-pro-20260422/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048576, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/morph-v3-fast", "provider": "openrouter", "model": "morph-v3-fast", "displayName": "Morph V3 Fast", "family": "morph", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/morph/morph-v3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 81920, "outputTokens": 38000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "morph/morph-v3-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "morph/morph-v3-fast", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Morph V3 Fast", "Morph: Morph V3 Fast" ], "families": [ "morph" ], "releaseDate": "2025-07-07", "lastUpdated": "2025-07-07", "supportedParameters": [ "max_tokens", "stop", "temperature" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "morph/morph-v3-fast", "modelKey": "morph/morph-v3-fast", "displayName": "Morph V3 Fast", "family": "morph", "metadata": { "lastUpdated": "2025-07-07", "openWeights": false, "releaseDate": "2025-07-07" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "morph/morph-v3-fast", "displayName": "Morph: Morph V3 Fast", "metadata": { "canonicalSlug": "morph/morph-v3-fast", "createdAt": "2025-07-07T17:40:02.000Z", "links": { "details": "/api/v1/models/morph/morph-v3-fast/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature" ], "tokenizer": "Other", "topProvider": { "context_length": 81920, "max_completion_tokens": 38000, "is_moderated": false } } } ] }, { "id": "openrouter/morph-v3-large", "provider": "openrouter", "model": "morph-v3-large", "displayName": "Morph V3 Large", "family": "morph", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/morph/morph-v3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "morph/morph-v3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 1.9 } }, { "source": "openrouter", "provider": "openrouter", "model": "morph/morph-v3-large", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Morph V3 Large", "Morph: Morph V3 Large" ], "families": [ "morph" ], "releaseDate": "2025-07-07", "lastUpdated": "2025-07-07", "supportedParameters": [ "logprobs", "max_tokens", "response_format", "stop", "structured_outputs", "temperature", "top_logprobs" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "morph/morph-v3-large", "modelKey": "morph/morph-v3-large", "displayName": "Morph V3 Large", "family": "morph", "metadata": { "lastUpdated": "2025-07-07", "openWeights": false, "releaseDate": "2025-07-07" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "morph/morph-v3-large", "displayName": "Morph: Morph V3 Large", "metadata": { "canonicalSlug": "morph/morph-v3-large", "createdAt": "2025-07-07T17:54:18.000Z", "links": { "details": "/api/v1/models/morph/morph-v3-large/endpoints" }, "supportedParameters": [ "logprobs", "max_tokens", "response_format", "stop", "structured_outputs", "temperature", "top_logprobs" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/mythomax-l2-13b", "provider": "openrouter", "model": "mythomax-l2-13b", "displayName": "MythoMax 13B", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/gryphe/mythomax-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "gryphe/mythomax-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.06 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/gryphe/mythomax-l2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.875, "output": 1.875 } }, { "source": "openrouter", "provider": "openrouter", "model": "gryphe/mythomax-l2-13b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.06 } } ] }, "metadata": { "displayNames": [ "MythoMax 13B" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-07-02", "lastUpdated": "2023-07-02", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "gryphe/mythomax-l2-13b", "modelKey": "gryphe/mythomax-l2-13b", "displayName": "MythoMax 13B", "metadata": { "knowledgeCutoff": "2023-06-30", "lastUpdated": "2023-07-02", "openWeights": true, "releaseDate": "2023-07-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/gryphe/mythomax-l2-13b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "gryphe/mythomax-l2-13b", "displayName": "MythoMax 13B", "metadata": { "canonicalSlug": "gryphe/mythomax-l2-13b", "createdAt": "2023-07-02T00:00:00.000Z", "huggingFaceId": "Gryphe/MythoMax-L2-13b", "instructType": "alpaca", "knowledgeCutoff": "2023-06-30", "links": { "details": "/api/v1/models/gryphe/mythomax-l2-13b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama2", "topProvider": { "context_length": 4096, "max_completion_tokens": 4096, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-nano-30b-a3b", "provider": "openrouter", "model": "nemotron-3-nano-30b-a3b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 228000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Nano 30B A3B", "Nemotron 3 Nano 30B A3B" ], "families": [ "nemotron" ], "releaseDate": "2025-12-15", "lastUpdated": "2025-12-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-nano-30b-a3b", "modelKey": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "metadata": { "lastUpdated": "2025-12-15", "openWeights": true, "releaseDate": "2025-12-15" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "NVIDIA: Nemotron 3 Nano 30B A3B", "metadata": { "canonicalSlug": "nvidia/nemotron-3-nano-30b-a3b", "createdAt": "2025-12-14T16:54:35.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 228000, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-nano-30b-a3b:free", "provider": "openrouter", "model": "nemotron-3-nano-30b-a3b:free", "displayName": "Nemotron 3 Nano 30B A3B (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-nano-30b-a3b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Nano 30B A3B (free)", "Nemotron 3 Nano 30B A3B (free)" ], "families": [ "nemotron" ], "releaseDate": "2025-12-15", "lastUpdated": "2025-12-15", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-nano-30b-a3b:free", "modelKey": "nvidia/nemotron-3-nano-30b-a3b:free", "displayName": "Nemotron 3 Nano 30B A3B (free)", "family": "nemotron", "metadata": { "lastUpdated": "2025-12-15", "openWeights": true, "releaseDate": "2025-12-15" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-30b-a3b:free", "displayName": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-3-nano-30b-a3b", "createdAt": "2025-12-14T16:54:35.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-nano-omni-30b-a3b-reasoning:free", "provider": "openrouter", "model": "nemotron-3-nano-omni-30b-a3b-reasoning:free", "displayName": "Nemotron 3 Nano Omni (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Nano Omni (free)", "Nemotron 3 Nano Omni (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "modelKey": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "displayName": "Nemotron 3 Nano Omni (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "displayName": "NVIDIA: Nemotron 3 Nano Omni (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428", "createdAt": "2026-04-28T16:18:15.000Z", "huggingFaceId": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supports_max_tokens": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-super-120b-a12b", "provider": "openrouter", "model": "nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B A12B", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.45 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.09, "output": 0.45 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Super", "Nemotron 3 Super 120B A12B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B A12B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b", "displayName": "NVIDIA: Nemotron 3 Super", "metadata": { "canonicalSlug": "nvidia/nemotron-3-super-120b-a12b-20230311", "createdAt": "2026-03-11T16:07:19.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "links": { "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supports_max_tokens": true, "supported_efforts": [ "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-super-120b-a12b:free", "provider": "openrouter", "model": "nemotron-3-super-120b-a12b:free", "displayName": "Nemotron 3 Super (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-super-120b-a12b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Super (free)", "Nemotron 3 Super (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-super-120b-a12b:free", "modelKey": "nvidia/nemotron-3-super-120b-a12b:free", "displayName": "Nemotron 3 Super (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-super-120b-a12b:free", "displayName": "NVIDIA: Nemotron 3 Super (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-3-super-120b-a12b-20230311", "createdAt": "2026-03-11T16:07:19.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "links": { "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supports_max_tokens": true, "supported_efforts": [ "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-ultra-550b-a55b", "provider": "openrouter", "model": "nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-ultra-550b-a55b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.5, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.5, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Ultra", "Nemotron 3 Ultra 550B A55B" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-ultra-550b-a55b", "modelKey": "nvidia/nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b", "displayName": "NVIDIA: Nemotron 3 Ultra", "metadata": { "canonicalSlug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "createdAt": "2026-06-04T05:33:28.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supports_max_tokens": true, "supported_efforts": [ "high", "medium" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3-ultra-550b-a55b:free", "provider": "openrouter", "model": "nemotron-3-ultra-550b-a55b:free", "displayName": "Nemotron 3 Ultra (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3 Ultra (free)", "Nemotron 3 Ultra (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3-ultra-550b-a55b:free", "modelKey": "nvidia/nemotron-3-ultra-550b-a55b:free", "displayName": "Nemotron 3 Ultra (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3-ultra-550b-a55b:free", "displayName": "NVIDIA: Nemotron 3 Ultra (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "createdAt": "2026-06-04T05:33:28.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supports_max_tokens": true, "supported_efforts": [ "high", "medium" ], "default_effort": "high" }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-3.5-content-safety:free", "provider": "openrouter", "model": "nemotron-3.5-content-safety:free", "displayName": "Nemotron 3.5 Content Safety (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-3.5-content-safety:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-3.5-content-safety:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-3.5-content-safety:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron 3.5 Content Safety (free)", "Nemotron 3.5 Content Safety (free)" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-3.5-content-safety:free", "modelKey": "nvidia/nemotron-3.5-content-safety:free", "displayName": "Nemotron 3.5 Content Safety (free)", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-3.5-content-safety:free", "displayName": "NVIDIA: Nemotron 3.5 Content Safety (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-3.5-content-safety-20260604", "createdAt": "2026-06-04T14:04:24.000Z", "huggingFaceId": "nvidia/Nemotron-3.5-Content-Safety", "links": { "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-nano-12b-v2-vl:free", "provider": "openrouter", "model": "nemotron-nano-12b-v2-vl:free", "displayName": "Nemotron Nano 12B 2 VL (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-nano-12b-v2-vl:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-nano-12b-v2-vl:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-nano-12b-v2-vl:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron Nano 12B 2 VL (free)", "Nemotron Nano 12B 2 VL (free)" ], "families": [ "nemotron" ], "releaseDate": "2025-10-28", "lastUpdated": "2025-10-28", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-nano-12b-v2-vl:free", "modelKey": "nvidia/nemotron-nano-12b-v2-vl:free", "displayName": "Nemotron Nano 12B 2 VL (free)", "family": "nemotron", "metadata": { "lastUpdated": "2025-10-28", "openWeights": true, "releaseDate": "2025-10-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-nano-12b-v2-vl:free", "displayName": "NVIDIA: Nemotron Nano 12B 2 VL (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-nano-12b-v2-vl", "createdAt": "2025-10-28T18:19:25.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "links": { "details": "/api/v1/models/nvidia/nemotron-nano-12b-v2-vl/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "seed", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openrouter/nemotron-nano-9b-v2:free", "provider": "openrouter", "model": "nemotron-nano-9b-v2:free", "displayName": "Nemotron Nano 9B V2 (free)", "family": "nemotron", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nvidia/nemotron-nano-9b-v2:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nvidia/nemotron-nano-9b-v2:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nvidia/nemotron-nano-9b-v2:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "NVIDIA: Nemotron Nano 9B V2 (free)", "Nemotron Nano 9B V2 (free)" ], "families": [ "nemotron" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-08-18", "lastUpdated": "2025-08-18", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nvidia/nemotron-nano-9b-v2:free", "modelKey": "nvidia/nemotron-nano-9b-v2:free", "displayName": "Nemotron Nano 9B V2 (free)", "family": "nemotron", "metadata": { "lastUpdated": "2025-08-18", "openWeights": true, "releaseDate": "2025-08-18" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nvidia/nemotron-nano-9b-v2:free", "displayName": "NVIDIA: Nemotron Nano 9B V2 (free)", "metadata": { "canonicalSlug": "nvidia/nemotron-nano-9b-v2", "createdAt": "2025-09-05T21:13:27.000Z", "huggingFaceId": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/nvidia/nemotron-nano-9b-v2/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/nex-n2-pro:free", "provider": "openrouter", "model": "nex-n2-pro:free", "displayName": "Nex-N2-Pro (free)", "family": "agi", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/nex-agi/nex-n2-pro:free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "nex-agi/nex-n2-pro:free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "nex-agi/nex-n2-pro:free", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Nex AGI: Nex-N2-Pro (free)", "Nex-N2-Pro (free)" ], "families": [ "agi" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "nex-agi/nex-n2-pro:free", "modelKey": "nex-agi/nex-n2-pro:free", "displayName": "Nex-N2-Pro (free)", "family": "agi", "metadata": { "lastUpdated": "2026-06-08", "openWeights": true, "releaseDate": "2026-06-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "nex-agi/nex-n2-pro:free", "displayName": "Nex AGI: Nex-N2-Pro (free)", "metadata": { "canonicalSlug": "nex-agi/nex-n2-pro", "createdAt": "2026-06-08T16:45:40.000Z", "expirationDate": "2026-06-22", "huggingFaceId": "nex-agi/Nex-N2-Pro", "links": { "details": "/api/v1/models/nex-agi/nex-n2-pro/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Qwen3", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "openrouter/olmo-3-32b-think", "provider": "openrouter", "model": "olmo-3-32b-think", "displayName": "Olmo 3 32B Think", "family": "allenai", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/allenai/olmo-3-32b-think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "allenai/olmo-3-32b-think", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "allenai/olmo-3-32b-think", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "AllenAI: Olmo 3 32B Think", "Olmo 3 32B Think" ], "families": [ "allenai" ], "releaseDate": "2025-11-21", "lastUpdated": "2025-11-21", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "allenai/olmo-3-32b-think", "modelKey": "allenai/olmo-3-32b-think", "displayName": "Olmo 3 32B Think", "family": "allenai", "metadata": { "lastUpdated": "2025-11-21", "openWeights": true, "releaseDate": "2025-11-21" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "allenai/olmo-3-32b-think", "displayName": "AllenAI: Olmo 3 32B Think", "metadata": { "canonicalSlug": "allenai/olmo-3-32b-think-20251121", "createdAt": "2025-11-21T20:51:16.000Z", "huggingFaceId": "allenai/Olmo-3-32B-Think", "links": { "details": "/api/v1/models/allenai/olmo-3-32b-think-20251121/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 65536, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openrouter/owl-alpha", "provider": "openrouter", "model": "owl-alpha", "displayName": "Owl Alpha", "family": "alpha", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/owl-alpha" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048756, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "openrouter/owl-alpha", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "openrouter/owl-alpha", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Owl Alpha" ], "families": [ "alpha" ], "statuses": [ "alpha" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/owl-alpha", "modelKey": "openrouter/owl-alpha", "displayName": "Owl Alpha", "family": "alpha", "status": "alpha", "metadata": { "lastUpdated": "2026-04-28", "openWeights": false, "releaseDate": "2026-04-28" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/owl-alpha", "displayName": "Owl Alpha", "metadata": { "canonicalSlug": "openrouter/owl-alpha", "createdAt": "2026-04-28T17:49:49.000Z", "links": { "details": "/api/v1/models/openrouter/owl-alpha/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048756, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "openrouter/palmyra-x5", "provider": "openrouter", "model": "palmyra-x5", "displayName": "Palmyra X5", "family": "palmyra", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/writer/palmyra-x5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1040000, "outputTokens": 8192, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "writer/palmyra-x5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 6 } }, { "source": "openrouter", "provider": "openrouter", "model": "writer/palmyra-x5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 6 } } ] }, "metadata": { "displayNames": [ "Palmyra X5", "Writer: Palmyra X5" ], "families": [ "palmyra" ], "releaseDate": "2026-01-21", "lastUpdated": "2026-01-21", "supportedParameters": [ "max_tokens", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "writer/palmyra-x5", "modelKey": "writer/palmyra-x5", "displayName": "Palmyra X5", "family": "palmyra", "metadata": { "lastUpdated": "2026-01-21", "openWeights": false, "releaseDate": "2026-01-21" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "writer/palmyra-x5", "displayName": "Writer: Palmyra X5", "metadata": { "canonicalSlug": "writer/palmyra-x5-20250428", "createdAt": "2026-01-21T13:57:03.000Z", "links": { "details": "/api/v1/models/writer/palmyra-x5-20250428/endpoints" }, "supportedParameters": [ "max_tokens", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1040000, "max_completion_tokens": 8192, "is_moderated": true } } } ] }, { "id": "openrouter/pareto-code", "provider": "openrouter", "model": "pareto-code", "displayName": "Pareto Code Router", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/pareto-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 200000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "openrouter", "provider": "openrouter", "model": "openrouter/pareto-code", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "displayNames": [ "Pareto Code Router" ], "releaseDate": "2026-04-21", "lastUpdated": "2026-04-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "openrouter/pareto-code", "modelKey": "openrouter/pareto-code", "displayName": "Pareto Code Router", "metadata": { "lastUpdated": "2026-04-21", "openWeights": false, "releaseDate": "2026-04-21" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "openrouter/pareto-code", "displayName": "Pareto Code Router", "metadata": { "canonicalSlug": "openrouter/pareto-code", "createdAt": "2026-04-21T05:05:00.000Z", "links": { "details": "/api/v1/models/openrouter/pareto-code/endpoints" }, "tokenizer": "Router", "topProvider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/perceptron-mk1", "provider": "openrouter", "model": "perceptron-mk1", "displayName": "Perceptron Mk1", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/perceptron/perceptron-mk1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "perceptron/perceptron-mk1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 1.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "perceptron/perceptron-mk1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Perceptron Mk1", "Perceptron: Perceptron Mk1" ], "releaseDate": "2026-05-12", "lastUpdated": "2026-05-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perceptron/perceptron-mk1", "modelKey": "perceptron/perceptron-mk1", "displayName": "Perceptron Mk1", "metadata": { "lastUpdated": "2026-05-12", "openWeights": false, "releaseDate": "2026-05-12" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perceptron/perceptron-mk1", "displayName": "Perceptron: Perceptron Mk1", "metadata": { "canonicalSlug": "perceptron/perceptron-mk1-20260512", "createdAt": "2026-05-12T14:43:49.000Z", "links": { "details": "/api/v1/models/perceptron/perceptron-mk1-20260512/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": 8192, "is_moderated": false } } } ] }, { "id": "openrouter/phi-4", "provider": "openrouter", "model": "phi-4", "displayName": "Phi 4", "family": "phi", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/microsoft/phi-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "microsoft/phi-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.065, "output": 0.14 } }, { "source": "openrouter", "provider": "openrouter", "model": "microsoft/phi-4", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.065, "output": 0.14 } } ] }, "metadata": { "displayNames": [ "Microsoft: Phi 4", "Phi 4" ], "families": [ "phi" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-01-10", "lastUpdated": "2025-01-10", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "microsoft/phi-4", "modelKey": "microsoft/phi-4", "displayName": "Phi 4", "family": "phi", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-01-10", "openWeights": true, "releaseDate": "2025-01-10" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "microsoft/phi-4", "displayName": "Microsoft: Phi 4", "metadata": { "canonicalSlug": "microsoft/phi-4", "createdAt": "2025-01-10T06:17:52.000Z", "huggingFaceId": "microsoft/phi-4", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/microsoft/phi-4/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 16384, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/phi-4-mini-instruct", "provider": "openrouter", "model": "phi-4-mini-instruct", "displayName": "Phi 4 Mini Instruct", "family": "phi", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/microsoft/phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "microsoft/phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.08, "output": 0.35 } }, { "source": "openrouter", "provider": "openrouter", "model": "microsoft/phi-4-mini-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "input": 0.08, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "Microsoft: Phi 4 Mini Instruct", "Phi 4 Mini Instruct" ], "families": [ "phi" ], "releaseDate": "2025-10-17", "lastUpdated": "2025-10-17", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "microsoft/phi-4-mini-instruct", "modelKey": "microsoft/phi-4-mini-instruct", "displayName": "Phi 4 Mini Instruct", "family": "phi", "metadata": { "lastUpdated": "2025-10-17", "openWeights": true, "releaseDate": "2025-10-17" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "microsoft/phi-4-mini-instruct", "displayName": "Microsoft: Phi 4 Mini Instruct", "metadata": { "canonicalSlug": "microsoft/phi-4-mini-instruct", "createdAt": "2025-10-17T18:34:09.000Z", "huggingFaceId": "microsoft/Phi-4-mini-instruct", "links": { "details": "/api/v1/models/microsoft/phi-4-mini-instruct/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openrouter/reka-edge", "provider": "openrouter", "model": "reka-edge", "displayName": "Reka Edge", "family": "reka", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/rekaai/reka-edge" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "rekaai/reka-edge", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "rekaai/reka-edge", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Reka Edge" ], "families": [ "reka" ], "releaseDate": "2026-03-20", "lastUpdated": "2026-03-20", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "rekaai/reka-edge", "modelKey": "rekaai/reka-edge", "displayName": "Reka Edge", "family": "reka", "metadata": { "lastUpdated": "2026-03-20", "openWeights": true, "releaseDate": "2026-03-20" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "rekaai/reka-edge", "displayName": "Reka Edge", "metadata": { "canonicalSlug": "rekaai/reka-edge-2603", "createdAt": "2026-03-20T17:16:05.000Z", "huggingFaceId": "RekaAI/reka-edge-2603", "links": { "details": "/api/v1/models/rekaai/reka-edge-2603/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 16384, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/reka-flash-3", "provider": "openrouter", "model": "reka-flash-3", "displayName": "Reka Flash 3", "family": "reka", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/rekaai/reka-flash-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "rekaai/reka-flash-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "rekaai/reka-flash-3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Reka Flash 3" ], "families": [ "reka" ], "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "rekaai/reka-flash-3", "modelKey": "rekaai/reka-flash-3", "displayName": "Reka Flash 3", "family": "reka", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-03-12", "openWeights": true, "releaseDate": "2025-03-12" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "rekaai/reka-flash-3", "displayName": "Reka Flash 3", "metadata": { "canonicalSlug": "rekaai/reka-flash-3", "createdAt": "2025-03-12T20:53:33.000Z", "huggingFaceId": "RekaAI/reka-flash-3", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/rekaai/reka-flash-3/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 65536, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openrouter/relace-apply-3", "provider": "openrouter", "model": "relace-apply-3", "displayName": "Relace Apply 3", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/relace/relace-apply-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "relace/relace-apply-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 1.25 } }, { "source": "openrouter", "provider": "openrouter", "model": "relace/relace-apply-3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.85, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Relace Apply 3", "Relace: Relace Apply 3" ], "releaseDate": "2025-09-26", "lastUpdated": "2025-09-26", "supportedParameters": [ "max_tokens", "seed", "stop" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "relace/relace-apply-3", "modelKey": "relace/relace-apply-3", "displayName": "Relace Apply 3", "metadata": { "lastUpdated": "2025-09-26", "openWeights": false, "releaseDate": "2025-09-26" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "relace/relace-apply-3", "displayName": "Relace: Relace Apply 3", "metadata": { "canonicalSlug": "relace/relace-apply-3", "createdAt": "2025-09-26T12:59:32.000Z", "links": { "details": "/api/v1/models/relace/relace-apply-3/endpoints" }, "supportedParameters": [ "max_tokens", "seed", "stop" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openrouter/relace-search", "provider": "openrouter", "model": "relace-search", "displayName": "Relace Search", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/relace/relace-search" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "relace/relace-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } }, { "source": "openrouter", "provider": "openrouter", "model": "relace/relace-search", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Relace Search", "Relace: Relace Search" ], "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "supportedParameters": [ "max_tokens", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "relace/relace-search", "modelKey": "relace/relace-search", "displayName": "Relace Search", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "relace/relace-search", "displayName": "Relace: Relace Search", "metadata": { "canonicalSlug": "relace/relace-search-20251208", "createdAt": "2025-12-08T17:06:00.000Z", "links": { "details": "/api/v1/models/relace/relace-search-20251208/endpoints" }, "supportedParameters": [ "max_tokens", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 128000, "is_moderated": false } } } ] }, { "id": "openrouter/remm-slerp-l2-13b", "provider": "openrouter", "model": "remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/undi95/remm-slerp-l2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 6144, "inputTokens": 6144, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "undi95/remm-slerp-l2-13b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 0.65 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/undi95/remm-slerp-l2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.875, "output": 1.875 } }, { "source": "openrouter", "provider": "openrouter", "model": "undi95/remm-slerp-l2-13b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "ReMM SLERP 13B" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-07-22", "lastUpdated": "2023-07-22", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "undi95/remm-slerp-l2-13b", "modelKey": "undi95/remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "metadata": { "knowledgeCutoff": "2023-06-30", "lastUpdated": "2023-07-22", "openWeights": true, "releaseDate": "2023-07-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/undi95/remm-slerp-l2-13b", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "undi95/remm-slerp-l2-13b", "displayName": "ReMM SLERP 13B", "metadata": { "canonicalSlug": "undi95/remm-slerp-l2-13b", "createdAt": "2023-07-22T00:00:00.000Z", "huggingFaceId": "Undi95/ReMM-SLERP-L2-13B", "instructType": "alpaca", "knowledgeCutoff": "2023-06-30", "links": { "details": "/api/v1/models/undi95/remm-slerp-l2-13b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama2", "topProvider": { "context_length": 6144, "max_completion_tokens": 4096, "is_moderated": false } } } ] }, { "id": "openrouter/ring-2.6-1t", "provider": "openrouter", "model": "ring-2.6-1t", "displayName": "Ring-2.6-1T", "family": "ring", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/inclusionai/ring-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.075, "output": 0.625 } }, { "source": "openrouter", "provider": "openrouter", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.015, "input": 0.075, "output": 0.625 } } ] }, "metadata": { "displayNames": [ "Ring-2.6-1T", "inclusionAI: Ring-2.6-1T" ], "families": [ "ring" ], "releaseDate": "2026-05-08", "lastUpdated": "2026-05-08", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "inclusionai/ring-2.6-1t", "modelKey": "inclusionai/ring-2.6-1t", "displayName": "Ring-2.6-1T", "family": "ring", "metadata": { "lastUpdated": "2026-05-08", "openWeights": false, "releaseDate": "2026-05-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "inclusionai/ring-2.6-1t", "displayName": "inclusionAI: Ring-2.6-1T", "metadata": { "canonicalSlug": "inclusionai/ring-2.6-1t-20260508", "createdAt": "2026-05-08T13:37:20.000Z", "links": { "details": "/api/v1/models/inclusionai/ring-2.6-1t-20260508/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "xhigh", "high" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false } } } ] }, { "id": "openrouter/rnj-1-instruct", "provider": "openrouter", "model": "rnj-1-instruct", "displayName": "Rnj 1 Instruct", "family": "rnj", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/essentialai/rnj-1-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "essentialai/rnj-1-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } }, { "source": "openrouter", "provider": "openrouter", "model": "essentialai/rnj-1-instruct", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "EssentialAI: Rnj 1 Instruct", "Rnj 1 Instruct" ], "families": [ "rnj" ], "releaseDate": "2025-12-07", "lastUpdated": "2025-12-07", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "essentialai/rnj-1-instruct", "modelKey": "essentialai/rnj-1-instruct", "displayName": "Rnj 1 Instruct", "family": "rnj", "metadata": { "lastUpdated": "2025-12-07", "openWeights": true, "releaseDate": "2025-12-07" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "essentialai/rnj-1-instruct", "displayName": "EssentialAI: Rnj 1 Instruct", "metadata": { "canonicalSlug": "essentialai/rnj-1-instruct", "createdAt": "2025-12-07T08:07:27.000Z", "huggingFaceId": "EssentialAI/rnj-1-instruct", "links": { "details": "/api/v1/models/essentialai/rnj-1-instruct/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/rocinante-12b", "provider": "openrouter", "model": "rocinante-12b", "displayName": "Rocinante 12B", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/thedrummer/rocinante-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "thedrummer/rocinante-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.17, "output": 0.43 } }, { "source": "openrouter", "provider": "openrouter", "model": "thedrummer/rocinante-12b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.17, "output": 0.43 } } ] }, "metadata": { "displayNames": [ "Rocinante 12B", "TheDrummer: Rocinante 12B" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-09-30", "lastUpdated": "2024-09-30", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "thedrummer/rocinante-12b", "modelKey": "thedrummer/rocinante-12b", "displayName": "Rocinante 12B", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-09-30", "openWeights": true, "releaseDate": "2024-09-30" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "thedrummer/rocinante-12b", "displayName": "TheDrummer: Rocinante 12B", "metadata": { "canonicalSlug": "thedrummer/rocinante-12b", "createdAt": "2024-09-30T00:00:00.000Z", "huggingFaceId": "TheDrummer/Rocinante-12B-v1.1", "instructType": "chatml", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/thedrummer/rocinante-12b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Qwen", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/router", "provider": "openrouter", "model": "router", "displayName": "Switchpoint Router", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/switchpoint/router" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "switchpoint/router", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 3.4 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/switchpoint/router", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.85, "output": 3.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "switchpoint/router", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.85, "output": 3.4 } } ] }, "metadata": { "displayNames": [ "Switchpoint Router" ], "modes": [ "chat" ], "releaseDate": "2025-07-11", "lastUpdated": "2025-07-11", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "switchpoint/router", "modelKey": "switchpoint/router", "displayName": "Switchpoint Router", "metadata": { "lastUpdated": "2025-07-11", "openWeights": false, "releaseDate": "2025-07-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/switchpoint/router", "mode": "chat", "metadata": { "source": "https://openrouter.ai/switchpoint/router" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "switchpoint/router", "displayName": "Switchpoint Router", "metadata": { "canonicalSlug": "switchpoint/router", "createdAt": "2025-07-11T22:28:19.000Z", "links": { "details": "/api/v1/models/switchpoint/router/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/seed-1.6", "provider": "openrouter", "model": "seed-1.6", "displayName": "Seed 1.6", "family": "seed", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bytedance-seed/seed-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "bytedance-seed/seed-1.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "bytedance-seed/seed-1.6", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed 1.6", "Seed 1.6" ], "families": [ "seed" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "bytedance-seed/seed-1.6", "modelKey": "bytedance-seed/seed-1.6", "displayName": "Seed 1.6", "family": "seed", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "bytedance-seed/seed-1.6", "displayName": "ByteDance Seed: Seed 1.6", "metadata": { "canonicalSlug": "bytedance-seed/seed-1.6-20250625", "createdAt": "2025-12-23T15:49:57.000Z", "links": { "details": "/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/seed-1.6-flash", "provider": "openrouter", "model": "seed-1.6-flash", "displayName": "Seed 1.6 Flash", "family": "seed", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bytedance-seed/seed-1.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "bytedance-seed/seed-1.6-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "bytedance-seed/seed-1.6-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed 1.6 Flash", "Seed 1.6 Flash" ], "families": [ "seed" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "bytedance-seed/seed-1.6-flash", "modelKey": "bytedance-seed/seed-1.6-flash", "displayName": "Seed 1.6 Flash", "family": "seed", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "bytedance-seed/seed-1.6-flash", "displayName": "ByteDance Seed: Seed 1.6 Flash", "metadata": { "canonicalSlug": "bytedance-seed/seed-1.6-flash-20250625", "createdAt": "2025-12-23T15:50:11.000Z", "links": { "details": "/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/seed-2.0-lite", "provider": "openrouter", "model": "seed-2.0-lite", "displayName": "Seed-2.0-Lite", "family": "seed", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bytedance-seed/seed-2.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-lite", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed-2.0-Lite", "Seed-2.0-Lite" ], "families": [ "seed" ], "releaseDate": "2026-03-10", "lastUpdated": "2026-03-10", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "bytedance-seed/seed-2.0-lite", "modelKey": "bytedance-seed/seed-2.0-lite", "displayName": "Seed-2.0-Lite", "family": "seed", "metadata": { "lastUpdated": "2026-03-10", "openWeights": false, "releaseDate": "2026-03-10" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-lite", "displayName": "ByteDance Seed: Seed-2.0-Lite", "metadata": { "canonicalSlug": "bytedance-seed/seed-2.0-lite-20260309", "createdAt": "2026-03-10T15:40:31.000Z", "links": { "details": "/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/seed-2.0-mini", "provider": "openrouter", "model": "seed-2.0-mini", "displayName": "Seed-2.0-Mini", "family": "seed", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bytedance-seed/seed-2.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "ByteDance Seed: Seed-2.0-Mini", "Seed-2.0-Mini" ], "families": [ "seed" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-02-26", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "bytedance-seed/seed-2.0-mini", "modelKey": "bytedance-seed/seed-2.0-mini", "displayName": "Seed-2.0-Mini", "family": "seed", "metadata": { "lastUpdated": "2026-02-26", "openWeights": false, "releaseDate": "2026-02-26", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "bytedance-seed/seed-2.0-mini", "displayName": "ByteDance Seed: Seed-2.0-Mini", "metadata": { "canonicalSlug": "bytedance-seed/seed-2.0-mini-20260224", "createdAt": "2026-02-26T18:38:27.000Z", "links": { "details": "/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints" }, "reasoning": { "mandatory": false, "supported_efforts": [ "high", "medium", "low", "minimal" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/skyfall-36b-v2", "provider": "openrouter", "model": "skyfall-36b-v2", "displayName": "Skyfall 36B V2", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/thedrummer/skyfall-36b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "thedrummer/skyfall-36b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 0.55, "output": 0.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "thedrummer/skyfall-36b-v2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.25, "input": 0.55, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Skyfall 36B V2", "TheDrummer: Skyfall 36B V2" ], "knowledgeCutoff": "2024-06-30", "releaseDate": "2025-03-10", "lastUpdated": "2025-03-10", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "thedrummer/skyfall-36b-v2", "modelKey": "thedrummer/skyfall-36b-v2", "displayName": "Skyfall 36B V2", "metadata": { "knowledgeCutoff": "2024-06-30", "lastUpdated": "2025-03-10", "openWeights": true, "releaseDate": "2025-03-10" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "thedrummer/skyfall-36b-v2", "displayName": "TheDrummer: Skyfall 36B V2", "metadata": { "canonicalSlug": "thedrummer/skyfall-36b-v2", "createdAt": "2025-03-10T19:56:06.000Z", "huggingFaceId": "TheDrummer/Skyfall-36B-v2", "knowledgeCutoff": "2024-06-30", "links": { "details": "/api/v1/models/thedrummer/skyfall-36b-v2/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/solar-pro-3", "provider": "openrouter", "model": "solar-pro-3", "displayName": "Solar Pro 3", "family": "solar-pro", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/upstage/solar-pro-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "upstage/solar-pro-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } }, { "source": "openrouter", "provider": "openrouter", "model": "upstage/solar-pro-3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.015, "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Solar Pro 3", "Upstage: Solar Pro 3" ], "families": [ "solar-pro" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-01-27", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "tool_choice", "tools" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "upstage/solar-pro-3", "modelKey": "upstage/solar-pro-3", "displayName": "Solar Pro 3", "family": "solar-pro", "metadata": { "lastUpdated": "2026-01-27", "openWeights": false, "releaseDate": "2026-01-27" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "upstage/solar-pro-3", "displayName": "Upstage: Solar Pro 3", "metadata": { "canonicalSlug": "upstage/solar-pro-3", "createdAt": "2026-01-27T02:33:20.000Z", "links": { "details": "/api/v1/models/upstage/solar-pro-3/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "tool_choice", "tools" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "openrouter/step-3.5-flash", "provider": "openrouter", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "stepfun/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.09, "output": 0.3 } }, { "source": "openrouter", "provider": "openrouter", "model": "stepfun/step-3.5-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.09, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash", "StepFun: Step 3.5 Flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-02-13", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "stepfun/step-3.5-flash", "modelKey": "stepfun/step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-01-29" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "stepfun/step-3.5-flash", "displayName": "StepFun: Step 3.5 Flash", "metadata": { "canonicalSlug": "stepfun/step-3.5-flash", "createdAt": "2026-01-29T23:12:17.000Z", "huggingFaceId": "stepfun-ai/Step-3.5-Flash", "links": { "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "openrouter/step-3.7-flash", "provider": "openrouter", "model": "step-3.7-flash", "displayName": "Step 3.7 Flash", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/stepfun/step-3.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "stepfun/step-3.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 1.15 } }, { "source": "openrouter", "provider": "openrouter", "model": "stepfun/step-3.7-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash", "StepFun: Step 3.7 Flash" ], "knowledgeCutoff": "2026-01-01", "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "stepfun/step-3.7-flash", "modelKey": "stepfun/step-3.7-flash", "displayName": "Step 3.7 Flash", "metadata": { "knowledgeCutoff": "2026-01-01", "lastUpdated": "2026-05-29", "openWeights": true, "releaseDate": "2026-05-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "stepfun/step-3.7-flash", "displayName": "StepFun: Step 3.7 Flash", "metadata": { "canonicalSlug": "stepfun/step-3.7-flash-20260528", "createdAt": "2026-05-28T16:17:49.000Z", "huggingFaceId": "stepfun-ai/Step-3.7-Flash", "links": { "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints" }, "reasoning": { "mandatory": true, "supported_efforts": [ "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 256000, "max_completion_tokens": 256000, "is_moderated": false } } } ] }, { "id": "openrouter/trinity-large-thinking", "provider": "openrouter", "model": "trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/arcee-ai/trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "arcee-ai/trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.22, "output": 0.85 } }, { "source": "openrouter", "provider": "openrouter", "model": "arcee-ai/trinity-large-thinking", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.06, "input": 0.22, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Trinity Large Thinking", "Trinity Large Thinking" ], "families": [ "trinity" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "arcee-ai/trinity-large-thinking", "modelKey": "arcee-ai/trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "arcee-ai/trinity-large-thinking", "displayName": "Arcee AI: Trinity Large Thinking", "metadata": { "canonicalSlug": "arcee-ai/trinity-large-thinking", "createdAt": "2026-04-01T15:45:18.000Z", "huggingFaceId": "arcee-ai/Trinity-Large-Thinking", "links": { "details": "/api/v1/models/arcee-ai/trinity-large-thinking/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 262144, "is_moderated": false } } } ] }, { "id": "openrouter/trinity-mini", "provider": "openrouter", "model": "trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/arcee-ai/trinity-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "arcee-ai/trinity-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.15 } }, { "source": "openrouter", "provider": "openrouter", "model": "arcee-ai/trinity-mini", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.045, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Trinity Mini", "Trinity Mini" ], "families": [ "trinity-mini" ], "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "supportedParameters": [ "include_reasoning", "logprobs", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "arcee-ai/trinity-mini", "modelKey": "arcee-ai/trinity-mini", "displayName": "Trinity Mini", "family": "trinity-mini", "metadata": { "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "arcee-ai/trinity-mini", "displayName": "Arcee AI: Trinity Mini", "metadata": { "canonicalSlug": "arcee-ai/trinity-mini-20251201", "createdAt": "2025-12-01T15:08:40.000Z", "huggingFaceId": "arcee-ai/Trinity-Mini", "links": { "details": "/api/v1/models/arcee-ai/trinity-mini-20251201/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "include_reasoning", "logprobs", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "openrouter/ui-tars-1.5-7b", "provider": "openrouter", "model": "ui-tars-1.5-7b", "displayName": "UI-TARS 7B", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/bytedance/ui-tars-1.5-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 2048, "outputTokens": 2048, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "bytedance/ui-tars-1.5-7b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.1, "output": 0.2 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/bytedance/ui-tars-1.5-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "bytedance/ui-tars-1.5-7b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 0.1, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "ByteDance: UI-TARS 7B", "UI-TARS 7B" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01-31", "releaseDate": "2025-07-22", "lastUpdated": "2025-07-22", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "bytedance/ui-tars-1.5-7b", "modelKey": "bytedance/ui-tars-1.5-7b", "displayName": "UI-TARS 7B", "metadata": { "knowledgeCutoff": "2025-01-31", "lastUpdated": "2025-07-22", "openWeights": true, "releaseDate": "2025-07-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/bytedance/ui-tars-1.5-7b", "mode": "chat", "metadata": { "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "bytedance/ui-tars-1.5-7b", "displayName": "ByteDance: UI-TARS 7B", "metadata": { "canonicalSlug": "bytedance/ui-tars-1.5-7b", "createdAt": "2025-07-22T17:24:16.000Z", "huggingFaceId": "ByteDance-Seed/UI-TARS-1.5-7B", "knowledgeCutoff": "2025-01-31", "links": { "details": "/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": 2048, "is_moderated": false } } } ] }, { "id": "openrouter/unslopnemo-12b", "provider": "openrouter", "model": "unslopnemo-12b", "displayName": "UnslopNemo 12B", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/thedrummer/unslopnemo-12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "thedrummer/unslopnemo-12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "thedrummer/unslopnemo-12b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "TheDrummer: UnslopNemo 12B", "UnslopNemo 12B" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-11-08", "lastUpdated": "2024-11-08", "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "thedrummer/unslopnemo-12b", "modelKey": "thedrummer/unslopnemo-12b", "displayName": "UnslopNemo 12B", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-11-08", "openWeights": true, "releaseDate": "2024-11-08" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "thedrummer/unslopnemo-12b", "displayName": "TheDrummer: UnslopNemo 12B", "metadata": { "canonicalSlug": "thedrummer/unslopnemo-12b", "createdAt": "2024-11-08T22:04:08.000Z", "huggingFaceId": "TheDrummer/UnslopNemo-12B-v4.1", "instructType": "mistral", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/thedrummer/unslopnemo-12b/endpoints" }, "supportedParameters": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 32768, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "openrouter/virtuoso-large", "provider": "openrouter", "model": "virtuoso-large", "displayName": "Virtuoso Large", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/arcee-ai/virtuoso-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "arcee-ai/virtuoso-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 1.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "arcee-ai/virtuoso-large", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Arcee AI: Virtuoso Large", "Virtuoso Large" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-05", "lastUpdated": "2025-05-05", "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "arcee-ai/virtuoso-large", "modelKey": "arcee-ai/virtuoso-large", "displayName": "Virtuoso Large", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-05", "openWeights": false, "releaseDate": "2025-05-05" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "arcee-ai/virtuoso-large", "displayName": "Arcee AI: Virtuoso Large", "metadata": { "canonicalSlug": "arcee-ai/virtuoso-large", "createdAt": "2025-05-05T21:01:25.000Z", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/arcee-ai/virtuoso-large/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 64000, "is_moderated": false } } } ] }, { "id": "openrouter/weaver", "provider": "openrouter", "model": "weaver", "displayName": "Weaver (alpha)", "family": "alpha", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/mancer/weaver" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 2000, "outputTokens": 2000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "mancer/weaver", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 1 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/mancer/weaver", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5.625, "output": 5.625 } }, { "source": "openrouter", "provider": "openrouter", "model": "mancer/weaver", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.75, "output": 1 } } ] }, "metadata": { "displayNames": [ "Mancer: Weaver (alpha)", "Weaver (alpha)" ], "families": [ "alpha" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-06-30", "releaseDate": "2023-08-02", "lastUpdated": "2023-08-02", "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "mancer/weaver", "modelKey": "mancer/weaver", "displayName": "Weaver (alpha)", "family": "alpha", "metadata": { "knowledgeCutoff": "2023-06-30", "lastUpdated": "2023-08-02", "openWeights": false, "releaseDate": "2023-08-02" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/mancer/weaver", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "mancer/weaver", "displayName": "Mancer: Weaver (alpha)", "metadata": { "canonicalSlug": "mancer/weaver", "createdAt": "2023-08-02T00:00:00.000Z", "instructType": "alpaca", "knowledgeCutoff": "2023-06-30", "links": { "details": "/api/v1/models/mancer/weaver/endpoints" }, "supportedParameters": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Llama2", "topProvider": { "context_length": 8000, "max_completion_tokens": 2000, "is_moderated": false } } } ] }, { "id": "openrouter/wizardlm-2-8x22b", "provider": "openrouter", "model": "wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "sources": [ "models.dev", "openrouter" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/microsoft/wizardlm-2-8x22b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "openrouter", "model": "microsoft/wizardlm-2-8x22b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.62, "output": 0.62 } }, { "source": "openrouter", "provider": "openrouter", "model": "microsoft/wizardlm-2-8x22b", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.62, "output": 0.62 } } ] }, "metadata": { "displayNames": [ "WizardLM-2 8x22B" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-04-16", "lastUpdated": "2024-04-16", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "microsoft/wizardlm-2-8x22b", "modelKey": "microsoft/wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-04-16", "openWeights": true, "releaseDate": "2024-04-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "microsoft/wizardlm-2-8x22b", "displayName": "WizardLM-2 8x22B", "metadata": { "canonicalSlug": "microsoft/wizardlm-2-8x22b", "createdAt": "2024-04-16T00:00:00.000Z", "huggingFaceId": "microsoft/WizardLM-2-8x22B", "instructType": "vicuna", "knowledgeCutoff": "2024-04-30", "links": { "details": "/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "temperature", "top_k", "top_p" ], "tokenizer": "Mistral", "topProvider": { "context_length": 65535, "max_completion_tokens": 8000, "is_moderated": false } } } ] }, { "id": "orcarouter/auto", "provider": "orcarouter", "model": "auto", "displayName": "OrcaRouter Auto", "family": "auto", "sources": [ "models.dev" ], "providers": [ "orcarouter" ], "aliases": [ "orcarouter/auto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "orcarouter", "model": "orcarouter/auto", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "OrcaRouter Auto" ], "families": [ "auto" ], "releaseDate": "2025-01-01", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "orcarouter/auto", "modelKey": "orcarouter/auto", "displayName": "OrcaRouter Auto", "family": "auto", "metadata": { "lastUpdated": "2026-05-14", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "ovhcloud/llava-v1.6-mistral-7b-hf", "provider": "ovhcloud", "model": "llava-v1.6-mistral-7b-hf", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ovhcloud" ], "aliases": [ "ovhcloud/llava-v1.6-mistral-7b-hf" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/llava-v1.6-mistral-7b-hf", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.29, "output": 0.29 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/llava-v1.6-mistral-7b-hf", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b" } } ] }, { "id": "ovhcloud/mamba-codestral-7b-v0.1", "provider": "ovhcloud", "model": "mamba-codestral-7b-v0.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "ovhcloud" ], "aliases": [ "ovhcloud/mamba-codestral-7B-v0.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "ovhcloud", "model": "ovhcloud/mamba-codestral-7B-v0.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.19, "output": 0.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "ovhcloud", "model": "ovhcloud/mamba-codestral-7B-v0.1", "mode": "chat", "metadata": { "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1" } } ] }, { "id": "palm/chat-bison", "provider": "palm", "model": "chat-bison", "mode": "chat", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/chat-bison" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/chat-bison", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/chat-bison", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "palm/chat-bison-001", "provider": "palm", "model": "chat-bison-001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/chat-bison-001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/chat-bison-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/chat-bison-001", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "palm/text-bison", "provider": "palm", "model": "text-bison", "mode": "completion", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/text-bison" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/text-bison", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/text-bison", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "palm/text-bison-001", "provider": "palm", "model": "text-bison-001", "mode": "completion", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/text-bison-001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/text-bison-001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/text-bison-001", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "palm/text-bison-safety-off", "provider": "palm", "model": "text-bison-safety-off", "mode": "completion", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/text-bison-safety-off" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/text-bison-safety-off", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/text-bison-safety-off", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "palm/text-bison-safety-recitation-off", "provider": "palm", "model": "text-bison-safety-recitation-off", "mode": "completion", "sources": [ "litellm" ], "providers": [ "palm" ], "aliases": [ "palm/text-bison-safety-recitation-off" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "palm", "model": "palm/text-bison-safety-recitation-off", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.125, "output": 0.125 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "palm", "model": "palm/text-bison-safety-recitation-off", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "parallel-ai/search", "provider": "parallel-ai", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "parallel_ai" ], "aliases": [ "parallel_ai/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "parallel_ai", "model": "parallel_ai/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.004 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "parallel_ai", "model": "parallel_ai/search", "mode": "search" } ] }, { "id": "parallel-ai/search-pro", "provider": "parallel-ai", "model": "search-pro", "mode": "search", "sources": [ "litellm" ], "providers": [ "parallel_ai" ], "aliases": [ "parallel_ai/search-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "parallel_ai", "model": "parallel_ai/search-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.009 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "parallel_ai", "model": "parallel_ai/search-pro", "mode": "search" } ] }, { "id": "perplexity-agent/nemotron-3-super-120b-a12b", "provider": "perplexity-agent", "model": "nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "perplexity-agent" ], "aliases": [ "perplexity-agent/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 32000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "perplexity-agent", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2026-02", "releaseDate": "2026-03-11", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2026-02", "lastUpdated": "2026-03-11", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "perplexity/advanced-deep-research", "provider": "perplexity", "model": "advanced-deep-research", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/preset/advanced-deep-research" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/preset/advanced-deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/preset/advanced-deep-research", "mode": "responses" } ] }, { "id": "perplexity/claude-haiku-4-5", "provider": "perplexity", "model": "claude-haiku-4-5", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/anthropic/claude-haiku-4-5" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/anthropic/claude-haiku-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/anthropic/claude-haiku-4-5", "mode": "responses" } ] }, { "id": "perplexity/claude-opus-4-5", "provider": "perplexity", "model": "claude-opus-4-5", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/anthropic/claude-opus-4-5" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-5", "mode": "responses" } ] }, { "id": "perplexity/claude-opus-4-6", "provider": "perplexity", "model": "claude-opus-4-6", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/anthropic/claude-opus-4-6" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-6", "mode": "responses" } ] }, { "id": "perplexity/claude-opus-4-7", "provider": "perplexity", "model": "claude-opus-4-7", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/anthropic/claude-opus-4-7" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/anthropic/claude-opus-4-7", "mode": "responses" } ] }, { "id": "perplexity/claude-sonnet-4-5", "provider": "perplexity", "model": "claude-sonnet-4-5", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/anthropic/claude-sonnet-4-5" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/anthropic/claude-sonnet-4-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/anthropic/claude-sonnet-4-5", "mode": "responses" } ] }, { "id": "perplexity/codellama-34b-instruct", "provider": "perplexity", "model": "codellama-34b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/codellama-34b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/codellama-34b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.35, "output": 1.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/codellama-34b-instruct", "mode": "chat" } ] }, { "id": "perplexity/codellama-70b-instruct", "provider": "perplexity", "model": "codellama-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/codellama-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/codellama-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/codellama-70b-instruct", "mode": "chat" } ] }, { "id": "perplexity/deep-research", "provider": "perplexity", "model": "deep-research", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/preset/deep-research" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/preset/deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/preset/deep-research", "mode": "responses" } ] }, { "id": "perplexity/fast-search", "provider": "perplexity", "model": "fast-search", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/preset/fast-search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/preset/fast-search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/preset/fast-search", "mode": "responses" } ] }, { "id": "perplexity/gemini-2.5-flash", "provider": "perplexity", "model": "gemini-2.5-flash", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/google/gemini-2.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/google/gemini-2.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/google/gemini-2.5-flash", "mode": "responses" } ] }, { "id": "perplexity/gemini-2.5-pro", "provider": "perplexity", "model": "gemini-2.5-pro", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/google/gemini-2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/google/gemini-2.5-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/google/gemini-2.5-pro", "mode": "responses" } ] }, { "id": "perplexity/gemini-3-flash-preview", "provider": "perplexity", "model": "gemini-3-flash-preview", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/google/gemini-3-flash-preview" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/google/gemini-3-flash-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/google/gemini-3-flash-preview", "mode": "responses" } ] }, { "id": "perplexity/gemini-3-pro-preview", "provider": "perplexity", "model": "gemini-3-pro-preview", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/google/gemini-3-pro-preview" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/google/gemini-3-pro-preview", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/google/gemini-3-pro-preview", "mode": "responses" } ] }, { "id": "perplexity/gpt-5-mini", "provider": "perplexity", "model": "gpt-5-mini", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/openai/gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/openai/gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/openai/gpt-5-mini", "mode": "responses" } ] }, { "id": "perplexity/gpt-5.1", "provider": "perplexity", "model": "gpt-5.1", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/openai/gpt-5.1" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/openai/gpt-5.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/openai/gpt-5.1", "mode": "responses" } ] }, { "id": "perplexity/gpt-5.2", "provider": "perplexity", "model": "gpt-5.2", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/openai/gpt-5.2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/openai/gpt-5.2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/openai/gpt-5.2", "mode": "responses" } ] }, { "id": "perplexity/grok-4-1-fast-non-reasoning", "provider": "perplexity", "model": "grok-4-1-fast-non-reasoning", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/xai/grok-4-1-fast-non-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/xai/grok-4-1-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/xai/grok-4-1-fast-non-reasoning", "mode": "responses" } ] }, { "id": "perplexity/llama-2-70b-chat", "provider": "perplexity", "model": "llama-2-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/llama-2-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/llama-2-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/llama-2-70b-chat", "mode": "chat" } ] }, { "id": "perplexity/llama-3.1-70b-instruct", "provider": "perplexity", "model": "llama-3.1-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/llama-3.1-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/llama-3.1-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/llama-3.1-70b-instruct", "mode": "chat" } ] }, { "id": "perplexity/llama-3.1-8b-instruct", "provider": "perplexity", "model": "llama-3.1-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/llama-3.1-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/llama-3.1-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/llama-3.1-8b-instruct", "mode": "chat" } ] }, { "id": "perplexity/mistral-7b-instruct", "provider": "perplexity", "model": "mistral-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/mistral-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/mistral-7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/mistral-7b-instruct", "mode": "chat" } ] }, { "id": "perplexity/mixtral-8x7b-instruct", "provider": "perplexity", "model": "mixtral-8x7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/mixtral-8x7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/mixtral-8x7b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/mixtral-8x7b-instruct", "mode": "chat" } ] }, { "id": "perplexity/pplx-70b-chat", "provider": "perplexity", "model": "pplx-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.7, "output": 2.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-70b-chat", "mode": "chat" } ] }, { "id": "perplexity/pplx-70b-online", "provider": "perplexity", "model": "pplx-70b-online", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-70b-online" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-70b-online", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 2.8 }, "perRequest": { "input": 0.005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-70b-online", "mode": "chat" } ] }, { "id": "perplexity/pplx-7b-chat", "provider": "perplexity", "model": "pplx-7b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-7b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-7b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-7b-chat", "mode": "chat" } ] }, { "id": "perplexity/pplx-7b-online", "provider": "perplexity", "model": "pplx-7b-online", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-7b-online" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-7b-online", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0.28 }, "perRequest": { "input": 0.005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-7b-online", "mode": "chat" } ] }, { "id": "perplexity/pplx-embed-v1-0.6b", "provider": "perplexity", "model": "pplx-embed-v1-0.6b", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-embed-v1-0.6b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "outputVectorSize": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-embed-v1-0.6b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.004, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-embed-v1-0.6b", "mode": "embedding", "metadata": { "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" } } ] }, { "id": "perplexity/pplx-embed-v1-4b", "provider": "perplexity", "model": "pplx-embed-v1-4b", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/pplx-embed-v1-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "outputVectorSize": 2560, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/pplx-embed-v1-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/pplx-embed-v1-4b", "mode": "embedding", "metadata": { "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" } } ] }, { "id": "perplexity/pro-search", "provider": "perplexity", "model": "pro-search", "mode": "responses", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/preset/pro-search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/preset/pro-search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "responses" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/preset/pro-search", "mode": "responses" } ] }, { "id": "perplexity/search", "provider": "perplexity", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.005 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/search", "mode": "search" } ] }, { "id": "perplexity/sonar", "provider": "perplexity", "model": "sonar", "displayName": "Sonar", "family": "sonar", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter", "perplexity", "perplexity-agent", "vercel", "vercel_ai_gateway" ], "aliases": [ "kilo/perplexity/sonar", "openrouter/perplexity/sonar", "perplexity-agent/perplexity/sonar", "perplexity/perplexity/sonar", "perplexity/sonar", "vercel/perplexity/sonar", "vercel_ai_gateway/perplexity/sonar" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "webSearch": true, "supports1MContext": false, "functionCalling": true, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "perplexity/sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "models.dev", "provider": "openrouter", "model": "perplexity/sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "perplexity/sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0625, "input": 0.25, "output": 2.5 } }, { "source": "models.dev", "provider": "perplexity", "model": "sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/perplexity/sonar", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 }, "searchContextPerQuery": { "search_context_size_high": 0.012, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 } }, { "source": "openrouter", "provider": "openrouter", "model": "perplexity/sonar", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 1 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Perplexity: Sonar", "Sonar" ], "families": [ "sonar" ], "modes": [ "chat", "responses" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2024-01-01", "lastUpdated": "2025-09-01", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "temperature", "top_k", "top_p", "web_search_options" ], "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perplexity/sonar", "modelKey": "perplexity/sonar", "displayName": "Perplexity: Sonar", "metadata": { "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perplexity/sonar", "modelKey": "perplexity/sonar", "displayName": "Sonar", "family": "sonar", "metadata": { "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "perplexity/sonar", "modelKey": "perplexity/sonar", "displayName": "Sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity", "providerName": "Perplexity", "providerDoc": "https://docs.perplexity.ai", "model": "sonar", "modelKey": "sonar", "displayName": "Sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "perplexity/sonar", "modelKey": "perplexity/sonar", "displayName": "Sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-02", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/perplexity/sonar", "mode": "responses" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perplexity/sonar", "displayName": "Perplexity: Sonar", "metadata": { "canonicalSlug": "perplexity/sonar", "createdAt": "2025-01-27T21:36:48.000Z", "links": { "details": "/api/v1/models/perplexity/sonar/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "temperature", "top_k", "top_p", "web_search_options" ], "tokenizer": "Other", "topProvider": { "context_length": 127072, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "perplexity/sonar-deep-research", "provider": "perplexity", "model": "sonar-deep-research", "displayName": "Perplexity Sonar Deep Research", "family": "sonar-deep-research", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "helicone", "kilo", "nano-gpt", "openrouter", "perplexity", "sap-ai-core" ], "aliases": [ "helicone/sonar-deep-research", "kilo/perplexity/sonar-deep-research", "nano-gpt/sonar-deep-research", "openrouter/perplexity/sonar-deep-research", "perplexity/sonar-deep-research", "sap-ai-core/sonar-deep-research" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "webSearch": true, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "kilo", "model": "perplexity/sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.4, "output": 13.6 } }, { "source": "models.dev", "provider": "openrouter", "model": "perplexity/sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8, "reasoningOutput": 3 } }, { "source": "models.dev", "provider": "perplexity", "model": "sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8, "reasoningOutput": 3 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "sonar-deep-research", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8, "reasoningOutput": 3 } }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-deep-research", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8, "reasoningOutput": 3 }, "searchContextPerQuery": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "extra": { "citation_cost_per_token": 0.000002 } }, { "source": "openrouter", "provider": "openrouter", "model": "perplexity/sonar-deep-research", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "internalReasoning": 3, "output": 8 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Perplexity Deep Research", "Perplexity Sonar Deep Research", "Perplexity: Sonar Deep Research", "Sonar Deep Research", "sonar-deep-research" ], "families": [ "sonar-deep-research" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-27", "lastUpdated": "2025-01-27", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "temperature", "top_k", "top_p", "web_search_options" ], "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "sonar-deep-research", "modelKey": "sonar-deep-research", "displayName": "Perplexity Sonar Deep Research", "family": "sonar-deep-research", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perplexity/sonar-deep-research", "modelKey": "perplexity/sonar-deep-research", "displayName": "Perplexity: Sonar Deep Research", "metadata": { "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sonar-deep-research", "modelKey": "sonar-deep-research", "displayName": "Perplexity Deep Research", "metadata": { "lastUpdated": "2025-02-25", "openWeights": false, "releaseDate": "2025-02-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perplexity/sonar-deep-research", "modelKey": "perplexity/sonar-deep-research", "displayName": "Sonar Deep Research", "family": "sonar-deep-research", "metadata": { "lastUpdated": "2025-03-07", "openWeights": false, "releaseDate": "2025-03-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity", "providerName": "Perplexity", "providerDoc": "https://docs.perplexity.ai", "model": "sonar-deep-research", "modelKey": "sonar-deep-research", "displayName": "Perplexity Sonar Deep Research", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2025-02-01", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "sonar-deep-research", "modelKey": "sonar-deep-research", "displayName": "sonar-deep-research", "family": "sonar-deep-research", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2025-02-01" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-deep-research", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perplexity/sonar-deep-research", "displayName": "Perplexity: Sonar Deep Research", "metadata": { "canonicalSlug": "perplexity/sonar-deep-research", "createdAt": "2025-03-07T01:34:06.000Z", "instructType": "deepseek-r1", "links": { "details": "/api/v1/models/perplexity/sonar-deep-research/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "temperature", "top_k", "top_p", "web_search_options" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "perplexity/sonar-medium-chat", "provider": "perplexity", "model": "sonar-medium-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/sonar-medium-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-medium-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-medium-chat", "mode": "chat" } ] }, { "id": "perplexity/sonar-medium-online", "provider": "perplexity", "model": "sonar-medium-online", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/sonar-medium-online" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 12000, "inputTokens": 12000, "maxTokens": 12000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-medium-online", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 1.8 }, "perRequest": { "input": 0.005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-medium-online", "mode": "chat" } ] }, { "id": "perplexity/sonar-pro", "provider": "perplexity", "model": "sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "helicone", "kilo", "llmgateway", "nano-gpt", "openrouter", "perplexity", "sap-ai-core", "vercel", "vercel_ai_gateway" ], "aliases": [ "anyapi/perplexity/sonar-pro", "helicone/sonar-pro", "kilo/perplexity/sonar-pro", "llmgateway/sonar-pro", "nano-gpt/sonar-pro", "openrouter/perplexity/sonar-pro", "perplexity/sonar-pro", "sap-ai-core/sonar-pro", "vercel/perplexity/sonar-pro", "vercel_ai_gateway/perplexity/sonar-pro" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 8000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "webSearch": true, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "kilo", "model": "perplexity/sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "llmgateway", "model": "sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.992, "output": 14.994 } }, { "source": "models.dev", "provider": "openrouter", "model": "perplexity/sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "perplexity", "model": "sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "sap-ai-core", "model": "sonar-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "searchContextPerQuery": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "perplexity/sonar-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Perplexity Pro", "Perplexity Sonar Pro", "Perplexity: Sonar Pro", "Sonar Pro", "sonar-pro" ], "families": [ "sonar-pro" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2024-01-01", "lastUpdated": "2025-09-01", "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "temperature", "top_k", "top_p", "web_search_options" ], "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "perplexity/sonar-pro", "modelKey": "perplexity/sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "sonar-pro", "modelKey": "sonar-pro", "displayName": "Perplexity Sonar Pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perplexity/sonar-pro", "modelKey": "perplexity/sonar-pro", "displayName": "Perplexity: Sonar Pro", "metadata": { "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "sonar-pro", "modelKey": "sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sonar-pro", "modelKey": "sonar-pro", "displayName": "Perplexity Pro", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perplexity/sonar-pro", "modelKey": "perplexity/sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "metadata": { "lastUpdated": "2025-03-07", "openWeights": false, "releaseDate": "2025-03-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity", "providerName": "Perplexity", "providerDoc": "https://docs.perplexity.ai", "model": "sonar-pro", "modelKey": "sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "sonar-pro", "modelKey": "sonar-pro", "displayName": "sonar-pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "perplexity/sonar-pro", "modelKey": "perplexity/sonar-pro", "displayName": "Sonar Pro", "family": "sonar-pro", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-pro", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perplexity/sonar-pro", "displayName": "Perplexity: Sonar Pro", "metadata": { "canonicalSlug": "perplexity/sonar-pro", "createdAt": "2025-03-07T01:53:43.000Z", "links": { "details": "/api/v1/models/perplexity/sonar-pro/endpoints" }, "supportedParameters": [ "frequency_penalty", "max_tokens", "presence_penalty", "temperature", "top_k", "top_p", "web_search_options" ], "tokenizer": "Other", "topProvider": { "context_length": 200000, "max_completion_tokens": 8000, "is_moderated": false } } } ] }, { "id": "perplexity/sonar-pro-search", "provider": "perplexity", "model": "sonar-pro-search", "displayName": "Perplexity: Sonar Pro Search", "family": "sonar-pro", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "openrouter" ], "aliases": [ "kilo/perplexity/sonar-pro-search", "openrouter/perplexity/sonar-pro-search" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "perplexity/sonar-pro-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "openrouter", "model": "perplexity/sonar-pro-search", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "openrouter", "provider": "openrouter", "model": "perplexity/sonar-pro-search", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "other": { "webSearch": 0.018 } } ] }, "metadata": { "displayNames": [ "Perplexity: Sonar Pro Search", "Sonar Pro Search" ], "families": [ "sonar-pro" ], "releaseDate": "2025-10-31", "lastUpdated": "2026-03-15", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "structured_outputs", "temperature", "top_k", "top_p", "web_search_options" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perplexity/sonar-pro-search", "modelKey": "perplexity/sonar-pro-search", "displayName": "Perplexity: Sonar Pro Search", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2025-10-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perplexity/sonar-pro-search", "modelKey": "perplexity/sonar-pro-search", "displayName": "Sonar Pro Search", "family": "sonar-pro", "metadata": { "lastUpdated": "2025-10-30", "openWeights": false, "releaseDate": "2025-10-30" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perplexity/sonar-pro-search", "displayName": "Perplexity: Sonar Pro Search", "metadata": { "canonicalSlug": "perplexity/sonar-pro-search", "createdAt": "2025-10-30T19:59:26.000Z", "links": { "details": "/api/v1/models/perplexity/sonar-pro-search/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "structured_outputs", "temperature", "top_k", "top_p", "web_search_options" ], "tokenizer": "Other", "topProvider": { "context_length": 200000, "max_completion_tokens": 8000, "is_moderated": false } } } ] }, { "id": "perplexity/sonar-reasoning", "provider": "perplexity", "model": "sonar-reasoning", "displayName": "Perplexity Sonar Reasoning", "family": "sonar-reasoning", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "helicone", "perplexity", "vercel_ai_gateway" ], "aliases": [ "helicone/sonar-reasoning", "perplexity/sonar-reasoning", "vercel_ai_gateway/perplexity/sonar-reasoning" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false, "attachments": false, "openWeights": false, "temperature": true, "toolCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "sonar-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 5 } }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 }, "searchContextPerQuery": { "search_context_size_high": 0.014, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "Perplexity Sonar Reasoning" ], "families": [ "sonar-reasoning" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-01-27", "lastUpdated": "2025-01-27", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "sonar-reasoning", "modelKey": "sonar-reasoning", "displayName": "Perplexity Sonar Reasoning", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-reasoning", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-reasoning", "mode": "chat" } ] }, { "id": "perplexity/sonar-reasoning-pro", "provider": "perplexity", "model": "sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "anyapi", "helicone", "kilo", "llmgateway", "nano-gpt", "openrouter", "perplexity", "vercel", "vercel_ai_gateway" ], "aliases": [ "anyapi/perplexity/sonar-reasoning-pro", "helicone/sonar-reasoning-pro", "kilo/perplexity/sonar-reasoning-pro", "llmgateway/sonar-reasoning-pro", "nano-gpt/sonar-reasoning-pro", "openrouter/perplexity/sonar-reasoning-pro", "perplexity/sonar-reasoning-pro", "vercel/perplexity/sonar-reasoning-pro", "vercel_ai_gateway/perplexity/sonar-reasoning-pro" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "webSearch": true, "supports1MContext": false, "structuredOutput": false, "parallelFunctionCalling": false, "responseSchema": false, "toolChoice": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "helicone", "model": "sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "kilo", "model": "perplexity/sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "llmgateway", "model": "sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 7.9985 } }, { "source": "models.dev", "provider": "openrouter", "model": "perplexity/sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "models.dev", "provider": "perplexity", "model": "sonar-reasoning-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-reasoning-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 }, "searchContextPerQuery": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-reasoning-pro", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } }, { "source": "openrouter", "provider": "openrouter", "model": "perplexity/sonar-reasoning-pro", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Perplexity Reasoning Pro", "Perplexity Sonar Reasoning Pro", "Perplexity: Sonar Reasoning Pro", "Sonar Reasoning Pro" ], "families": [ "sonar-reasoning" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2024-01-01", "lastUpdated": "2025-09-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "temperature", "top_k", "top_p", "web_search_options" ], "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "perplexity/sonar-reasoning-pro", "modelKey": "perplexity/sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "sonar-reasoning-pro", "modelKey": "sonar-reasoning-pro", "displayName": "Perplexity Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01-27", "openWeights": false, "releaseDate": "2025-01-27", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "perplexity/sonar-reasoning-pro", "modelKey": "perplexity/sonar-reasoning-pro", "displayName": "Perplexity: Sonar Reasoning Pro", "metadata": { "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "sonar-reasoning-pro", "modelKey": "sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "sonar-reasoning-pro", "modelKey": "sonar-reasoning-pro", "displayName": "Perplexity Reasoning Pro", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "perplexity/sonar-reasoning-pro", "modelKey": "perplexity/sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "lastUpdated": "2025-03-07", "openWeights": false, "releaseDate": "2025-03-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity", "providerName": "Perplexity", "providerDoc": "https://docs.perplexity.ai", "model": "sonar-reasoning-pro", "modelKey": "sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "perplexity/sonar-reasoning-pro", "modelKey": "perplexity/sonar-reasoning-pro", "displayName": "Sonar Reasoning Pro", "family": "sonar-reasoning", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-reasoning-pro", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/perplexity/sonar-reasoning-pro", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "perplexity/sonar-reasoning-pro", "displayName": "Perplexity: Sonar Reasoning Pro", "metadata": { "canonicalSlug": "perplexity/sonar-reasoning-pro", "createdAt": "2025-03-07T02:08:28.000Z", "instructType": "deepseek-r1", "links": { "details": "/api/v1/models/perplexity/sonar-reasoning-pro/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "temperature", "top_k", "top_p", "web_search_options" ], "tokenizer": "Other", "topProvider": { "context_length": 128000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "perplexity/sonar-small-chat", "provider": "perplexity", "model": "sonar-small-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/sonar-small-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-small-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0.28 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-small-chat", "mode": "chat" } ] }, { "id": "perplexity/sonar-small-online", "provider": "perplexity", "model": "sonar-small-online", "mode": "chat", "sources": [ "litellm" ], "providers": [ "perplexity" ], "aliases": [ "perplexity/sonar-small-online" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 12000, "inputTokens": 12000, "maxTokens": 12000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "perplexity", "model": "perplexity/sonar-small-online", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0.28 }, "perRequest": { "input": 0.005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "perplexity", "model": "perplexity/sonar-small-online", "mode": "chat" } ] }, { "id": "poe/elevenlabs-music", "provider": "poe", "model": "elevenlabs-music", "displayName": "ElevenLabs-Music", "family": "elevenlabs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/elevenlabs/elevenlabs-music" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ElevenLabs-Music" ], "families": [ "elevenlabs" ], "releaseDate": "2025-08-29", "lastUpdated": "2025-08-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "elevenlabs/elevenlabs-music", "modelKey": "elevenlabs/elevenlabs-music", "displayName": "ElevenLabs-Music", "family": "elevenlabs", "metadata": { "lastUpdated": "2025-08-29", "openWeights": false, "releaseDate": "2025-08-29" } } ] }, { "id": "poe/elevenlabs-v2.5-turbo", "provider": "poe", "model": "elevenlabs-v2.5-turbo", "displayName": "ElevenLabs-v2.5-Turbo", "family": "elevenlabs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/elevenlabs/elevenlabs-v2.5-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ElevenLabs-v2.5-Turbo" ], "families": [ "elevenlabs" ], "releaseDate": "2024-10-28", "lastUpdated": "2024-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "elevenlabs/elevenlabs-v2.5-turbo", "modelKey": "elevenlabs/elevenlabs-v2.5-turbo", "displayName": "ElevenLabs-v2.5-Turbo", "family": "elevenlabs", "metadata": { "lastUpdated": "2024-10-28", "openWeights": false, "releaseDate": "2024-10-28" } } ] }, { "id": "poe/elevenlabs-v3", "provider": "poe", "model": "elevenlabs-v3", "displayName": "ElevenLabs-v3", "family": "elevenlabs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/elevenlabs/elevenlabs-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "ElevenLabs-v3" ], "families": [ "elevenlabs" ], "releaseDate": "2025-06-05", "lastUpdated": "2025-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "elevenlabs/elevenlabs-v3", "modelKey": "elevenlabs/elevenlabs-v3", "displayName": "ElevenLabs-v3", "family": "elevenlabs", "metadata": { "lastUpdated": "2025-06-05", "openWeights": false, "releaseDate": "2025-06-05" } } ] }, { "id": "poe/ideogram", "provider": "poe", "model": "ideogram", "displayName": "Ideogram", "family": "ideogram", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/ideogramai/ideogram" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 150, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Ideogram" ], "families": [ "ideogram" ], "releaseDate": "2024-04-03", "lastUpdated": "2024-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "ideogramai/ideogram", "modelKey": "ideogramai/ideogram", "displayName": "Ideogram", "family": "ideogram", "metadata": { "lastUpdated": "2024-04-03", "openWeights": false, "releaseDate": "2024-04-03" } } ] }, { "id": "poe/ideogram-v2", "provider": "poe", "model": "ideogram-v2", "displayName": "Ideogram-v2", "family": "ideogram", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/ideogramai/ideogram-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 150, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Ideogram-v2" ], "families": [ "ideogram" ], "releaseDate": "2024-08-21", "lastUpdated": "2024-08-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "ideogramai/ideogram-v2", "modelKey": "ideogramai/ideogram-v2", "displayName": "Ideogram-v2", "family": "ideogram", "metadata": { "lastUpdated": "2024-08-21", "openWeights": false, "releaseDate": "2024-08-21" } } ] }, { "id": "poe/ideogram-v2a", "provider": "poe", "model": "ideogram-v2a", "displayName": "Ideogram-v2a", "family": "ideogram", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/ideogramai/ideogram-v2a" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 150, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Ideogram-v2a" ], "families": [ "ideogram" ], "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "ideogramai/ideogram-v2a", "modelKey": "ideogramai/ideogram-v2a", "displayName": "Ideogram-v2a", "family": "ideogram", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } } ] }, { "id": "poe/ideogram-v2a-turbo", "provider": "poe", "model": "ideogram-v2a-turbo", "displayName": "Ideogram-v2a-Turbo", "family": "ideogram", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/ideogramai/ideogram-v2a-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 150, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Ideogram-v2a-Turbo" ], "families": [ "ideogram" ], "releaseDate": "2025-02-27", "lastUpdated": "2025-02-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "ideogramai/ideogram-v2a-turbo", "modelKey": "ideogramai/ideogram-v2a-turbo", "displayName": "Ideogram-v2a-Turbo", "family": "ideogram", "metadata": { "lastUpdated": "2025-02-27", "openWeights": false, "releaseDate": "2025-02-27" } } ] }, { "id": "poe/ray2", "provider": "poe", "model": "ray2", "displayName": "Ray2", "family": "ray", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/lumalabs/ray2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 5000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Ray2" ], "families": [ "ray" ], "releaseDate": "2025-02-20", "lastUpdated": "2025-02-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "lumalabs/ray2", "modelKey": "lumalabs/ray2", "displayName": "Ray2", "family": "ray", "metadata": { "lastUpdated": "2025-02-20", "openWeights": false, "releaseDate": "2025-02-20" } } ] }, { "id": "poe/runway", "provider": "poe", "model": "runway", "displayName": "Runway", "family": "runway", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/runwayml/runway" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Runway" ], "families": [ "runway" ], "releaseDate": "2024-10-11", "lastUpdated": "2024-10-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "runwayml/runway", "modelKey": "runwayml/runway", "displayName": "Runway", "family": "runway", "metadata": { "lastUpdated": "2024-10-11", "openWeights": false, "releaseDate": "2024-10-11" } } ] }, { "id": "poe/runway-gen-4-turbo", "provider": "poe", "model": "runway-gen-4-turbo", "displayName": "Runway-Gen-4-Turbo", "family": "runway", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/runwayml/runway-gen-4-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Runway-Gen-4-Turbo" ], "families": [ "runway" ], "releaseDate": "2025-05-09", "lastUpdated": "2025-05-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "runwayml/runway-gen-4-turbo", "modelKey": "runwayml/runway-gen-4-turbo", "displayName": "Runway-Gen-4-Turbo", "family": "runway", "metadata": { "lastUpdated": "2025-05-09", "openWeights": false, "releaseDate": "2025-05-09" } } ] }, { "id": "poe/stablediffusionxl", "provider": "poe", "model": "stablediffusionxl", "displayName": "StableDiffusionXL", "family": "stable-diffusion", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/stabilityai/stablediffusionxl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "StableDiffusionXL" ], "families": [ "stable-diffusion" ], "releaseDate": "2023-07-09", "lastUpdated": "2023-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "stabilityai/stablediffusionxl", "modelKey": "stabilityai/stablediffusionxl", "displayName": "StableDiffusionXL", "family": "stable-diffusion", "metadata": { "lastUpdated": "2023-07-09", "openWeights": false, "releaseDate": "2023-07-09" } } ] }, { "id": "poe/tako", "provider": "poe", "model": "tako", "displayName": "Tako", "family": "tako", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/trytako/tako" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Tako" ], "families": [ "tako" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "trytako/tako", "modelKey": "trytako/tako", "displayName": "Tako", "family": "tako", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } } ] }, { "id": "poe/topazlabs", "provider": "poe", "model": "topazlabs", "displayName": "TopazLabs", "family": "topazlabs", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/topazlabs-co/topazlabs" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "TopazLabs" ], "families": [ "topazlabs" ], "releaseDate": "2024-12-03", "lastUpdated": "2024-12-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "topazlabs-co/topazlabs", "modelKey": "topazlabs-co/topazlabs", "displayName": "TopazLabs", "family": "topazlabs", "metadata": { "lastUpdated": "2024-12-03", "openWeights": false, "releaseDate": "2024-12-03" } } ] }, { "id": "poolside/laguna-m.1", "provider": "poolside", "model": "laguna-m.1", "displayName": "Laguna M.1", "sources": [ "models.dev" ], "providers": [ "poolside" ], "aliases": [ "poolside/laguna-m.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poolside", "model": "poolside/laguna-m.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Laguna M.1" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poolside", "providerName": "Poolside", "providerApi": "https://inference.poolside.ai/v1", "providerDoc": "https://platform.poolside.ai", "model": "poolside/laguna-m.1", "modelKey": "poolside/laguna-m.1", "displayName": "Laguna M.1", "metadata": { "lastUpdated": "2026-06-13", "openWeights": false, "releaseDate": "2026-04-28", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "poolside/laguna-xs.2", "provider": "poolside", "model": "laguna-xs.2", "displayName": "Laguna XS.2", "sources": [ "models.dev" ], "providers": [ "poolside" ], "aliases": [ "poolside/laguna-xs.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "poolside", "model": "poolside/laguna-xs.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Laguna XS.2" ], "releaseDate": "2026-04-28", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poolside", "providerName": "Poolside", "providerApi": "https://inference.poolside.ai/v1", "providerDoc": "https://platform.poolside.ai", "model": "poolside/laguna-xs.2", "modelKey": "poolside/laguna-xs.2", "displayName": "Laguna XS.2", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-04-28", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "privatemode-ai/gemma-3-27b", "provider": "privatemode-ai", "model": "gemma-3-27b", "displayName": "Gemma 3 27B", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "privatemode-ai" ], "aliases": [ "privatemode-ai/gemma-3-27b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "privatemode-ai", "model": "gemma-3-27b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Gemma 3 27B" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-08", "releaseDate": "2025-03-12", "lastUpdated": "2025-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "privatemode-ai", "providerName": "Privatemode AI", "providerApi": "http://localhost:8080/v1", "providerDoc": "https://docs.privatemode.ai/api/overview", "model": "gemma-3-27b", "modelKey": "gemma-3-27b", "displayName": "Gemma 3 27B", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2025-03-12", "openWeights": true, "releaseDate": "2025-03-12" } } ] }, { "id": "publicai/alia-40b-instruct-q8-0", "provider": "publicai", "model": "alia-40b-instruct-q8-0", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/BSC-LT/ALIA-40b-instruct_Q8_0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/BSC-LT/ALIA-40b-instruct_Q8_0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/BSC-LT/ALIA-40b-instruct_Q8_0", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/apertus-70b-instruct", "provider": "publicai", "model": "apertus-70b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/swiss-ai/apertus-70b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/swiss-ai/apertus-70b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/swiss-ai/apertus-70b-instruct", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/apertus-8b-instruct", "provider": "publicai", "model": "apertus-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/swiss-ai/apertus-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/swiss-ai/apertus-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/swiss-ai/apertus-8b-instruct", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/gemma-sea-lion-v4-27b-it", "provider": "publicai", "model": "gemma-sea-lion-v4-27b-it", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/olmo-3-32b-think", "provider": "publicai", "model": "olmo-3-32b-think", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/allenai/Olmo-3-32B-Think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/allenai/Olmo-3-32B-Think", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/allenai/Olmo-3-32B-Think", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/olmo-3-7b-instruct", "provider": "publicai", "model": "olmo-3-7b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/allenai/Olmo-3-7B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/allenai/Olmo-3-7B-Instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/allenai/Olmo-3-7B-Instruct", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/olmo-3-7b-think", "provider": "publicai", "model": "olmo-3-7b-think", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/allenai/Olmo-3-7B-Think" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/allenai/Olmo-3-7B-Think", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/allenai/Olmo-3-7B-Think", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "publicai/salamandra-7b-instruct-tools-16k", "provider": "publicai", "model": "salamandra-7b-instruct-tools-16k", "mode": "chat", "sources": [ "litellm" ], "providers": [ "publicai" ], "aliases": [ "publicai/BSC-LT/salamandra-7b-instruct-tools-16k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "publicai", "model": "publicai/BSC-LT/salamandra-7b-instruct-tools-16k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "publicai", "model": "publicai/BSC-LT/salamandra-7b-instruct-tools-16k", "mode": "chat", "metadata": { "source": "https://platform.publicai.co/docs" } } ] }, { "id": "qiniu-ai/doubao-1.5-pro-32k", "provider": "qiniu-ai", "model": "doubao-1.5-pro-32k", "displayName": "Doubao 1.5 Pro 32k", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-1.5-pro-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 12000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao 1.5 Pro 32k" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-1.5-pro-32k", "modelKey": "doubao-1.5-pro-32k", "displayName": "Doubao 1.5 Pro 32k", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "qiniu-ai/doubao-1.5-thinking-pro", "provider": "qiniu-ai", "model": "doubao-1.5-thinking-pro", "displayName": "Doubao 1.5 Thinking Pro", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-1.5-thinking-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao 1.5 Thinking Pro" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-1.5-thinking-pro", "modelKey": "doubao-1.5-thinking-pro", "displayName": "Doubao 1.5 Thinking Pro", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "qiniu-ai/doubao-1.5-vision-pro", "provider": "qiniu-ai", "model": "doubao-1.5-vision-pro", "displayName": "Doubao 1.5 Vision Pro", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-1.5-vision-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao 1.5 Vision Pro" ], "releaseDate": "2025-08-05", "lastUpdated": "2025-08-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-1.5-vision-pro", "modelKey": "doubao-1.5-vision-pro", "displayName": "Doubao 1.5 Vision Pro", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } } ] }, { "id": "qiniu-ai/doubao-seed-1.6", "provider": "qiniu-ai", "model": "doubao-seed-1.6", "displayName": "Doubao-Seed 1.6", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao-Seed 1.6" ], "releaseDate": "2025-08-15", "lastUpdated": "2025-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-1.6", "modelKey": "doubao-seed-1.6", "displayName": "Doubao-Seed 1.6", "metadata": { "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2025-08-15" } } ] }, { "id": "qiniu-ai/doubao-seed-1.6-flash", "provider": "qiniu-ai", "model": "doubao-seed-1.6-flash", "displayName": "Doubao-Seed 1.6 Flash", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-1.6-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao-Seed 1.6 Flash" ], "releaseDate": "2025-08-15", "lastUpdated": "2025-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-1.6-flash", "modelKey": "doubao-seed-1.6-flash", "displayName": "Doubao-Seed 1.6 Flash", "metadata": { "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2025-08-15" } } ] }, { "id": "qiniu-ai/doubao-seed-1.6-thinking", "provider": "qiniu-ai", "model": "doubao-seed-1.6-thinking", "displayName": "Doubao-Seed 1.6 Thinking", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-1.6-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao-Seed 1.6 Thinking" ], "releaseDate": "2025-08-15", "lastUpdated": "2025-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-1.6-thinking", "modelKey": "doubao-seed-1.6-thinking", "displayName": "Doubao-Seed 1.6 Thinking", "metadata": { "lastUpdated": "2025-08-15", "openWeights": false, "releaseDate": "2025-08-15" } } ] }, { "id": "qiniu-ai/doubao-seed-2.0-code", "provider": "qiniu-ai", "model": "doubao-seed-2.0-code", "displayName": "Doubao Seed 2.0 Code", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-2.0-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Code" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-2.0-code", "modelKey": "doubao-seed-2.0-code", "displayName": "Doubao Seed 2.0 Code", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "qiniu-ai/doubao-seed-2.0-lite", "provider": "qiniu-ai", "model": "doubao-seed-2.0-lite", "displayName": "Doubao Seed 2.0 Lite", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-2.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Lite" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-2.0-lite", "modelKey": "doubao-seed-2.0-lite", "displayName": "Doubao Seed 2.0 Lite", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "qiniu-ai/doubao-seed-2.0-mini", "provider": "qiniu-ai", "model": "doubao-seed-2.0-mini", "displayName": "Doubao Seed 2.0 Mini", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-2.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Mini" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-2.0-mini", "modelKey": "doubao-seed-2.0-mini", "displayName": "Doubao Seed 2.0 Mini", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "qiniu-ai/doubao-seed-2.0-pro", "provider": "qiniu-ai", "model": "doubao-seed-2.0-pro", "displayName": "Doubao Seed 2.0 Pro", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/doubao-seed-2.0-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Pro" ], "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "doubao-seed-2.0-pro", "modelKey": "doubao-seed-2.0-pro", "displayName": "Doubao Seed 2.0 Pro", "metadata": { "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14" } } ] }, { "id": "qiniu-ai/gelab-zero-4b-preview", "provider": "qiniu-ai", "model": "gelab-zero-4b-preview", "displayName": "Stepfun-Ai/Gelab Zero 4b Preview", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/stepfun-ai/gelab-zero-4b-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Stepfun-Ai/Gelab Zero 4b Preview" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "stepfun-ai/gelab-zero-4b-preview", "modelKey": "stepfun-ai/gelab-zero-4b-preview", "displayName": "Stepfun-Ai/Gelab Zero 4b Preview", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } } ] }, { "id": "qiniu-ai/kling-v2-6", "provider": "qiniu-ai", "model": "kling-v2-6", "displayName": "Kling-V2 6", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/kling-v2-6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 99999999, "outputTokens": 99999999, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": true }, "metadata": { "displayNames": [ "Kling-V2 6" ], "releaseDate": "2026-01-13", "lastUpdated": "2026-01-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "kling-v2-6", "modelKey": "kling-v2-6", "displayName": "Kling-V2 6", "metadata": { "lastUpdated": "2026-01-13", "openWeights": false, "releaseDate": "2026-01-13" } } ] }, { "id": "qiniu-ai/longcat-flash-chat", "provider": "qiniu-ai", "model": "longcat-flash-chat", "displayName": "Meituan/Longcat-Flash-Chat", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/meituan/longcat-flash-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Meituan/Longcat-Flash-Chat" ], "releaseDate": "2025-11-05", "lastUpdated": "2025-11-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "meituan/longcat-flash-chat", "modelKey": "meituan/longcat-flash-chat", "displayName": "Meituan/Longcat-Flash-Chat", "metadata": { "lastUpdated": "2025-11-05", "openWeights": false, "releaseDate": "2025-11-05" } } ] }, { "id": "qiniu-ai/longcat-flash-lite", "provider": "qiniu-ai", "model": "longcat-flash-lite", "displayName": "Meituan/Longcat-Flash-Lite", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/meituan/longcat-flash-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 320000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Meituan/Longcat-Flash-Lite" ], "releaseDate": "2026-02-06", "lastUpdated": "2026-02-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "meituan/longcat-flash-lite", "modelKey": "meituan/longcat-flash-lite", "displayName": "Meituan/Longcat-Flash-Lite", "metadata": { "lastUpdated": "2026-02-06", "openWeights": false, "releaseDate": "2026-02-06" } } ] }, { "id": "qiniu-ai/mimo-v2-flash", "provider": "qiniu-ai", "model": "mimo-v2-flash", "displayName": "Mimo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/mimo-v2-flash", "qiniu-ai/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "qiniu-ai", "model": "mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } }, { "source": "models.dev", "provider": "qiniu-ai", "model": "xiaomi/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Mimo-V2-Flash", "Xiaomi/Mimo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "mimo-v2-flash", "modelKey": "mimo-v2-flash", "displayName": "Mimo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "xiaomi/mimo-v2-flash", "modelKey": "xiaomi/mimo-v2-flash", "displayName": "Xiaomi/Mimo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16" } } ] }, { "id": "qiniu-ai/step-3.5-flash", "provider": "qiniu-ai", "model": "step-3.5-flash", "displayName": "Stepfun/Step-3.5 Flash", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Stepfun/Step-3.5 Flash" ], "releaseDate": "2026-02-02", "lastUpdated": "2026-02-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "stepfun/step-3.5-flash", "modelKey": "stepfun/step-3.5-flash", "displayName": "Stepfun/Step-3.5 Flash", "metadata": { "lastUpdated": "2026-02-02", "openWeights": false, "releaseDate": "2026-02-02" } } ] }, { "id": "recraft/recraftv2", "provider": "recraft", "model": "recraftv2", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "recraft" ], "aliases": [ "recraft/recraftv2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "recraft", "model": "recraft/recraftv2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.022 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "recraft", "model": "recraft/recraftv2", "mode": "image_generation", "metadata": { "source": "https://www.recraft.ai/docs#pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "recraft/recraftv3", "provider": "recraft", "model": "recraftv3", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "recraft" ], "aliases": [ "recraft/recraftv3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "recraft", "model": "recraft/recraftv3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "recraft", "model": "recraft/recraftv3", "mode": "image_generation", "metadata": { "source": "https://www.recraft.ai/docs#pricing", "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "reducto/parse-legacy", "provider": "reducto", "model": "parse-legacy", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "reducto" ], "aliases": [ "reducto/parse-legacy" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "reducto", "model": "reducto/parse-legacy", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCredit": { "ocr": 0.015 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "reducto", "model": "reducto/parse-legacy", "mode": "ocr", "metadata": { "source": "https://reducto.ai/pricing", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "reducto/parse-v3", "provider": "reducto", "model": "parse-v3", "mode": "ocr", "sources": [ "litellm" ], "providers": [ "reducto" ], "aliases": [ "reducto/parse-v3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "reducto", "model": "reducto/parse-v3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCredit": { "ocr": 0.015 } } ] }, "metadata": { "modes": [ "ocr" ], "supportedEndpoints": [ "/v1/ocr" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "reducto", "model": "reducto/parse-v3", "mode": "ocr", "metadata": { "source": "https://reducto.ai/pricing", "supportedEndpoints": [ "/v1/ocr" ] } } ] }, { "id": "replicate/granite-3.3-8b-instruct", "provider": "replicate", "model": "granite-3.3-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "replicate" ], "aliases": [ "replicate/ibm-granite/granite-3.3-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "replicate", "model": "replicate/ibm-granite/granite-3.3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.03, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/ibm-granite/granite-3.3-8b-instruct", "mode": "chat" } ] }, { "id": "routing-run/gemma-4-31b-it", "provider": "routing-run", "model": "gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/gemma-4-31b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Gemma 4 31B IT" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/gemma-4-31b-it", "modelKey": "route/gemma-4-31b-it", "displayName": "Gemma 4 31B IT", "family": "gemma", "metadata": { "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } } ] }, { "id": "routing-run/mimo-v2.5", "provider": "routing-run", "model": "mimo-v2.5", "displayName": "MiMo V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.45, "output": 1.35 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mimo-v2.5", "modelKey": "route/mimo-v2.5", "displayName": "MiMo V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "routing-run/mimo-v2.5-pro", "provider": "routing-run", "model": "mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.45, "output": 1.35 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mimo-v2.5-pro", "modelKey": "route/mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "routing-run/mimo-v2.5-pro-6bit", "provider": "routing-run", "model": "mimo-v2.5-pro-6bit", "displayName": "MiMo V2.5 Pro 6bit", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/mimo-v2.5-pro-6bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 262144, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/mimo-v2.5-pro-6bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.45, "output": 1.35 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Pro 6bit" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/mimo-v2.5-pro-6bit", "modelKey": "route/mimo-v2.5-pro-6bit", "displayName": "MiMo V2.5 Pro 6bit", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "routing-run/step-3.5-flash", "provider": "routing-run", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.019, "input": 0.096, "output": 0.288 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-02-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/step-3.5-flash", "modelKey": "route/step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-01-29" } } ] }, { "id": "routing-run/step-3.5-flash-2603", "provider": "routing-run", "model": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/step-3.5-flash-2603" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/step-3.5-flash-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash 2603" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/step-3.5-flash-2603", "modelKey": "route/step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02" } } ] }, { "id": "routing-run/stepfun-3.5-flash", "provider": "routing-run", "model": "stepfun-3.5-flash", "displayName": "StepFun 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/stepfun-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "inputTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/stepfun-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.019, "input": 0.096, "output": 0.288 } } ] }, "metadata": { "displayNames": [ "StepFun 3.5 Flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-02-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/stepfun-3.5-flash", "modelKey": "route/stepfun-3.5-flash", "displayName": "StepFun 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "openWeights": true, "releaseDate": "2026-01-29" } } ] }, { "id": "runwayml/eleven-multilingual-v2", "provider": "runwayml", "model": "eleven-multilingual-v2", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/eleven_multilingual_v2" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/eleven_multilingual_v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 3e-7 } } ] }, "metadata": { "modes": [ "audio_speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/eleven_multilingual_v2", "mode": "audio_speech", "metadata": { "metadata": { "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "runwayml/gen3a-turbo", "provider": "runwayml", "model": "gen3a-turbo", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/gen3a_turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/gen3a_turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.05 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/gen3a_turbo", "mode": "video_generation", "metadata": { "metadata": { "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "runwayml/gen4-aleph", "provider": "runwayml", "model": "gen4-aleph", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/gen4_aleph" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/gen4_aleph", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.15 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/gen4_aleph", "mode": "video_generation", "metadata": { "metadata": { "comment": "15 credits per second @ $0.01 per credit = $0.15 per second" }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "runwayml/gen4-image", "provider": "runwayml", "model": "gen4-image", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/gen4_image" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/gen4_image", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.05, "output": 0.05 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/gen4_image", "mode": "image_generation", "metadata": { "metadata": { "comment": "5 credits per 720p image or 8 credits per 1080p image @ $0.01 per credit. Using 5 credits ($0.05) as base cost" }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "runwayml/gen4-image-turbo", "provider": "runwayml", "model": "gen4-image-turbo", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/gen4_image_turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/gen4_image_turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "input": 0.02, "output": 0.02 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/gen4_image_turbo", "mode": "image_generation", "metadata": { "metadata": { "comment": "2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image" }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "runwayml/gen4-turbo", "provider": "runwayml", "model": "gen4-turbo", "mode": "video_generation", "sources": [ "litellm" ], "providers": [ "runwayml" ], "aliases": [ "runwayml/gen4_turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "runwayml", "model": "runwayml/gen4_turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perVideoSecond": { "output": 0.05 } } ] }, "metadata": { "modes": [ "video_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "runwayml", "model": "runwayml/gen4_turbo", "mode": "video_generation", "metadata": { "metadata": { "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" }, "source": "https://docs.dev.runwayml.com/guides/pricing/" } } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-13b", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-13b", "mode": "completion", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-13b", "mode": "completion" } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-13b-f", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-13b-f", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-13b-f" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-13b-f", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-13b-f", "mode": "chat" } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-70b", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-70b", "mode": "completion", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-70b", "mode": "completion" } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-70b-b-f", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-70b-b-f", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-70b-b-f" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-70b-b-f", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-70b-b-f", "mode": "chat" } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-7b", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-7b", "mode": "completion", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-7b", "mode": "completion" } ] }, { "id": "sagemaker/meta-textgeneration-llama-2-7b-f", "provider": "sagemaker", "model": "meta-textgeneration-llama-2-7b-f", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sagemaker" ], "aliases": [ "sagemaker/meta-textgeneration-llama-2-7b-f" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-7b-f", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sagemaker", "model": "sagemaker/meta-textgeneration-llama-2-7b-f", "mode": "chat" } ] }, { "id": "sap-ai-core/anthropic-claude-3-haiku", "provider": "sap-ai-core", "model": "anthropic-claude-3-haiku", "displayName": "anthropic--claude-3-haiku", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-3-haiku" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-3-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0.3, "input": 0.25, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-3-haiku" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-13", "lastUpdated": "2024-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-3-haiku", "modelKey": "anthropic--claude-3-haiku", "displayName": "anthropic--claude-3-haiku", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "openWeights": false, "releaseDate": "2024-03-13" } } ] }, { "id": "sap-ai-core/anthropic-claude-3-opus", "provider": "sap-ai-core", "model": "anthropic-claude-3-opus", "displayName": "anthropic--claude-3-opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-3-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-3-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-3-opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-02-29", "lastUpdated": "2024-02-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-3-opus", "modelKey": "anthropic--claude-3-opus", "displayName": "anthropic--claude-3-opus", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-02-29", "openWeights": false, "releaseDate": "2024-02-29" } } ] }, { "id": "sap-ai-core/anthropic-claude-3-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-3-sonnet", "displayName": "anthropic--claude-3-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-3-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-3-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-3-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2023-08-31", "releaseDate": "2024-03-04", "lastUpdated": "2024-03-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-3-sonnet", "modelKey": "anthropic--claude-3-sonnet", "displayName": "anthropic--claude-3-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-04", "openWeights": false, "releaseDate": "2024-03-04" } } ] }, { "id": "sap-ai-core/anthropic-claude-3.5-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-3.5-sonnet", "displayName": "anthropic--claude-3.5-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-3.5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-3.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-3.5-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2024-04-30", "releaseDate": "2024-10-22", "lastUpdated": "2024-10-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-3.5-sonnet", "modelKey": "anthropic--claude-3.5-sonnet", "displayName": "anthropic--claude-3.5-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-04-30", "lastUpdated": "2024-10-22", "openWeights": false, "releaseDate": "2024-10-22" } } ] }, { "id": "sap-ai-core/anthropic-claude-3.7-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-3.7-sonnet", "displayName": "anthropic--claude-3.7-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-3.7-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-3.7-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-3.7-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2024-10-31", "releaseDate": "2025-02-24", "lastUpdated": "2025-02-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-3.7-sonnet", "modelKey": "anthropic--claude-3.7-sonnet", "displayName": "anthropic--claude-3.7-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2024-10-31", "lastUpdated": "2025-02-24", "openWeights": false, "releaseDate": "2025-02-24" } } ] }, { "id": "sap-ai-core/anthropic-claude-4-opus", "provider": "sap-ai-core", "model": "anthropic-claude-4-opus", "displayName": "anthropic--claude-4-opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.5, "cacheWrite": 18.75, "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4-opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4-opus", "modelKey": "anthropic--claude-4-opus", "displayName": "anthropic--claude-4-opus", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "sap-ai-core/anthropic-claude-4-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-4-sonnet", "displayName": "anthropic--claude-4-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-03-31", "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4-sonnet", "modelKey": "anthropic--claude-4-sonnet", "displayName": "anthropic--claude-4-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.5-haiku", "provider": "sap-ai-core", "model": "anthropic-claude-4.5-haiku", "displayName": "anthropic--claude-4.5-haiku", "family": "claude-haiku", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.5-haiku" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.5-haiku", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1.25, "input": 1, "output": 5 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.5-haiku" ], "families": [ "claude-haiku" ], "knowledgeCutoff": "2025-02-28", "releaseDate": "2025-10-15", "lastUpdated": "2025-10-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.5-haiku", "modelKey": "anthropic--claude-4.5-haiku", "displayName": "anthropic--claude-4.5-haiku", "family": "claude-haiku", "metadata": { "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "openWeights": false, "releaseDate": "2025-10-15" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.5-opus", "provider": "sap-ai-core", "model": "anthropic-claude-4.5-opus", "displayName": "anthropic--claude-4.5-opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.5-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.5-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.5-opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05", "releaseDate": "2025-11-24", "lastUpdated": "2025-11-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.5-opus", "modelKey": "anthropic--claude-4.5-opus", "displayName": "anthropic--claude-4.5-opus", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2025-11-24", "openWeights": false, "releaseDate": "2025-11-24" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.5-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-4.5-sonnet", "displayName": "anthropic--claude-4.5-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.5-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.5-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.5-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-07-31", "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.5-sonnet", "modelKey": "anthropic--claude-4.5-sonnet", "displayName": "anthropic--claude-4.5-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.6-opus", "provider": "sap-ai-core", "model": "anthropic-claude-4.6-opus", "displayName": "anthropic--claude-4.6-opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.6-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.6-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.6-opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-02-05", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.6-opus", "modelKey": "anthropic--claude-4.6-opus", "displayName": "anthropic--claude-4.6-opus", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.6-sonnet", "provider": "sap-ai-core", "model": "anthropic-claude-4.6-sonnet", "displayName": "anthropic--claude-4.6-sonnet", "family": "claude-sonnet", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.6-sonnet" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 64000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.6-sonnet", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 3.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.6-sonnet" ], "families": [ "claude-sonnet" ], "knowledgeCutoff": "2025-08", "releaseDate": "2026-02-17", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.6-sonnet", "modelKey": "anthropic--claude-4.6-sonnet", "displayName": "anthropic--claude-4.6-sonnet", "family": "claude-sonnet", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "sap-ai-core/anthropic-claude-4.7-opus", "provider": "sap-ai-core", "model": "anthropic-claude-4.7-opus", "displayName": "anthropic--claude-4.7-opus", "family": "claude-opus", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/anthropic--claude-4.7-opus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "anthropic--claude-4.7-opus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "cacheWrite": 6.25, "input": 5, "output": 25 } } ] }, "metadata": { "displayNames": [ "anthropic--claude-4.7-opus" ], "families": [ "claude-opus" ], "knowledgeCutoff": "2026-01-31", "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "anthropic--claude-4.7-opus", "modelKey": "anthropic--claude-4.7-opus", "displayName": "anthropic--claude-4.7-opus", "family": "claude-opus", "metadata": { "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } } ] }, { "id": "sap-ai-core/sonar", "provider": "sap-ai-core", "model": "sonar", "displayName": "sonar", "family": "sonar", "sources": [ "models.dev" ], "providers": [ "sap-ai-core" ], "aliases": [ "sap-ai-core/sonar" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "sap-ai-core", "model": "sonar", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 1 } } ] }, "metadata": { "displayNames": [ "sonar" ], "families": [ "sonar" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2024-01-01", "lastUpdated": "2025-09-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sap-ai-core", "providerName": "SAP AI Core", "providerDoc": "https://help.sap.com/docs/sap-ai-core", "model": "sonar", "modelKey": "sonar", "displayName": "sonar", "family": "sonar", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "sarvam/sarvam-105b", "provider": "sarvam", "model": "sarvam-105b", "displayName": "Sarvam-105B", "family": "sarvam", "sources": [ "models.dev" ], "providers": [ "sarvam" ], "aliases": [ "sarvam/sarvam-105b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Sarvam-105B" ], "families": [ "sarvam" ], "releaseDate": "2026-02-18", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sarvam", "providerName": "Sarvam AI", "providerApi": "https://api.sarvam.ai/v1", "providerDoc": "https://docs.sarvam.ai/api-reference-docs/getting-started/models", "model": "sarvam-105b", "modelKey": "sarvam-105b", "displayName": "Sarvam-105B", "family": "sarvam", "metadata": { "lastUpdated": "2026-03-06", "openWeights": true, "releaseDate": "2026-02-18", "reasoningOptions": [ { "type": "effort", "values": [ null, "low", "medium", "high" ] } ] } } ] }, { "id": "sarvam/sarvam-30b", "provider": "sarvam", "model": "sarvam-30b", "displayName": "Sarvam-30B", "family": "sarvam", "sources": [ "models.dev" ], "providers": [ "sarvam" ], "aliases": [ "sarvam/sarvam-30b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Sarvam-30B" ], "families": [ "sarvam" ], "releaseDate": "2026-02-18", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "sarvam", "providerName": "Sarvam AI", "providerApi": "https://api.sarvam.ai/v1", "providerDoc": "https://docs.sarvam.ai/api-reference-docs/getting-started/models", "model": "sarvam-30b", "modelKey": "sarvam-30b", "displayName": "Sarvam-30B", "family": "sarvam", "metadata": { "lastUpdated": "2026-03-06", "openWeights": true, "releaseDate": "2026-02-18", "reasoningOptions": [ { "type": "effort", "values": [ null, "low", "medium", "high" ] } ] } } ] }, { "id": "sarvam/sarvam-m", "provider": "sarvam", "model": "sarvam-m", "mode": "chat", "sources": [ "litellm" ], "providers": [ "sarvam" ], "aliases": [ "sarvam/sarvam-m" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "sarvam", "model": "sarvam/sarvam-m", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 }, "extra": { "cache_creation_input_token_cost_above_1hr": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "sarvam", "model": "sarvam/sarvam-m", "mode": "chat" } ] }, { "id": "scaleway/bge-multilingual-gemma2", "provider": "scaleway", "model": "bge-multilingual-gemma2", "displayName": "BGE Multilingual Gemma2", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "scaleway" ], "aliases": [ "scaleway/bge-multilingual-gemma2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8191, "outputTokens": 3072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "scaleway", "model": "bge-multilingual-gemma2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "displayNames": [ "BGE Multilingual Gemma2" ], "families": [ "gemma" ], "releaseDate": "2024-07-26", "lastUpdated": "2025-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "bge-multilingual-gemma2", "modelKey": "bge-multilingual-gemma2", "displayName": "BGE Multilingual Gemma2", "family": "gemma", "metadata": { "lastUpdated": "2025-06-15", "openWeights": false, "releaseDate": "2024-07-26" } } ] }, { "id": "scaleway/gemma-3-27b-it", "provider": "scaleway", "model": "gemma-3-27b-it", "displayName": "Gemma-3-27B-IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "scaleway" ], "aliases": [ "scaleway/gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 40000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "scaleway", "model": "gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Gemma-3-27B-IT" ], "families": [ "gemma" ], "knowledgeCutoff": "2024-12", "releaseDate": "2024-12-01", "lastUpdated": "2026-03-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "gemma-3-27b-it", "modelKey": "gemma-3-27b-it", "displayName": "Gemma-3-27B-IT", "family": "gemma", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-17", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "scaleway/gemma-4-26b-a4b-it", "provider": "scaleway", "model": "gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "scaleway" ], "aliases": [ "scaleway/gemma-4-26b-a4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "scaleway", "model": "gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Gemma 4 26B A4B IT" ], "families": [ "gemma" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-01", "lastUpdated": "2026-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "scaleway", "providerName": "Scaleway", "providerApi": "https://api.scaleway.ai/v1", "providerDoc": "https://www.scaleway.com/en/docs/generative-apis/", "model": "gemma-4-26b-a4b-it", "modelKey": "gemma-4-26b-a4b-it", "displayName": "Gemma 4 26B A4B IT", "family": "gemma", "status": "beta", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-05-22", "openWeights": true, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "searxng/search", "provider": "searxng", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "searxng" ], "aliases": [ "searxng/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "searxng", "model": "searxng/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "searxng", "model": "searxng/search", "mode": "search", "metadata": { "metadata": { "notes": "SearXNG is an open-source metasearch engine. Free to use when self-hosted or using public instances." } } } ] }, { "id": "serper/search", "provider": "serper", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "serper" ], "aliases": [ "serper/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "serper", "model": "serper/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.001 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "serper", "model": "serper/search", "mode": "search", "metadata": { "metadata": { "notes": "Serper Google Search API. Pricing: $1.00/1k queries (Starter), $0.75/1k (Standard), $0.50/1k (Scale), $0.30/1k (Ultimate)." } } } ] }, { "id": "siliconflow-cn/ernie-4.5-300b-a47b", "provider": "siliconflow-cn", "model": "ernie-4.5-300b-a47b", "displayName": "baidu/ERNIE-4.5-300B-A47B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/baidu/ERNIE-4.5-300B-A47B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "baidu/ERNIE-4.5-300B-A47B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "baidu/ERNIE-4.5-300B-A47B" ], "families": [ "ernie" ], "releaseDate": "2025-07-02", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "baidu/ERNIE-4.5-300B-A47B", "modelKey": "baidu/ERNIE-4.5-300B-A47B", "displayName": "baidu/ERNIE-4.5-300B-A47B", "family": "ernie", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-02" } } ] }, { "id": "siliconflow-cn/hunyuan-a13b-instruct", "provider": "siliconflow-cn", "model": "hunyuan-a13b-instruct", "displayName": "tencent/Hunyuan-A13B-Instruct", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/tencent/Hunyuan-A13B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "tencent/Hunyuan-A13B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "tencent/Hunyuan-A13B-Instruct" ], "families": [ "hunyuan" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "tencent/Hunyuan-A13B-Instruct", "modelKey": "tencent/Hunyuan-A13B-Instruct", "displayName": "tencent/Hunyuan-A13B-Instruct", "family": "hunyuan", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-06-30", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "siliconflow-cn/kat-dev", "provider": "siliconflow-cn", "model": "kat-dev", "displayName": "Kwaipilot/KAT-Dev", "family": "kat-coder", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/Kwaipilot/KAT-Dev" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "Kwaipilot/KAT-Dev", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Kwaipilot/KAT-Dev" ], "families": [ "kat-coder" ], "releaseDate": "2025-09-27", "lastUpdated": "2026-01-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Kwaipilot/KAT-Dev", "modelKey": "Kwaipilot/KAT-Dev", "displayName": "Kwaipilot/KAT-Dev", "family": "kat-coder", "metadata": { "lastUpdated": "2026-01-16", "openWeights": false, "releaseDate": "2025-09-27" } } ] }, { "id": "siliconflow-cn/ling-flash-2.0", "provider": "siliconflow-cn", "model": "ling-flash-2.0", "displayName": "inclusionAI/Ling-flash-2.0", "family": "ling", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/inclusionAI/Ling-flash-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "inclusionAI/Ling-flash-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "inclusionAI/Ling-flash-2.0" ], "families": [ "ling" ], "releaseDate": "2025-09-18", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "inclusionAI/Ling-flash-2.0", "modelKey": "inclusionAI/Ling-flash-2.0", "displayName": "inclusionAI/Ling-flash-2.0", "family": "ling", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-18" } } ] }, { "id": "siliconflow-cn/paddleocr-vl-1.5", "provider": "siliconflow-cn", "model": "paddleocr-vl-1.5", "displayName": "PaddlePaddle/PaddleOCR-VL-1.5", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/PaddlePaddle/PaddleOCR-VL-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "PaddlePaddle/PaddleOCR-VL-1.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "PaddlePaddle/PaddleOCR-VL-1.5" ], "releaseDate": "2026-01-29", "lastUpdated": "2026-01-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "PaddlePaddle/PaddleOCR-VL-1.5", "modelKey": "PaddlePaddle/PaddleOCR-VL-1.5", "displayName": "PaddlePaddle/PaddleOCR-VL-1.5", "metadata": { "lastUpdated": "2026-01-29", "openWeights": true, "releaseDate": "2026-01-29" } } ] }, { "id": "siliconflow-cn/seed-oss-36b-instruct", "provider": "siliconflow-cn", "model": "seed-oss-36b-instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "ByteDance-Seed/Seed-OSS-36B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "ByteDance-Seed/Seed-OSS-36B-Instruct" ], "families": [ "seed" ], "releaseDate": "2025-09-04", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "ByteDance-Seed/Seed-OSS-36B-Instruct", "modelKey": "ByteDance-Seed/Seed-OSS-36B-Instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-04" } } ] }, { "id": "siliconflow-cn/step-3.5-flash", "provider": "siliconflow-cn", "model": "step-3.5-flash", "displayName": "stepfun-ai/Step-3.5-Flash", "family": "step", "sources": [ "models.dev" ], "providers": [ "siliconflow-cn" ], "aliases": [ "siliconflow-cn/stepfun-ai/Step-3.5-Flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow-cn", "model": "stepfun-ai/Step-3.5-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "stepfun-ai/Step-3.5-Flash" ], "families": [ "step" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "stepfun-ai/Step-3.5-Flash", "modelKey": "stepfun-ai/Step-3.5-Flash", "displayName": "stepfun-ai/Step-3.5-Flash", "family": "step", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } } ] }, { "id": "siliconflow/ernie-4.5-300b-a47b", "provider": "siliconflow", "model": "ernie-4.5-300b-a47b", "displayName": "baidu/ERNIE-4.5-300B-A47B", "family": "ernie", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/baidu/ERNIE-4.5-300B-A47B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "baidu/ERNIE-4.5-300B-A47B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 1.1 } } ] }, "metadata": { "displayNames": [ "baidu/ERNIE-4.5-300B-A47B" ], "families": [ "ernie" ], "releaseDate": "2025-07-02", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "baidu/ERNIE-4.5-300B-A47B", "modelKey": "baidu/ERNIE-4.5-300B-A47B", "displayName": "baidu/ERNIE-4.5-300B-A47B", "family": "ernie", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-02" } } ] }, { "id": "siliconflow/hunyuan-a13b-instruct", "provider": "siliconflow", "model": "hunyuan-a13b-instruct", "displayName": "tencent/Hunyuan-A13B-Instruct", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/tencent/Hunyuan-A13B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "tencent/Hunyuan-A13B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "tencent/Hunyuan-A13B-Instruct" ], "families": [ "hunyuan" ], "releaseDate": "2025-06-30", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "tencent/Hunyuan-A13B-Instruct", "modelKey": "tencent/Hunyuan-A13B-Instruct", "displayName": "tencent/Hunyuan-A13B-Instruct", "family": "hunyuan", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-06-30", "reasoningOptions": [ { "type": "toggle" }, { "type": "budget_tokens", "min": 128, "max": 32768 } ] } } ] }, { "id": "siliconflow/hy3-preview", "provider": "siliconflow", "model": "hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/tencent/Hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "tencent/Hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.029, "input": 0.066, "output": 0.26 } } ] }, "metadata": { "displayNames": [ "Hy3 preview" ], "families": [ "Hy" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "tencent/Hy3-preview", "modelKey": "tencent/Hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "metadata": { "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "budget_tokens", "min": 128, "max": 32768 } ] } } ] }, { "id": "siliconflow/ling-flash-2.0", "provider": "siliconflow", "model": "ling-flash-2.0", "displayName": "inclusionAI/Ling-flash-2.0", "family": "ling", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/inclusionAI/Ling-flash-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "inclusionAI/Ling-flash-2.0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "inclusionAI/Ling-flash-2.0" ], "families": [ "ling" ], "releaseDate": "2025-09-18", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "inclusionAI/Ling-flash-2.0", "modelKey": "inclusionAI/Ling-flash-2.0", "displayName": "inclusionAI/Ling-flash-2.0", "family": "ling", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-18" } } ] }, { "id": "siliconflow/seed-oss-36b-instruct", "provider": "siliconflow", "model": "seed-oss-36b-instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "ByteDance-Seed/Seed-OSS-36B-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "ByteDance-Seed/Seed-OSS-36B-Instruct" ], "families": [ "seed" ], "releaseDate": "2025-09-04", "lastUpdated": "2025-11-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "ByteDance-Seed/Seed-OSS-36B-Instruct", "modelKey": "ByteDance-Seed/Seed-OSS-36B-Instruct", "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "family": "seed", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-09-04" } } ] }, { "id": "siliconflow/step-3.5-flash", "provider": "siliconflow", "model": "step-3.5-flash", "displayName": "stepfun-ai/Step-3.5-Flash", "family": "step", "sources": [ "models.dev" ], "providers": [ "siliconflow" ], "aliases": [ "siliconflow/stepfun-ai/Step-3.5-Flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 262000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "siliconflow", "model": "stepfun-ai/Step-3.5-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "stepfun-ai/Step-3.5-Flash" ], "families": [ "step" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "stepfun-ai/Step-3.5-Flash", "modelKey": "stepfun-ai/Step-3.5-Flash", "displayName": "stepfun-ai/Step-3.5-Flash", "family": "step", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } } ] }, { "id": "snowflake-cortex/openai-gpt-4.1", "provider": "snowflake-cortex", "model": "openai-gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1047576, "outputTokens": 32768, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "GPT-4.1" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-04", "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-4.1", "modelKey": "openai-gpt-4.1", "displayName": "GPT-4.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } } ] }, { "id": "snowflake-cortex/openai-gpt-5", "provider": "snowflake-cortex", "model": "openai-gpt-5", "displayName": "GPT-5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT-5" ], "families": [ "gpt" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5", "modelKey": "openai-gpt-5", "displayName": "GPT-5", "family": "gpt", "status": "beta", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } } ] }, { "id": "snowflake-cortex/openai-gpt-5-mini", "provider": "snowflake-cortex", "model": "openai-gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 272000, "inputTokens": 272000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT-5 Mini" ], "families": [ "gpt-mini" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5-mini", "modelKey": "openai-gpt-5-mini", "displayName": "GPT-5 Mini", "family": "gpt-mini", "status": "beta", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } } ] }, { "id": "snowflake-cortex/openai-gpt-5-nano", "provider": "snowflake-cortex", "model": "openai-gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT-5 Nano" ], "families": [ "gpt-nano" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-05-30", "releaseDate": "2025-08-07", "lastUpdated": "2025-08-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5-nano", "modelKey": "openai-gpt-5-nano", "displayName": "GPT-5 Nano", "family": "gpt-nano", "status": "beta", "metadata": { "knowledgeCutoff": "2024-05-30", "lastUpdated": "2025-08-07", "openWeights": false, "releaseDate": "2025-08-07" } } ] }, { "id": "snowflake-cortex/openai-gpt-5.1", "provider": "snowflake-cortex", "model": "openai-gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT-5.1" ], "families": [ "gpt" ], "knowledgeCutoff": "2024-09-30", "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5.1", "modelKey": "openai-gpt-5.1", "displayName": "GPT-5.1", "family": "gpt", "metadata": { "knowledgeCutoff": "2024-09-30", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13" } } ] }, { "id": "snowflake-cortex/openai-gpt-5.2", "provider": "snowflake-cortex", "model": "openai-gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "GPT-5.2" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5.2", "modelKey": "openai-gpt-5.2", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "snowflake-cortex/openai-gpt-5.4", "provider": "snowflake-cortex", "model": "openai-gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5.4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-03-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5.4", "modelKey": "openai-gpt-5.4", "displayName": "GPT-5.4", "family": "gpt", "status": "beta", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-05", "openWeights": false, "releaseDate": "2026-03-05" } } ] }, { "id": "snowflake-cortex/openai-gpt-5.5", "provider": "snowflake-cortex", "model": "openai-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/openai-gpt-5.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-04-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "openai-gpt-5.5", "modelKey": "openai-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "status": "beta", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-04-23", "openWeights": false, "releaseDate": "2026-04-23" } } ] }, { "id": "snowflake-cortex/snowflake-llama3.3-70b", "provider": "snowflake-cortex", "model": "snowflake-llama3.3-70b", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "sources": [ "models.dev" ], "providers": [ "snowflake-cortex" ], "aliases": [ "snowflake-cortex/snowflake-llama3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Llama-3.3-70B-Instruct" ], "families": [ "llama" ], "knowledgeCutoff": "2023-12", "releaseDate": "2024-12-06", "lastUpdated": "2024-12-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "snowflake-cortex", "providerName": "Snowflake Cortex", "providerApi": "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", "providerDoc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api", "model": "snowflake-llama3.3-70b", "modelKey": "snowflake-llama3.3-70b", "displayName": "Llama-3.3-70B-Instruct", "family": "llama", "metadata": { "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "openWeights": true, "releaseDate": "2024-12-06" } } ] }, { "id": "snowflake/gemma-7b", "provider": "snowflake", "model": "gemma-7b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/gemma-7b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/gemma-7b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/gemma-7b", "mode": "chat" } ] }, { "id": "snowflake/jamba-1.5-large", "provider": "snowflake", "model": "jamba-1.5-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/jamba-1.5-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/jamba-1.5-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/jamba-1.5-large", "mode": "chat" } ] }, { "id": "snowflake/jamba-1.5-mini", "provider": "snowflake", "model": "jamba-1.5-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/jamba-1.5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/jamba-1.5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/jamba-1.5-mini", "mode": "chat" } ] }, { "id": "snowflake/jamba-instruct", "provider": "snowflake", "model": "jamba-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/jamba-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/jamba-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/jamba-instruct", "mode": "chat" } ] }, { "id": "snowflake/llama2-70b-chat", "provider": "snowflake", "model": "llama2-70b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama2-70b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama2-70b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama2-70b-chat", "mode": "chat" } ] }, { "id": "snowflake/llama3-70b", "provider": "snowflake", "model": "llama3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3-70b", "mode": "chat" } ] }, { "id": "snowflake/llama3-8b", "provider": "snowflake", "model": "llama3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3-8b", "mode": "chat" } ] }, { "id": "snowflake/llama3.1-405b", "provider": "snowflake", "model": "llama3.1-405b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.1-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.1-405b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.1-405b", "mode": "chat" } ] }, { "id": "snowflake/llama3.1-70b", "provider": "snowflake", "model": "llama3.1-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.1-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.1-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.1-70b", "mode": "chat" } ] }, { "id": "snowflake/llama3.1-8b", "provider": "snowflake", "model": "llama3.1-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.1-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.1-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.24, "output": 0.24 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.1-8b", "mode": "chat" } ] }, { "id": "snowflake/llama3.2-1b", "provider": "snowflake", "model": "llama3.2-1b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.2-1b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.2-1b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.2-1b", "mode": "chat" } ] }, { "id": "snowflake/llama3.2-3b", "provider": "snowflake", "model": "llama3.2-3b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.2-3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.2-3b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.2-3b", "mode": "chat" } ] }, { "id": "snowflake/llama3.3-70b", "provider": "snowflake", "model": "llama3.3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama3.3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama3.3-70b", "mode": "chat" } ] }, { "id": "snowflake/llama4-maverick", "provider": "snowflake", "model": "llama4-maverick", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/llama4-maverick" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/llama4-maverick", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.24, "output": 0.97 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/llama4-maverick", "mode": "chat" } ] }, { "id": "snowflake/openai-gpt-4.1", "provider": "snowflake", "model": "openai-gpt-4.1", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/openai-gpt-4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/openai-gpt-4.1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.5, "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/openai-gpt-4.1", "mode": "chat" } ] }, { "id": "snowflake/openai-gpt-5", "provider": "snowflake", "model": "openai-gpt-5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/openai-gpt-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 300000, "inputTokens": 300000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/openai-gpt-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.125, "input": 1.25, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/openai-gpt-5", "mode": "chat" } ] }, { "id": "snowflake/openai-gpt-5-mini", "provider": "snowflake", "model": "openai-gpt-5-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/openai-gpt-5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/openai-gpt-5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/openai-gpt-5-mini", "mode": "chat" } ] }, { "id": "snowflake/openai-gpt-5-nano", "provider": "snowflake", "model": "openai-gpt-5-nano", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/openai-gpt-5-nano" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 5000000, "inputTokens": 5000000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/openai-gpt-5-nano", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/openai-gpt-5-nano", "mode": "chat" } ] }, { "id": "snowflake/reka-core", "provider": "snowflake", "model": "reka-core", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/reka-core" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/reka-core", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/reka-core", "mode": "chat" } ] }, { "id": "snowflake/reka-flash", "provider": "snowflake", "model": "reka-flash", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/reka-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 100000, "inputTokens": 100000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/reka-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/reka-flash", "mode": "chat" } ] }, { "id": "snowflake/snowflake-arctic", "provider": "snowflake", "model": "snowflake-arctic", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/snowflake-arctic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/snowflake-arctic", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/snowflake-arctic", "mode": "chat" } ] }, { "id": "snowflake/snowflake-arctic-embed-l-v2.0", "provider": "snowflake", "model": "snowflake-arctic-embed-l-v2.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/snowflake-arctic-embed-l-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/snowflake-arctic-embed-l-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/snowflake-arctic-embed-l-v2.0", "mode": "embedding" } ] }, { "id": "snowflake/snowflake-arctic-embed-m-v2.0", "provider": "snowflake", "model": "snowflake-arctic-embed-m-v2.0", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/snowflake-arctic-embed-m-v2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/snowflake-arctic-embed-m-v2.0", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.07, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/snowflake-arctic-embed-m-v2.0", "mode": "embedding" } ] }, { "id": "snowflake/snowflake-llama-3.1-405b", "provider": "snowflake", "model": "snowflake-llama-3.1-405b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/snowflake-llama-3.1-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/snowflake-llama-3.1-405b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/snowflake-llama-3.1-405b", "mode": "chat" } ] }, { "id": "snowflake/snowflake-llama-3.3-70b", "provider": "snowflake", "model": "snowflake-llama-3.3-70b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "snowflake" ], "aliases": [ "snowflake/snowflake-llama-3.3-70b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "snowflake", "model": "snowflake/snowflake-llama-3.3-70b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.72, "output": 0.72 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "snowflake", "model": "snowflake/snowflake-llama-3.3-70b", "mode": "chat" } ] }, { "id": "soniox/stt-async-v4", "provider": "soniox", "model": "stt-async-v4", "mode": "audio_transcription", "sources": [ "litellm" ], "providers": [ "soniox" ], "aliases": [ "soniox/stt-async-v4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "soniox", "model": "soniox/stt-async-v4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perAudioSecond": { "output": 0.0000277778 }, "extra": { "input_cost_per_second": 0 } } ] }, "metadata": { "modes": [ "audio_transcription" ], "supportedEndpoints": [ "/v1/audio/transcriptions" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "soniox", "model": "soniox/stt-async-v4", "mode": "audio_transcription", "metadata": { "source": "https://soniox.com/pricing", "supportedEndpoints": [ "/v1/audio/transcriptions" ] } } ] }, { "id": "stability/conservative", "provider": "stability", "model": "conservative", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/conservative" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/conservative", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/conservative", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/creative", "provider": "stability", "model": "creative", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/creative" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/creative", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.06 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/creative", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/erase", "provider": "stability", "model": "erase", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/erase" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/erase", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/erase", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/fast", "provider": "stability", "model": "fast", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/fast" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.002 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/fast", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/inpaint", "provider": "stability", "model": "inpaint", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/inpaint" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/inpaint", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/inpaint", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/outpaint", "provider": "stability", "model": "outpaint", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/outpaint" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/outpaint", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.004 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/outpaint", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/remove-background", "provider": "stability", "model": "remove-background", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/remove-background" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/remove-background", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/remove-background", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/replace-background-and-relight", "provider": "stability", "model": "replace-background-and-relight", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/replace-background-and-relight" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/replace-background-and-relight", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.008 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/replace-background-and-relight", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/sd3", "provider": "stability", "model": "sd3", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.065 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3-large", "provider": "stability", "model": "sd3-large", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3-large" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.065 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3-large", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3-large-turbo", "provider": "stability", "model": "sd3-large-turbo", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3-large-turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3-large-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3-large-turbo", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3-medium", "provider": "stability", "model": "sd3-medium", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3-medium" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.035 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3-medium", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3.5-large", "provider": "stability", "model": "sd3.5-large", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3.5-large" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3.5-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.065 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3.5-large", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3.5-large-turbo", "provider": "stability", "model": "sd3.5-large-turbo", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3.5-large-turbo" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3.5-large-turbo", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.04 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3.5-large-turbo", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/sd3.5-medium", "provider": "stability", "model": "sd3.5-medium", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sd3.5-medium" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sd3.5-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.035 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sd3.5-medium", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/search-and-recolor", "provider": "stability", "model": "search-and-recolor", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/search-and-recolor" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/search-and-recolor", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/search-and-recolor", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/search-and-replace", "provider": "stability", "model": "search-and-replace", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/search-and-replace" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/search-and-replace", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/search-and-replace", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/sketch", "provider": "stability", "model": "sketch", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/sketch" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/sketch", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/sketch", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/stable-image-core", "provider": "stability", "model": "stable-image-core", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/stable-image-core" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/stable-image-core", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.03 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/stable-image-core", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/stable-image-ultra", "provider": "stability", "model": "stable-image-ultra", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/stable-image-ultra" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/stable-image-ultra", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.08 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/images/generations" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/stable-image-ultra", "mode": "image_generation", "metadata": { "supportedEndpoints": [ "/v1/images/generations" ] } } ] }, { "id": "stability/structure", "provider": "stability", "model": "structure", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/structure" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/structure", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/structure", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/style", "provider": "stability", "model": "style", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/style" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/style", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.005 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/style", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stability/style-transfer", "provider": "stability", "model": "style-transfer", "mode": "image_edit", "sources": [ "litellm" ], "providers": [ "stability" ], "aliases": [ "stability/style-transfer" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "stability", "model": "stability/style-transfer", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.008 } } ] }, "metadata": { "modes": [ "image_edit" ], "supportedEndpoints": [ "/v1/images/edits" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "stability", "model": "stability/style-transfer", "mode": "image_edit", "metadata": { "supportedEndpoints": [ "/v1/images/edits" ] } } ] }, { "id": "stackit/e5-mistral-7b-instruct", "provider": "stackit", "model": "e5-mistral-7b-instruct", "displayName": "E5 Mistral 7B", "family": "mistral", "sources": [ "models.dev" ], "providers": [ "stackit" ], "aliases": [ "stackit/intfloat/e5-mistral-7b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stackit", "model": "intfloat/e5-mistral-7b-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.02, "output": 0.02 } } ] }, "metadata": { "displayNames": [ "E5 Mistral 7B" ], "families": [ "mistral" ], "releaseDate": "2023-12-11", "lastUpdated": "2023-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stackit", "providerName": "STACKIT", "providerApi": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "providerDoc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "model": "intfloat/e5-mistral-7b-instruct", "modelKey": "intfloat/e5-mistral-7b-instruct", "displayName": "E5 Mistral 7B", "family": "mistral", "metadata": { "lastUpdated": "2023-12-11", "openWeights": true, "releaseDate": "2023-12-11" } } ] }, { "id": "stepfun-ai/step-3.5-flash", "provider": "stepfun-ai", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "stepfun-ai" ], "aliases": [ "stepfun-ai/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun-ai", "model": "step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun-ai", "providerName": "StepFun AI", "providerApi": "https://api.stepfun.ai/step_plan/v1", "providerDoc": "https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code", "model": "step-3.5-flash", "modelKey": "step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-15", "openWeights": true, "releaseDate": "2026-01-29" } } ] }, { "id": "stepfun-ai/step-3.5-flash-2603", "provider": "stepfun-ai", "model": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "sources": [ "models.dev" ], "providers": [ "stepfun-ai" ], "aliases": [ "stepfun-ai/step-3.5-flash-2603" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun-ai", "model": "step-3.5-flash-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash 2603" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun-ai", "providerName": "StepFun AI", "providerApi": "https://api.stepfun.ai/step_plan/v1", "providerDoc": "https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code", "model": "step-3.5-flash-2603", "modelKey": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } } ] }, { "id": "stepfun/step-1-32k", "provider": "stepfun", "model": "step-1-32k", "displayName": "Step 1 (32K)", "sources": [ "models.dev" ], "providers": [ "stepfun" ], "aliases": [ "stepfun/step-1-32k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun", "model": "step-1-32k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.41, "input": 2.05, "output": 9.59 } } ] }, "metadata": { "displayNames": [ "Step 1 (32K)" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-01-01", "lastUpdated": "2026-02-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun", "providerName": "StepFun", "providerApi": "https://api.stepfun.com/v1", "providerDoc": "https://platform.stepfun.com/docs/zh/overview/concept", "model": "step-1-32k", "modelKey": "step-1-32k", "displayName": "Step 1 (32K)", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "stepfun/step-2-16k", "provider": "stepfun", "model": "step-2-16k", "displayName": "Step 2 (16K)", "sources": [ "models.dev" ], "providers": [ "stepfun" ], "aliases": [ "stepfun/step-2-16k" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun", "model": "step-2-16k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.04, "input": 5.21, "output": 16.44 } } ] }, "metadata": { "displayNames": [ "Step 2 (16K)" ], "knowledgeCutoff": "2024-06", "releaseDate": "2025-01-01", "lastUpdated": "2026-02-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun", "providerName": "StepFun", "providerApi": "https://api.stepfun.com/v1", "providerDoc": "https://platform.stepfun.com/docs/zh/overview/concept", "model": "step-2-16k", "modelKey": "step-2-16k", "displayName": "Step 2 (16K)", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "stepfun/step-3.5-flash", "provider": "stepfun", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "stepfun" ], "aliases": [ "stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun", "model": "step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-06-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun", "providerName": "StepFun", "providerApi": "https://api.stepfun.com/v1", "providerDoc": "https://platform.stepfun.com/docs/zh/overview/concept", "model": "step-3.5-flash", "modelKey": "step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-15", "openWeights": true, "releaseDate": "2026-01-29" } } ] }, { "id": "stepfun/step-3.5-flash-2603", "provider": "stepfun", "model": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "sources": [ "models.dev" ], "providers": [ "stepfun" ], "aliases": [ "stepfun/step-3.5-flash-2603" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "stepfun", "model": "step-3.5-flash-2603", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash 2603" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "stepfun", "providerName": "StepFun", "providerApi": "https://api.stepfun.com/v1", "providerDoc": "https://platform.stepfun.com/docs/zh/overview/concept", "model": "step-3.5-flash-2603", "modelKey": "step-3.5-flash-2603", "displayName": "Step 3.5 Flash 2603", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } } ] }, { "id": "synthetic/nvidia-nemotron-3-super-120b-a12b-nvfp4", "provider": "synthetic", "model": "nvidia-nemotron-3-super-120b-a12b-nvfp4", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "synthetic" ], "aliases": [ "synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "synthetic", "model": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 0.3, "output": 1 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-04", "releaseDate": "2026-03-11", "lastUpdated": "2026-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "modelKey": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "displayName": "Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-04", "lastUpdated": "2026-04-03", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "tavily/search", "provider": "tavily", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "tavily" ], "aliases": [ "tavily/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "tavily", "model": "tavily/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.008 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "tavily", "model": "tavily/search", "mode": "search" } ] }, { "id": "tavily/search-advanced", "provider": "tavily", "model": "search-advanced", "mode": "search", "sources": [ "litellm" ], "providers": [ "tavily" ], "aliases": [ "tavily/search-advanced" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "tavily", "model": "tavily/search-advanced", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.016 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "tavily", "model": "tavily/search-advanced", "mode": "search" } ] }, { "id": "tencent-coding-plan/hunyuan-2.0-instruct", "provider": "tencent-coding-plan", "model": "hunyuan-2.0-instruct", "displayName": "Tencent HY 2.0 Instruct", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "tencent-coding-plan" ], "aliases": [ "tencent-coding-plan/hunyuan-2.0-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-coding-plan", "model": "hunyuan-2.0-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Tencent HY 2.0 Instruct" ], "families": [ "hunyuan" ], "releaseDate": "2026-03-08", "lastUpdated": "2026-03-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "hunyuan-2.0-instruct", "modelKey": "hunyuan-2.0-instruct", "displayName": "Tencent HY 2.0 Instruct", "family": "hunyuan", "metadata": { "lastUpdated": "2026-03-08", "openWeights": false, "releaseDate": "2026-03-08" } } ] }, { "id": "tencent-coding-plan/hunyuan-2.0-thinking", "provider": "tencent-coding-plan", "model": "hunyuan-2.0-thinking", "displayName": "Tencent HY 2.0 Think", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "tencent-coding-plan" ], "aliases": [ "tencent-coding-plan/hunyuan-2.0-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-coding-plan", "model": "hunyuan-2.0-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Tencent HY 2.0 Think" ], "families": [ "hunyuan" ], "releaseDate": "2026-03-08", "lastUpdated": "2026-03-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "hunyuan-2.0-thinking", "modelKey": "hunyuan-2.0-thinking", "displayName": "Tencent HY 2.0 Think", "family": "hunyuan", "metadata": { "lastUpdated": "2026-03-08", "openWeights": false, "releaseDate": "2026-03-08" } } ] }, { "id": "tencent-coding-plan/hunyuan-t1", "provider": "tencent-coding-plan", "model": "hunyuan-t1", "displayName": "Hunyuan-T1", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "tencent-coding-plan" ], "aliases": [ "tencent-coding-plan/hunyuan-t1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-coding-plan", "model": "hunyuan-t1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Hunyuan-T1" ], "families": [ "hunyuan" ], "releaseDate": "2026-03-08", "lastUpdated": "2026-03-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "hunyuan-t1", "modelKey": "hunyuan-t1", "displayName": "Hunyuan-T1", "family": "hunyuan", "metadata": { "lastUpdated": "2026-03-08", "openWeights": false, "releaseDate": "2026-03-08" } } ] }, { "id": "tencent-coding-plan/hunyuan-turbos", "provider": "tencent-coding-plan", "model": "hunyuan-turbos", "displayName": "Hunyuan-TurboS", "family": "hunyuan", "sources": [ "models.dev" ], "providers": [ "tencent-coding-plan" ], "aliases": [ "tencent-coding-plan/hunyuan-turbos" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-coding-plan", "model": "hunyuan-turbos", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Hunyuan-TurboS" ], "families": [ "hunyuan" ], "releaseDate": "2026-03-08", "lastUpdated": "2026-03-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "hunyuan-turbos", "modelKey": "hunyuan-turbos", "displayName": "Hunyuan-TurboS", "family": "hunyuan", "metadata": { "lastUpdated": "2026-03-08", "openWeights": false, "releaseDate": "2026-03-08" } } ] }, { "id": "tencent-coding-plan/tc-code-latest", "provider": "tencent-coding-plan", "model": "tc-code-latest", "displayName": "Auto", "family": "auto", "sources": [ "models.dev" ], "providers": [ "tencent-coding-plan" ], "aliases": [ "tencent-coding-plan/tc-code-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-coding-plan", "model": "tc-code-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Auto" ], "families": [ "auto" ], "releaseDate": "2026-03-08", "lastUpdated": "2026-03-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "tc-code-latest", "modelKey": "tc-code-latest", "displayName": "Auto", "family": "auto", "metadata": { "lastUpdated": "2026-03-08", "openWeights": false, "releaseDate": "2026-03-08" } } ] }, { "id": "tencent-tokenhub/hy3-preview", "provider": "tencent-tokenhub", "model": "hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "sources": [ "models.dev" ], "providers": [ "tencent-tokenhub" ], "aliases": [ "tencent-tokenhub/hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "tencent-tokenhub", "model": "hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Hy3 preview" ], "families": [ "Hy" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-tokenhub", "providerName": "Tencent TokenHub", "providerApi": "https://tokenhub.tencentmaas.com/v1", "providerDoc": "https://cloud.tencent.com/document/product/1823/130050", "model": "hy3-preview", "modelKey": "hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "metadata": { "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20" } } ] }, { "id": "text-completion-inception/mercury-edit-2", "provider": "text-completion-inception", "model": "mercury-edit-2", "mode": "completion", "sources": [ "litellm" ], "providers": [ "text-completion-inception" ], "aliases": [ "text-completion-inception/mercury-edit-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "text-completion-inception", "model": "text-completion-inception/mercury-edit-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-inception", "model": "text-completion-inception/mercury-edit-2", "mode": "completion" } ] }, { "id": "text-completion-openai/babbage-002", "provider": "text-completion-openai", "model": "babbage-002", "mode": "completion", "sources": [ "litellm" ], "providers": [ "text-completion-openai" ], "aliases": [ "text-completion-openai/babbage-002" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "text-completion-openai", "model": "babbage-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 0.4 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "babbage-002", "mode": "completion" } ] }, { "id": "text-completion-openai/davinci-002", "provider": "text-completion-openai", "model": "davinci-002", "mode": "completion", "sources": [ "litellm" ], "providers": [ "text-completion-openai" ], "aliases": [ "text-completion-openai/davinci-002" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "text-completion-openai", "model": "davinci-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 2 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "davinci-002", "mode": "completion" } ] }, { "id": "text-completion-openai/ft:babbage-002", "provider": "text-completion-openai", "model": "ft:babbage-002", "mode": "completion", "sources": [ "litellm" ], "providers": [ "text-completion-openai" ], "aliases": [ "text-completion-openai/ft:babbage-002" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "text-completion-openai", "model": "ft:babbage-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.6, "output": 1.6 }, "extra": { "input_cost_per_token_batches": 2e-7, "output_cost_per_token_batches": 2e-7 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "ft:babbage-002", "mode": "completion" } ] }, { "id": "text-completion-openai/ft:davinci-002", "provider": "text-completion-openai", "model": "ft:davinci-002", "mode": "completion", "sources": [ "litellm" ], "providers": [ "text-completion-openai" ], "aliases": [ "text-completion-openai/ft:davinci-002" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16384, "inputTokens": 16384, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "text-completion-openai", "model": "ft:davinci-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 12, "output": 12 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000001 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "text-completion-openai", "model": "ft:davinci-002", "mode": "completion" } ] }, { "id": "the-grid-ai/agent-max", "provider": "the-grid-ai", "model": "agent-max", "displayName": "Agent Max", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/agent-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "Agent Max" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "agent-max", "modelKey": "agent-max", "displayName": "Agent Max", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/agent-prime", "provider": "the-grid-ai", "model": "agent-prime", "displayName": "Agent Prime", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/agent-prime" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Agent Prime" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "agent-prime", "modelKey": "agent-prime", "displayName": "Agent Prime", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/agent-standard", "provider": "the-grid-ai", "model": "agent-standard", "displayName": "Agent Standard", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/agent-standard" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Agent Standard" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "agent-standard", "modelKey": "agent-standard", "displayName": "Agent Standard", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/code-max", "provider": "the-grid-ai", "model": "code-max", "displayName": "Code Max", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/code-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "Code Max" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "code-max", "modelKey": "code-max", "displayName": "Code Max", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/code-prime", "provider": "the-grid-ai", "model": "code-prime", "displayName": "Code Prime", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/code-prime" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Code Prime" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "code-prime", "modelKey": "code-prime", "displayName": "Code Prime", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/code-standard", "provider": "the-grid-ai", "model": "code-standard", "displayName": "Code Standard", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/code-standard" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Code Standard" ], "statuses": [ "beta" ], "releaseDate": "2026-05-04", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "code-standard", "modelKey": "code-standard", "displayName": "Code Standard", "status": "beta", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-05-04" } } ] }, { "id": "the-grid-ai/text-max", "provider": "the-grid-ai", "model": "text-max", "displayName": "Text Max", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/text-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "metadata": { "displayNames": [ "Text Max" ], "releaseDate": "2026-03-24", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "text-max", "modelKey": "text-max", "displayName": "Text Max", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-03-24" } } ] }, { "id": "the-grid-ai/text-prime", "provider": "the-grid-ai", "model": "text-prime", "displayName": "Text Prime", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/text-prime" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 30000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Text Prime" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "text-prime", "modelKey": "text-prime", "displayName": "Text Prime", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-02-26" } } ] }, { "id": "the-grid-ai/text-standard", "provider": "the-grid-ai", "model": "text-standard", "displayName": "Text Standard", "sources": [ "models.dev" ], "providers": [ "the-grid-ai" ], "aliases": [ "the-grid-ai/text-standard" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Text Standard" ], "releaseDate": "2026-02-26", "lastUpdated": "2026-05-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "the-grid-ai", "providerName": "The Grid AI", "providerApi": "https://api.thegrid.ai/v1", "providerDoc": "https://thegrid.ai/docs", "model": "text-standard", "modelKey": "text-standard", "displayName": "Text Standard", "metadata": { "lastUpdated": "2026-05-19", "openWeights": false, "releaseDate": "2026-02-26" } } ] }, { "id": "together-ai/bge-base-en-v1.5", "provider": "together-ai", "model": "bge-base-en-v1.5", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/BAAI/bge-base-en-v1.5", "together_ai/baai/bge-base-en-v1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/baai/bge-base-en-v1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/BAAI/bge-base-en-v1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/baai/bge-base-en-v1.5", "mode": "embedding" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/BAAI/bge-base-en-v1.5", "mode": "embedding" } ] }, { "id": "together-ai/together-ai-21.1b-41b", "provider": "together-ai", "model": "together-ai-21.1b-41b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-21.1b-41b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-21.1b-41b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-21.1b-41b", "mode": "chat" } ] }, { "id": "together-ai/together-ai-4.1b-8b", "provider": "together-ai", "model": "together-ai-4.1b-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-4.1b-8b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-4.1b-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-4.1b-8b", "mode": "chat" } ] }, { "id": "together-ai/together-ai-41.1b-80b", "provider": "together-ai", "model": "together-ai-41.1b-80b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-41.1b-80b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-41.1b-80b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 0.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-41.1b-80b", "mode": "chat" } ] }, { "id": "together-ai/together-ai-8.1b-21b", "provider": "together-ai", "model": "together-ai-8.1b-21b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-8.1b-21b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000, "maxTokens": 1000, "outputTokens": 1000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-8.1b-21b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-8.1b-21b", "mode": "chat" } ] }, { "id": "together-ai/together-ai-81.1b-110b", "provider": "together-ai", "model": "together-ai-81.1b-110b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-81.1b-110b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-81.1b-110b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.8, "output": 1.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-81.1b-110b", "mode": "chat" } ] }, { "id": "together-ai/together-ai-embedding-151m-to-350m", "provider": "together-ai", "model": "together-ai-embedding-151m-to-350m", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-embedding-151m-to-350m" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-embedding-151m-to-350m", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.016, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-embedding-151m-to-350m", "mode": "embedding" } ] }, { "id": "together-ai/together-ai-embedding-up-to-150m", "provider": "together-ai", "model": "together-ai-embedding-up-to-150m", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-embedding-up-to-150m" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-embedding-up-to-150m", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.008, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-embedding-up-to-150m", "mode": "embedding" } ] }, { "id": "together-ai/together-ai-up-to-4b", "provider": "together-ai", "model": "together-ai-up-to-4b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/together-ai-up-to-4b" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together-ai-up-to-4b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together-ai-up-to-4b", "mode": "chat" } ] }, { "id": "togetherai/cogito-v2-1-671b", "provider": "togetherai", "model": "cogito-v2-1-671b", "displayName": "Cogito v2.1 671B", "family": "cogito", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/deepcogito/cogito-v2-1-671b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 163840, "outputTokens": 163840, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "deepcogito/cogito-v2-1-671b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 1.25 } } ] }, "metadata": { "displayNames": [ "Cogito v2.1 671B" ], "families": [ "cogito" ], "releaseDate": "2025-11-13", "lastUpdated": "2025-11-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "deepcogito/cogito-v2-1-671b", "modelKey": "deepcogito/cogito-v2-1-671b", "displayName": "Cogito v2.1 671B", "family": "cogito", "metadata": { "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2025-11-13", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "togetherai/gemma-4-31b-it", "provider": "togetherai", "model": "gemma-4-31b-it", "displayName": "Pearl AI Gemma 4 31B Instruct", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/pearl-ai/gemma-4-31b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "pearl-ai/gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.28, "output": 0.86 } } ] }, "metadata": { "displayNames": [ "Pearl AI Gemma 4 31B Instruct" ], "families": [ "gemma" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "pearl-ai/gemma-4-31b-it", "modelKey": "pearl-ai/gemma-4-31b-it", "displayName": "Pearl AI Gemma 4 31B Instruct", "family": "gemma", "metadata": { "lastUpdated": "2026-04-07", "openWeights": false, "releaseDate": "2026-04-07" } } ] }, { "id": "togetherai/lfm2-24b-a2b", "provider": "togetherai", "model": "lfm2-24b-a2b", "displayName": "LFM2-24B-A2B", "family": "liquid", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/LiquidAI/LFM2-24B-A2B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "LiquidAI/LFM2-24B-A2B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.03, "output": 0.12 } } ] }, "metadata": { "displayNames": [ "LFM2-24B-A2B" ], "families": [ "liquid" ], "releaseDate": "2026-02-25", "lastUpdated": "2026-02-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "LiquidAI/LFM2-24B-A2B", "modelKey": "LiquidAI/LFM2-24B-A2B", "displayName": "LFM2-24B-A2B", "family": "liquid", "metadata": { "lastUpdated": "2026-02-25", "openWeights": true, "releaseDate": "2026-02-25" } } ] }, { "id": "togetherai/nemotron-3-ultra-550b-a55b", "provider": "togetherai", "model": "nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/nvidia/nemotron-3-ultra-550b-a55b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512300, "outputTokens": 512300, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "nvidia/nemotron-3-ultra-550b-a55b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.6, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Ultra 550B A55B" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "nvidia/nemotron-3-ultra-550b-a55b", "modelKey": "nvidia/nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra 550B A55B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "togetherai/rnj-1-instruct", "provider": "togetherai", "model": "rnj-1-instruct", "displayName": "Rnj-1 Instruct", "family": "rnj", "sources": [ "models.dev" ], "providers": [ "togetherai" ], "aliases": [ "togetherai/essentialai/Rnj-1-Instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "togetherai", "model": "essentialai/Rnj-1-Instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Rnj-1 Instruct" ], "families": [ "rnj" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-05", "lastUpdated": "2025-12-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "essentialai/Rnj-1-Instruct", "modelKey": "essentialai/Rnj-1-Instruct", "displayName": "Rnj-1 Instruct", "family": "rnj", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-05", "openWeights": true, "releaseDate": "2025-12-05" } } ] }, { "id": "umans-ai-coding-plan/umans-coder", "provider": "umans-ai-coding-plan", "model": "umans-coder", "displayName": "Umans Coder", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Umans Coder" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-coder", "modelKey": "umans-coder", "displayName": "Umans Coder", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "umans-ai-coding-plan/umans-flash", "provider": "umans-ai-coding-plan", "model": "umans-flash", "displayName": "Umans Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Umans Flash" ], "families": [ "qwen" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-flash", "modelKey": "umans-flash", "displayName": "Umans Flash", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "umans-ai-coding-plan/umans-glm-5.1", "provider": "umans-ai-coding-plan", "model": "umans-glm-5.1", "displayName": "GLM 5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-glm-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM 5.1" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-glm-5.1", "modelKey": "umans-glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "umans-ai-coding-plan/umans-glm-5.2", "provider": "umans-ai-coding-plan", "model": "umans-glm-5.2", "displayName": "GLM 5.2", "family": "glm", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-glm-5.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 405504, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM 5.2" ], "families": [ "glm" ], "releaseDate": "2026-06-13", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-glm-5.2", "modelKey": "umans-glm-5.2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } } ] }, { "id": "umans-ai-coding-plan/umans-kimi-k2.7", "provider": "umans-ai-coding-plan", "model": "umans-kimi-k2.7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-kimi-k2.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-kimi-k2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-kimi-k2.7", "modelKey": "umans-kimi-k2.7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "umans-ai-coding-plan/umans-qwen3.6-35b-a3b", "provider": "umans-ai-coding-plan", "model": "umans-qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B A3B", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "umans-ai-coding-plan" ], "aliases": [ "umans-ai-coding-plan/umans-qwen3.6-35b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai-coding-plan", "model": "umans-qwen3.6-35b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Qwen3.6 35B A3B" ], "families": [ "qwen" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai-coding-plan", "providerName": "Umans AI Coding Plan", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs", "model": "umans-qwen3.6-35b-a3b", "modelKey": "umans-qwen3.6-35b-a3b", "displayName": "Qwen3.6 35B A3B", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "umans-ai/umans-coder", "provider": "umans-ai", "model": "umans-coder", "displayName": "Umans Coder", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "umans-ai" ], "aliases": [ "umans-ai/umans-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai", "model": "umans-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } } ] }, "metadata": { "displayNames": [ "Umans Coder" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai", "providerName": "Umans AI", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs/orgs", "model": "umans-coder", "modelKey": "umans-coder", "displayName": "Umans Coder", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "umans-ai/umans-flash", "provider": "umans-ai", "model": "umans-flash", "displayName": "Umans Flash", "family": "qwen", "sources": [ "models.dev" ], "providers": [ "umans-ai" ], "aliases": [ "umans-ai/umans-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai", "model": "umans-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.15, "output": 1 } } ] }, "metadata": { "displayNames": [ "Umans Flash" ], "families": [ "qwen" ], "releaseDate": "2026-04-17", "lastUpdated": "2026-04-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai", "providerName": "Umans AI", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs/orgs", "model": "umans-flash", "modelKey": "umans-flash", "displayName": "Umans Flash", "family": "qwen", "metadata": { "lastUpdated": "2026-04-17", "openWeights": true, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "umans-ai/umans-glm-5.1", "provider": "umans-ai", "model": "umans-glm-5.1", "displayName": "GLM 5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "umans-ai" ], "aliases": [ "umans-ai/umans-glm-5.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai", "model": "umans-glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.29, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "GLM 5.1" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai", "providerName": "Umans AI", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs/orgs", "model": "umans-glm-5.1", "modelKey": "umans-glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "umans-ai/umans-glm-5.2", "provider": "umans-ai", "model": "umans-glm-5.2", "displayName": "GLM 5.2", "family": "glm", "sources": [ "models.dev" ], "providers": [ "umans-ai" ], "aliases": [ "umans-ai/umans-glm-5.2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 405504, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai", "model": "umans-glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "GLM 5.2" ], "families": [ "glm" ], "releaseDate": "2026-06-13", "lastUpdated": "2026-06-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai", "providerName": "Umans AI", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs/orgs", "model": "umans-glm-5.2", "modelKey": "umans-glm-5.2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } } ] }, { "id": "umans-ai/umans-kimi-k2.7", "provider": "umans-ai", "model": "umans-kimi-k2.7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "sources": [ "models.dev" ], "providers": [ "umans-ai" ], "aliases": [ "umans-ai/umans-kimi-k2.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "umans-ai", "model": "umans-kimi-k2.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.19, "input": 0.95, "output": 4 } } ] }, "metadata": { "displayNames": [ "Kimi K2.7 Code" ], "families": [ "kimi-k2" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-06-12", "lastUpdated": "2026-06-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "umans-ai", "providerName": "Umans AI", "providerApi": "https://api.code.umans.ai/v1", "providerDoc": "https://app.umans.ai/offers/code/docs/orgs", "model": "umans-kimi-k2.7", "modelKey": "umans-kimi-k2.7", "displayName": "Kimi K2.7 Code", "family": "kimi-k2", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-12", "openWeights": true, "releaseDate": "2026-06-12" } } ] }, { "id": "upstage/solar-mini", "provider": "upstage", "model": "solar-mini", "displayName": "solar-mini", "family": "solar-mini", "sources": [ "models.dev" ], "providers": [ "upstage" ], "aliases": [ "upstage/solar-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "upstage", "model": "solar-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "solar-mini" ], "families": [ "solar-mini" ], "knowledgeCutoff": "2024-09", "releaseDate": "2024-06-12", "lastUpdated": "2025-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "upstage", "providerName": "Upstage", "providerApi": "https://api.upstage.ai/v1/solar", "providerDoc": "https://developers.upstage.ai/docs/apis/chat", "model": "solar-mini", "modelKey": "solar-mini", "displayName": "solar-mini", "family": "solar-mini", "metadata": { "knowledgeCutoff": "2024-09", "lastUpdated": "2025-04-22", "openWeights": false, "releaseDate": "2024-06-12" } } ] }, { "id": "upstage/solar-pro2", "provider": "upstage", "model": "solar-pro2", "displayName": "solar-pro2", "family": "solar-pro", "sources": [ "models.dev" ], "providers": [ "upstage" ], "aliases": [ "upstage/solar-pro2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "upstage", "model": "solar-pro2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "solar-pro2" ], "families": [ "solar-pro" ], "knowledgeCutoff": "2025-03", "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "upstage", "providerName": "Upstage", "providerApi": "https://api.upstage.ai/v1/solar", "providerDoc": "https://developers.upstage.ai/docs/apis/chat", "model": "solar-pro2", "modelKey": "solar-pro2", "displayName": "solar-pro2", "family": "solar-pro", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "high" ] } ] } } ] }, { "id": "upstage/solar-pro3", "provider": "upstage", "model": "solar-pro3", "displayName": "solar-pro3", "family": "solar-pro", "sources": [ "models.dev" ], "providers": [ "upstage" ], "aliases": [ "upstage/solar-pro3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "upstage", "model": "solar-pro3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.25 } } ] }, "metadata": { "displayNames": [ "solar-pro3" ], "families": [ "solar-pro" ], "knowledgeCutoff": "2025-03", "releaseDate": "2026-01", "lastUpdated": "2026-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "upstage", "providerName": "Upstage", "providerApi": "https://api.upstage.ai/v1/solar", "providerDoc": "https://developers.upstage.ai/docs/apis/chat", "model": "solar-pro3", "modelKey": "solar-pro3", "displayName": "solar-pro3", "family": "solar-pro", "metadata": { "knowledgeCutoff": "2025-03", "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "v0/v0-1.0-md", "provider": "v0", "model": "v0-1.0-md", "displayName": "v0-1.0-md", "family": "v0", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "v0" ], "aliases": [ "v0/v0-1.0-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "v0", "model": "v0-1.0-md", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "v0", "model": "v0/v0-1.0-md", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "v0-1.0-md" ], "families": [ "v0" ], "modes": [ "chat" ], "releaseDate": "2025-05-22", "lastUpdated": "2025-05-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "v0", "providerName": "v0", "providerDoc": "https://sdk.vercel.ai/providers/ai-sdk-providers/vercel", "model": "v0-1.0-md", "modelKey": "v0-1.0-md", "displayName": "v0-1.0-md", "family": "v0", "metadata": { "lastUpdated": "2025-05-22", "openWeights": false, "releaseDate": "2025-05-22" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "v0", "model": "v0/v0-1.0-md", "mode": "chat" } ] }, { "id": "v0/v0-1.5-lg", "provider": "v0", "model": "v0-1.5-lg", "displayName": "v0-1.5-lg", "family": "v0", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "v0" ], "aliases": [ "v0/v0-1.5-lg" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512000, "inputTokens": 512000, "maxTokens": 512000, "outputTokens": 512000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "v0", "model": "v0-1.5-lg", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 15, "output": 75 } }, { "source": "litellm", "provider": "v0", "model": "v0/v0-1.5-lg", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 15, "output": 75 } } ] }, "metadata": { "displayNames": [ "v0-1.5-lg" ], "families": [ "v0" ], "modes": [ "chat" ], "releaseDate": "2025-06-09", "lastUpdated": "2025-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "v0", "providerName": "v0", "providerDoc": "https://sdk.vercel.ai/providers/ai-sdk-providers/vercel", "model": "v0-1.5-lg", "modelKey": "v0-1.5-lg", "displayName": "v0-1.5-lg", "family": "v0", "metadata": { "lastUpdated": "2025-06-09", "openWeights": false, "releaseDate": "2025-06-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "v0", "model": "v0/v0-1.5-lg", "mode": "chat" } ] }, { "id": "v0/v0-1.5-md", "provider": "v0", "model": "v0-1.5-md", "displayName": "v0-1.5-md", "family": "v0", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "v0" ], "aliases": [ "v0/v0-1.5-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "parallelFunctionCalling": true, "rerank": false, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "v0", "model": "v0-1.5-md", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "v0", "model": "v0/v0-1.5-md", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "v0-1.5-md" ], "families": [ "v0" ], "modes": [ "chat" ], "releaseDate": "2025-06-09", "lastUpdated": "2025-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "v0", "providerName": "v0", "providerDoc": "https://sdk.vercel.ai/providers/ai-sdk-providers/vercel", "model": "v0-1.5-md", "modelKey": "v0-1.5-md", "displayName": "v0-1.5-md", "family": "v0", "metadata": { "lastUpdated": "2025-06-09", "openWeights": false, "releaseDate": "2025-06-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "v0", "model": "v0/v0-1.5-md", "mode": "chat" } ] }, { "id": "venice/aion-labs-aion-2-0", "provider": "venice", "model": "aion-labs-aion-2-0", "displayName": "Aion 2.0", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/aion-labs-aion-2-0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "aion-labs-aion-2-0", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.25, "input": 1, "output": 2 } } ] }, "metadata": { "displayNames": [ "Aion 2.0" ], "releaseDate": "2026-03-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "aion-labs-aion-2-0", "modelKey": "aion-labs-aion-2-0", "displayName": "Aion 2.0", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "venice/arcee-trinity-large-thinking", "provider": "venice", "model": "arcee-trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/arcee-trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "arcee-trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3125, "output": 1.125 } } ] }, "metadata": { "displayNames": [ "Trinity Large Thinking" ], "families": [ "trinity" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "arcee-trinity-large-thinking", "modelKey": "arcee-trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "venice/gemma-4-uncensored", "provider": "venice", "model": "gemma-4-uncensored", "displayName": "Gemma 4 Uncensored", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/gemma-4-uncensored" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "gemma-4-uncensored", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1625, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Gemma 4 Uncensored" ], "families": [ "gemma" ], "releaseDate": "2026-04-13", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "gemma-4-uncensored", "modelKey": "gemma-4-uncensored", "displayName": "Gemma 4 Uncensored", "family": "gemma", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-13" } } ] }, { "id": "venice/google-gemma-3-27b-it", "provider": "venice", "model": "google-gemma-3-27b-it", "displayName": "Google Gemma 3 27B Instruct", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/google-gemma-3-27b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "google-gemma-3-27b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "Google Gemma 3 27B Instruct" ], "families": [ "gemma" ], "releaseDate": "2025-11-04", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "google-gemma-3-27b-it", "modelKey": "google-gemma-3-27b-it", "displayName": "Google Gemma 3 27B Instruct", "family": "gemma", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-11-04" } } ] }, { "id": "venice/google-gemma-4-26b-a4b-it", "provider": "venice", "model": "google-gemma-4-26b-a4b-it", "displayName": "Google Gemma 4 26B A4B Instruct", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/google-gemma-4-26b-a4b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "google-gemma-4-26b-a4b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1625, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Google Gemma 4 26B A4B Instruct" ], "families": [ "gemma" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "google-gemma-4-26b-a4b-it", "modelKey": "google-gemma-4-26b-a4b-it", "displayName": "Google Gemma 4 26B A4B Instruct", "family": "gemma", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-02", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/google-gemma-4-31b-it", "provider": "venice", "model": "google-gemma-4-31b-it", "displayName": "Google Gemma 4 31B Instruct", "family": "gemma", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/google-gemma-4-31b-it" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "google-gemma-4-31b-it", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09, "input": 0.12, "output": 0.36 } } ] }, "metadata": { "displayNames": [ "Google Gemma 4 31B Instruct" ], "families": [ "gemma" ], "releaseDate": "2026-04-03", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "google-gemma-4-31b-it", "modelKey": "google-gemma-4-31b-it", "displayName": "Google Gemma 4 31B Instruct", "family": "gemma", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-03", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/hermes-3-llama-3.1-405b", "provider": "venice", "model": "hermes-3-llama-3.1-405b", "displayName": "Hermes 3 Llama 3.1 405b", "family": "hermes", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/hermes-3-llama-3.1-405b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "hermes-3-llama-3.1-405b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3 } } ] }, "metadata": { "displayNames": [ "Hermes 3 Llama 3.1 405b" ], "families": [ "hermes" ], "releaseDate": "2025-09-25", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "hermes-3-llama-3.1-405b", "modelKey": "hermes-3-llama-3.1-405b", "displayName": "Hermes 3 Llama 3.1 405b", "family": "hermes", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-09-25" } } ] }, { "id": "venice/mercury-2", "provider": "venice", "model": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 50000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03125, "input": 0.3125, "output": 0.9375 } } ] }, "metadata": { "displayNames": [ "Mercury 2" ], "families": [ "mercury" ], "releaseDate": "2026-02-20", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "mercury-2", "modelKey": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-20", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/nvidia-nemotron-3-nano-30b-a3b", "provider": "venice", "model": "nvidia-nemotron-3-nano-30b-a3b", "displayName": "NVIDIA Nemotron 3 Nano 30B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/nvidia-nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "nvidia-nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.075, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Nano 30B" ], "families": [ "nemotron" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "nvidia-nemotron-3-nano-30b-a3b", "modelKey": "nvidia-nemotron-3-nano-30b-a3b", "displayName": "NVIDIA Nemotron 3 Nano 30B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-01-27" } } ] }, { "id": "venice/nvidia-nemotron-3-ultra-550b-a55b", "provider": "venice", "model": "nvidia-nemotron-3-ultra-550b-a55b", "displayName": "NVIDIA Nemotron 3 Ultra", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/nvidia-nemotron-3-ultra-550b-a55b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "nvidia-nemotron-3-ultra-550b-a55b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1875, "input": 0.625, "output": 3.125 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Ultra" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "nvidia-nemotron-3-ultra-550b-a55b", "modelKey": "nvidia-nemotron-3-ultra-550b-a55b", "displayName": "NVIDIA Nemotron 3 Ultra", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/nvidia-nemotron-cascade-2-30b-a3b", "provider": "venice", "model": "nvidia-nemotron-cascade-2-30b-a3b", "displayName": "Nemotron Cascade 2 30B A3B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/nvidia-nemotron-cascade-2-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "nvidia-nemotron-cascade-2-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Nemotron Cascade 2 30B A3B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "nvidia-nemotron-cascade-2-30b-a3b", "modelKey": "nvidia-nemotron-cascade-2-30b-a3b", "displayName": "Nemotron Cascade 2 30B A3B", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-03-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/olafangensan-glm-4.7-flash-heretic", "provider": "venice", "model": "olafangensan-glm-4.7-flash-heretic", "displayName": "GLM 4.7 Flash Heretic", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/olafangensan-glm-4.7-flash-heretic" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 24000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "olafangensan-glm-4.7-flash-heretic", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash Heretic" ], "families": [ "glm" ], "releaseDate": "2026-02-04", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "olafangensan-glm-4.7-flash-heretic", "modelKey": "olafangensan-glm-4.7-flash-heretic", "displayName": "GLM 4.7 Flash Heretic", "family": "glm", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-04", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-4o-2024-11-20", "provider": "venice", "model": "openai-gpt-4o-2024-11-20", "displayName": "GPT-4o", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-4o-2024-11-20" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-4o-2024-11-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.125, "output": 12.5 } } ] }, "metadata": { "displayNames": [ "GPT-4o" ], "families": [ "gpt" ], "knowledgeCutoff": "2023-09", "releaseDate": "2026-02-28", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-4o-2024-11-20", "modelKey": "openai-gpt-4o-2024-11-20", "displayName": "GPT-4o", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-28" } } ] }, { "id": "venice/openai-gpt-4o-mini-2024-07-18", "provider": "venice", "model": "openai-gpt-4o-mini-2024-07-18", "displayName": "GPT-4o Mini", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-4o-mini-2024-07-18" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-4o-mini-2024-07-18", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09375, "input": 0.1875, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "GPT-4o Mini" ], "families": [ "gpt" ], "knowledgeCutoff": "2023-09", "releaseDate": "2026-02-28", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-4o-mini-2024-07-18", "modelKey": "openai-gpt-4o-mini-2024-07-18", "displayName": "GPT-4o Mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2023-09", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-28" } } ] }, { "id": "venice/openai-gpt-52", "provider": "venice", "model": "openai-gpt-52", "displayName": "GPT-5.2", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-52" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 272000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-52", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.219, "input": 2.19, "output": 17.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.2" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2025-12-13", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-52", "modelKey": "openai-gpt-52", "displayName": "GPT-5.2", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2025-12-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-52-codex", "provider": "venice", "model": "openai-gpt-52-codex", "displayName": "GPT-5.2 Codex", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-52-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 272000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-52-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.219, "input": 2.19, "output": 17.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.2 Codex" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08", "releaseDate": "2025-01-15", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-52-codex", "modelKey": "openai-gpt-52-codex", "displayName": "GPT-5.2 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2025-01-15", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-53-codex", "provider": "venice", "model": "openai-gpt-53-codex", "displayName": "GPT-5.3 Codex", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-53-codex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-53-codex", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.219, "input": 2.19, "output": 17.5 } } ] }, "metadata": { "displayNames": [ "GPT-5.3 Codex" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-02-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-53-codex", "modelKey": "openai-gpt-53-codex", "displayName": "GPT-5.3 Codex", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-54", "provider": "venice", "model": "openai-gpt-54", "displayName": "GPT-5.4", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-54" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 922000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-54", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.313, "input": 3.13, "output": 18.8 } } ] }, "metadata": { "displayNames": [ "GPT-5.4" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-54", "modelKey": "openai-gpt-54", "displayName": "GPT-5.4", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-54-mini", "provider": "venice", "model": "openai-gpt-54-mini", "displayName": "GPT-5.4 Mini", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-54-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 400000, "inputTokens": 272000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-54-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09375, "input": 0.9375, "output": 5.625 } } ] }, "metadata": { "displayNames": [ "GPT-5.4 Mini" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-27", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-54-mini", "modelKey": "openai-gpt-54-mini", "displayName": "GPT-5.4 Mini", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-54-pro", "provider": "venice", "model": "openai-gpt-54-pro", "displayName": "GPT-5.4 Pro", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-54-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-54-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 37.5, "output": 225 }, "tiered": { "contextOver200K": { "input": 75, "output": 337.5 }, "tiers": [ { "input": 75, "output": 337.5, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.4 Pro" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-05", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-54-pro", "modelKey": "openai-gpt-54-pro", "displayName": "GPT-5.4 Pro", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-05", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-55", "provider": "venice", "model": "openai-gpt-55", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-55" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 922000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-55", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.625, "input": 6.25, "output": 37.5 }, "tiered": { "contextOver200K": { "input": 12.5, "output": 56.25, "cache_read": 1.25 }, "tiers": [ { "input": 12.5, "output": 56.25, "cache_read": 1.25, "tier": { "size": 272000 } } ] } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-23", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-55", "modelKey": "openai-gpt-55", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-23", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-55-pro", "provider": "venice", "model": "openai-gpt-55-pro", "displayName": "GPT-5.5 Pro", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-55-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 922000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-55-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 37.5, "output": 225 } } ] }, "metadata": { "displayNames": [ "GPT-5.5 Pro" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-01", "releaseDate": "2026-04-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-55-pro", "modelKey": "openai-gpt-55-pro", "displayName": "GPT-5.5 Pro", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-01", "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-24", "reasoningOptions": [ { "type": "effort", "values": [ "none", "minimal", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/openai-gpt-oss-120b", "provider": "venice", "model": "openai-gpt-oss-120b", "displayName": "OpenAI GPT OSS 120B", "family": "gpt-oss", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/openai-gpt-oss-120b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "openai-gpt-oss-120b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "OpenAI GPT OSS 120B" ], "families": [ "gpt-oss" ], "releaseDate": "2025-11-06", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "openai-gpt-oss-120b", "modelKey": "openai-gpt-oss-120b", "displayName": "OpenAI GPT OSS 120B", "family": "gpt-oss", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-11-06", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/venice-uncensored-1-2", "provider": "venice", "model": "venice-uncensored-1-2", "displayName": "Venice Uncensored 1.2", "family": "venice", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/venice-uncensored-1-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "venice-uncensored-1-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "Venice Uncensored 1.2" ], "families": [ "venice" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "venice-uncensored-1-2", "modelKey": "venice-uncensored-1-2", "displayName": "Venice Uncensored 1.2", "family": "venice", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-01" } } ] }, { "id": "venice/venice-uncensored-role-play", "provider": "venice", "model": "venice-uncensored-role-play", "displayName": "Venice Role Play Uncensored", "family": "venice", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/venice-uncensored-role-play" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "venice-uncensored-role-play", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 2 } } ] }, "metadata": { "displayNames": [ "Venice Role Play Uncensored" ], "families": [ "venice" ], "releaseDate": "2026-02-20", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "venice-uncensored-role-play", "modelKey": "venice-uncensored-role-play", "displayName": "Venice Role Play Uncensored", "family": "venice", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-20" } } ] }, { "id": "venice/xiaomi-mimo-v2-5", "provider": "venice", "model": "xiaomi-mimo-v2-5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/xiaomi-mimo-v2-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65536, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "xiaomi-mimo-v2-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0625, "input": 0.175, "output": 0.35 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-06-11", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "xiaomi-mimo-v2-5", "modelKey": "xiaomi-mimo-v2-5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-06-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/z-ai-glm-5-turbo", "provider": "venice", "model": "z-ai-glm-5-turbo", "displayName": "GLM 5 Turbo", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/z-ai-glm-5-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "z-ai-glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } } ] }, "metadata": { "displayNames": [ "GLM 5 Turbo" ], "families": [ "glm" ], "releaseDate": "2026-03-15", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "z-ai-glm-5-turbo", "modelKey": "z-ai-glm-5-turbo", "displayName": "GLM 5 Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-03-15", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/z-ai-glm-5v-turbo", "provider": "venice", "model": "z-ai-glm-5v-turbo", "displayName": "GLM 5V Turbo", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/z-ai-glm-5v-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "z-ai-glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 5 } } ] }, "metadata": { "displayNames": [ "GLM 5V Turbo" ], "families": [ "glm" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "z-ai-glm-5v-turbo", "modelKey": "z-ai-glm-5v-turbo", "displayName": "GLM 5V Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-4.6", "provider": "venice", "model": "zai-org-glm-4.6", "displayName": "GLM 4.6", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-4.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 0.85, "output": 2.75 } } ] }, "metadata": { "displayNames": [ "GLM 4.6" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2024-04-01", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-4.6", "modelKey": "zai-org-glm-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2024-04-01", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-4.7", "provider": "venice", "model": "zai-org-glm-4.7", "displayName": "GLM 4.7", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-4.7" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.55, "output": 2.65 } } ] }, "metadata": { "displayNames": [ "GLM 4.7" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-24", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-4.7", "modelKey": "zai-org-glm-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2025-12-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-4.7-flash", "provider": "venice", "model": "zai-org-glm-4.7-flash", "displayName": "GLM 4.7 Flash", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-4.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.125, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-29", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-4.7-flash", "modelKey": "zai-org-glm-4.7-flash", "displayName": "GLM 4.7 Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-01-29", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-5", "provider": "venice", "model": "zai-org-glm-5", "displayName": "GLM 5", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 198000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM 5" ], "families": [ "glm" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-5", "modelKey": "zai-org-glm-5", "displayName": "GLM 5", "family": "glm", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-5-1", "provider": "venice", "model": "zai-org-glm-5-1", "displayName": "GLM 5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-5-1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 24000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-5-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.325, "input": 1.75, "output": 5.5 } } ] }, "metadata": { "displayNames": [ "GLM 5.1" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-5-1", "modelKey": "zai-org-glm-5-1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-06-11", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "venice/zai-org-glm-5-2", "provider": "venice", "model": "zai-org-glm-5-2", "displayName": "GLM 5.2", "family": "glm", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/zai-org-glm-5-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "zai-org-glm-5-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "GLM 5.2" ], "families": [ "glm" ], "releaseDate": "2026-06-16", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "zai-org-glm-5-2", "modelKey": "zai-org-glm-5-2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-06-16" } } ] }, { "id": "vercel-ai-gateway/mercury-coder-small", "provider": "vercel-ai-gateway", "model": "mercury-coder-small", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/inception/mercury-coder-small" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/inception/mercury-coder-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/inception/mercury-coder-small", "mode": "chat" } ] }, { "id": "vercel-ai-gateway/morph-v3-fast", "provider": "vercel-ai-gateway", "model": "morph-v3-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/morph/morph-v3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/morph/morph-v3-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/morph/morph-v3-fast", "mode": "chat" } ] }, { "id": "vercel-ai-gateway/morph-v3-large", "provider": "vercel-ai-gateway", "model": "morph-v3-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/morph/morph-v3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 16384, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/morph/morph-v3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.9, "output": 1.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/morph/morph-v3-large", "mode": "chat" } ] }, { "id": "vercel-ai-gateway/v0-1.0-md", "provider": "vercel-ai-gateway", "model": "v0-1.0-md", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/vercel/v0-1.0-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/vercel/v0-1.0-md", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/vercel/v0-1.0-md", "mode": "chat" } ] }, { "id": "vercel-ai-gateway/v0-1.5-md", "provider": "vercel-ai-gateway", "model": "v0-1.5-md", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/vercel/v0-1.5-md" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/vercel/v0-1.5-md", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/vercel/v0-1.5-md", "mode": "chat" } ] }, { "id": "vercel/flux-2-flex", "provider": "vercel", "model": "flux-2-flex", "displayName": "FLUX.2 [flex]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-2-flex" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.2 [flex]" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-2-flex", "modelKey": "bfl/flux-2-flex", "displayName": "FLUX.2 [flex]", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-2-klein-4b", "provider": "vercel", "model": "flux-2-klein-4b", "displayName": "FLUX.2 [klein] 4B", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-2-klein-4b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.2 [klein] 4B" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-2-klein-4b", "modelKey": "bfl/flux-2-klein-4b", "displayName": "FLUX.2 [klein] 4B", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-2-klein-9b", "provider": "vercel", "model": "flux-2-klein-9b", "displayName": "FLUX.2 [klein] 9B", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-2-klein-9b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.2 [klein] 9B" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-2-klein-9b", "modelKey": "bfl/flux-2-klein-9b", "displayName": "FLUX.2 [klein] 9B", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-2-max", "provider": "vercel", "model": "flux-2-max", "displayName": "FLUX.2 [max]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-2-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 67300, "outputTokens": 67300, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.2 [max]" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-2-max", "modelKey": "bfl/flux-2-max", "displayName": "FLUX.2 [max]", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-2-pro", "provider": "vercel", "model": "flux-2-pro", "displayName": "FLUX.2 [pro]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 67300, "outputTokens": 67300, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.2 [pro]" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-2-pro", "modelKey": "bfl/flux-2-pro", "displayName": "FLUX.2 [pro]", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-fast-schnell", "provider": "vercel", "model": "flux-fast-schnell", "displayName": "Flux Schnell", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/prodia/flux-fast-schnell" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Flux Schnell" ], "families": [ "flux" ], "releaseDate": "2026-06-08", "lastUpdated": "2026-06-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "prodia/flux-fast-schnell", "modelKey": "prodia/flux-fast-schnell", "displayName": "Flux Schnell", "family": "flux", "metadata": { "lastUpdated": "2026-06-08", "openWeights": false, "releaseDate": "2026-06-08" } } ] }, { "id": "vercel/flux-kontext-max", "provider": "vercel", "model": "flux-kontext-max", "displayName": "FLUX.1 Kontext Max", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-kontext-max" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.1 Kontext Max" ], "families": [ "flux" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-kontext-max", "modelKey": "bfl/flux-kontext-max", "displayName": "FLUX.1 Kontext Max", "family": "flux", "metadata": { "lastUpdated": "2025-06", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "vercel/flux-kontext-pro", "provider": "vercel", "model": "flux-kontext-pro", "displayName": "FLUX.1 Kontext Pro", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-kontext-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.1 Kontext Pro" ], "families": [ "flux" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-kontext-pro", "modelKey": "bfl/flux-kontext-pro", "displayName": "FLUX.1 Kontext Pro", "family": "flux", "metadata": { "lastUpdated": "2025-06", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "vercel/flux-pro-1.0-fill", "provider": "vercel", "model": "flux-pro-1.0-fill", "displayName": "FLUX.1 Fill [pro]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-pro-1.0-fill" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX.1 Fill [pro]" ], "families": [ "flux" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-pro-1.0-fill", "modelKey": "bfl/flux-pro-1.0-fill", "displayName": "FLUX.1 Fill [pro]", "family": "flux", "metadata": { "lastUpdated": "2024-10", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "vercel/flux-pro-1.1", "provider": "vercel", "model": "flux-pro-1.1", "displayName": "FLUX1.1 [pro]", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-pro-1.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX1.1 [pro]" ], "families": [ "flux" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-pro-1.1", "modelKey": "bfl/flux-pro-1.1", "displayName": "FLUX1.1 [pro]", "family": "flux", "metadata": { "lastUpdated": "2024-10", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "vercel/flux-pro-1.1-ultra", "provider": "vercel", "model": "flux-pro-1.1-ultra", "displayName": "FLUX1.1 [pro] Ultra", "family": "flux", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bfl/flux-pro-1.1-ultra" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "FLUX1.1 [pro] Ultra" ], "families": [ "flux" ], "releaseDate": "2024-11-01", "lastUpdated": "2024-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bfl/flux-pro-1.1-ultra", "modelKey": "bfl/flux-pro-1.1-ultra", "displayName": "FLUX1.1 [pro] Ultra", "family": "flux", "metadata": { "lastUpdated": "2024-11", "openWeights": false, "releaseDate": "2024-11-01" } } ] }, { "id": "vercel/interfaze-beta", "provider": "vercel", "model": "interfaze-beta", "displayName": "Interfaze Beta", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/interfaze/interfaze-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 32000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "interfaze/interfaze-beta", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.5, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "Interfaze Beta" ], "releaseDate": "2025-10-07", "lastUpdated": "2026-04-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "interfaze/interfaze-beta", "modelKey": "interfaze/interfaze-beta", "displayName": "Interfaze Beta", "metadata": { "lastUpdated": "2026-04-29", "openWeights": false, "releaseDate": "2025-10-07" } } ] }, { "id": "vercel/kat-coder-pro-v1", "provider": "vercel", "model": "kat-coder-pro-v1", "displayName": "KAT-Coder-Pro V1", "family": "kat-coder", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/kwaipilot/kat-coder-pro-v1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "kwaipilot/kat-coder-pro-v1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "KAT-Coder-Pro V1" ], "families": [ "kat-coder" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-10-24", "lastUpdated": "2025-10-24", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "kwaipilot/kat-coder-pro-v1", "modelKey": "kwaipilot/kat-coder-pro-v1", "displayName": "KAT-Coder-Pro V1", "family": "kat-coder", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-24", "openWeights": false, "releaseDate": "2025-10-24" } } ] }, { "id": "vercel/kat-coder-pro-v2", "provider": "vercel", "model": "kat-coder-pro-v2", "displayName": "Kat Coder Pro V2", "family": "kat-coder", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/kwaipilot/kat-coder-pro-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "kwaipilot/kat-coder-pro-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Kat Coder Pro V2" ], "families": [ "kat-coder" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "kwaipilot/kat-coder-pro-v2", "modelKey": "kwaipilot/kat-coder-pro-v2", "displayName": "Kat Coder Pro V2", "family": "kat-coder", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-27" } } ] }, { "id": "vercel/kling-v2.5-turbo-i2v", "provider": "vercel", "model": "kling-v2.5-turbo-i2v", "displayName": "Kling v2.5 Turbo Image-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v2.5-turbo-i2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v2.5 Turbo Image-to-Video" ], "families": [ "ling" ], "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v2.5-turbo-i2v", "modelKey": "klingai/kling-v2.5-turbo-i2v", "displayName": "Kling v2.5 Turbo Image-to-Video", "family": "ling", "metadata": { "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } } ] }, { "id": "vercel/kling-v2.5-turbo-t2v", "provider": "vercel", "model": "kling-v2.5-turbo-t2v", "displayName": "Kling v2.5 Turbo Text-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v2.5-turbo-t2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v2.5 Turbo Text-to-Video" ], "families": [ "ling" ], "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v2.5-turbo-t2v", "modelKey": "klingai/kling-v2.5-turbo-t2v", "displayName": "Kling v2.5 Turbo Text-to-Video", "family": "ling", "metadata": { "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } } ] }, { "id": "vercel/kling-v2.6-i2v", "provider": "vercel", "model": "kling-v2.6-i2v", "displayName": "Kling v2.6 Image-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v2.6-i2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v2.6 Image-to-Video" ], "families": [ "ling" ], "releaseDate": "2025-12-21", "lastUpdated": "2025-12-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v2.6-i2v", "modelKey": "klingai/kling-v2.6-i2v", "displayName": "Kling v2.6 Image-to-Video", "family": "ling", "metadata": { "lastUpdated": "2025-12-21", "openWeights": false, "releaseDate": "2025-12-21" } } ] }, { "id": "vercel/kling-v2.6-motion-control", "provider": "vercel", "model": "kling-v2.6-motion-control", "displayName": "Kling v2.6 Motion Control", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v2.6-motion-control" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v2.6 Motion Control" ], "families": [ "ling" ], "releaseDate": "2025-12-21", "lastUpdated": "2025-12-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v2.6-motion-control", "modelKey": "klingai/kling-v2.6-motion-control", "displayName": "Kling v2.6 Motion Control", "family": "ling", "metadata": { "lastUpdated": "2025-12-21", "openWeights": false, "releaseDate": "2025-12-21" } } ] }, { "id": "vercel/kling-v2.6-t2v", "provider": "vercel", "model": "kling-v2.6-t2v", "displayName": "Kling v2.6 Text-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v2.6-t2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v2.6 Text-to-Video" ], "families": [ "ling" ], "releaseDate": "2025-12-21", "lastUpdated": "2025-12-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v2.6-t2v", "modelKey": "klingai/kling-v2.6-t2v", "displayName": "Kling v2.6 Text-to-Video", "family": "ling", "metadata": { "lastUpdated": "2025-12-21", "openWeights": false, "releaseDate": "2025-12-21" } } ] }, { "id": "vercel/kling-v3.0-i2v", "provider": "vercel", "model": "kling-v3.0-i2v", "displayName": "Kling v3.0 Image-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v3.0-i2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v3.0 Image-to-Video" ], "families": [ "ling" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v3.0-i2v", "modelKey": "klingai/kling-v3.0-i2v", "displayName": "Kling v3.0 Image-to-Video", "family": "ling", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "vercel/kling-v3.0-motion-control", "provider": "vercel", "model": "kling-v3.0-motion-control", "displayName": "Kling v3.0 Motion Control", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v3.0-motion-control" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v3.0 Motion Control" ], "families": [ "ling" ], "releaseDate": "2026-03-04", "lastUpdated": "2026-03-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v3.0-motion-control", "modelKey": "klingai/kling-v3.0-motion-control", "displayName": "Kling v3.0 Motion Control", "family": "ling", "metadata": { "lastUpdated": "2026-03-04", "openWeights": false, "releaseDate": "2026-03-04" } } ] }, { "id": "vercel/kling-v3.0-t2v", "provider": "vercel", "model": "kling-v3.0-t2v", "displayName": "Kling v3.0 Text-to-Video", "family": "ling", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/klingai/kling-v3.0-t2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Kling v3.0 Text-to-Video" ], "families": [ "ling" ], "releaseDate": "2026-02-05", "lastUpdated": "2026-02-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "klingai/kling-v3.0-t2v", "modelKey": "klingai/kling-v3.0-t2v", "displayName": "Kling v3.0 Text-to-Video", "family": "ling", "metadata": { "lastUpdated": "2026-02-05", "openWeights": false, "releaseDate": "2026-02-05" } } ] }, { "id": "vercel/longcat-flash-chat", "provider": "vercel", "model": "longcat-flash-chat", "displayName": "LongCat Flash Chat", "family": "longcat", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/meituan/longcat-flash-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 100000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "LongCat Flash Chat" ], "families": [ "longcat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-08-30", "lastUpdated": "2025-08-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meituan/longcat-flash-chat", "modelKey": "meituan/longcat-flash-chat", "displayName": "LongCat Flash Chat", "family": "longcat", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-30", "openWeights": false, "releaseDate": "2025-08-30" } } ] }, { "id": "vercel/longcat-flash-thinking-2601", "provider": "vercel", "model": "longcat-flash-thinking-2601", "displayName": "LongCat Flash Thinking 2601", "family": "longcat", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/meituan/longcat-flash-thinking-2601" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "LongCat Flash Thinking 2601" ], "families": [ "longcat" ], "releaseDate": "2026-03-13", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "meituan/longcat-flash-thinking-2601", "modelKey": "meituan/longcat-flash-thinking-2601", "displayName": "LongCat Flash Thinking 2601", "family": "longcat", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-13" } } ] }, { "id": "vercel/mercury-2", "provider": "vercel", "model": "mercury-2", "displayName": "Mercury 2", "family": "mercury", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/inception/mercury-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "inception/mercury-2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.024999999999999998, "input": 0.25, "output": 0.75 } } ] }, "metadata": { "displayNames": [ "Mercury 2" ], "families": [ "mercury" ], "releaseDate": "2026-02-24", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "inception/mercury-2", "modelKey": "inception/mercury-2", "displayName": "Mercury 2", "family": "mercury", "metadata": { "lastUpdated": "2026-03-06", "openWeights": false, "releaseDate": "2026-02-24", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "vercel/mercury-coder-small", "provider": "vercel", "model": "mercury-coder-small", "displayName": "Mercury Coder Small Beta", "family": "mercury", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/inception/mercury-coder-small" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "inception/mercury-coder-small", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } } ] }, "metadata": { "displayNames": [ "Mercury Coder Small Beta" ], "families": [ "mercury" ], "releaseDate": "2025-02-26", "lastUpdated": "2025-02-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "inception/mercury-coder-small", "modelKey": "inception/mercury-coder-small", "displayName": "Mercury Coder Small Beta", "family": "mercury", "metadata": { "lastUpdated": "2025-02-26", "openWeights": false, "releaseDate": "2025-02-26" } } ] }, { "id": "vercel/mimo-v2-flash", "provider": "vercel", "model": "mimo-v2-flash", "displayName": "MiMo V2 Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xiaomi/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-17", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xiaomi/mimo-v2-flash", "modelKey": "xiaomi/mimo-v2-flash", "displayName": "MiMo V2 Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2026-02-04", "openWeights": false, "releaseDate": "2025-12-17", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/mimo-v2-pro", "provider": "vercel", "model": "mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xiaomi/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xiaomi/mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xiaomi/mimo-v2-pro", "modelKey": "xiaomi/mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/mimo-v2.5", "provider": "vercel", "model": "mimo-v2.5", "displayName": "MiMo M2.5", "family": "mimo-v2.5", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "outputTokens": 131100, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0028, "input": 0.14, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "MiMo M2.5" ], "families": [ "mimo-v2.5" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xiaomi/mimo-v2.5", "modelKey": "xiaomi/mimo-v2.5", "displayName": "MiMo M2.5", "family": "mimo-v2.5", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": false, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/mimo-v2.5-pro", "provider": "vercel", "model": "mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo-v2.5-pro", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1050000, "outputTokens": 131000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0036, "input": 0.435, "output": 0.87 } } ] }, "metadata": { "displayNames": [ "MiMo V2.5 Pro" ], "families": [ "mimo-v2.5-pro" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xiaomi/mimo-v2.5-pro", "modelKey": "xiaomi/mimo-v2.5-pro", "displayName": "MiMo V2.5 Pro", "family": "mimo-v2.5-pro", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": false, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/morph-v3-fast", "provider": "vercel", "model": "morph-v3-fast", "displayName": "Morph v3 Fast", "family": "morph", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/morph/morph-v3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "morph/morph-v3-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "Morph v3 Fast" ], "families": [ "morph" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "morph/morph-v3-fast", "modelKey": "morph/morph-v3-fast", "displayName": "Morph v3 Fast", "family": "morph", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } } ] }, { "id": "vercel/morph-v3-large", "provider": "vercel", "model": "morph-v3-large", "displayName": "Morph v3 Large", "family": "morph", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/morph/morph-v3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "morph/morph-v3-large", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 1.9 } } ] }, "metadata": { "displayNames": [ "Morph v3 Large" ], "families": [ "morph" ], "releaseDate": "2024-08-15", "lastUpdated": "2024-08-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "morph/morph-v3-large", "modelKey": "morph/morph-v3-large", "displayName": "Morph v3 Large", "family": "morph", "metadata": { "lastUpdated": "2024-08-15", "openWeights": false, "releaseDate": "2024-08-15" } } ] }, { "id": "vercel/nemotron-3-nano-30b-a3b", "provider": "vercel", "model": "nemotron-3-nano-30b-a3b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/nvidia/nemotron-3-nano-30b-a3b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "nvidia/nemotron-3-nano-30b-a3b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.05, "output": 0.24 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Nano 30B A3B" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-01", "lastUpdated": "2025-12-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "nvidia/nemotron-3-nano-30b-a3b", "modelKey": "nvidia/nemotron-3-nano-30b-a3b", "displayName": "Nemotron 3 Nano 30B A3B", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-15", "openWeights": false, "releaseDate": "2024-12-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/nemotron-3-super-120b-a12b", "provider": "vercel", "model": "nemotron-3-super-120b-a12b", "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/nvidia/nemotron-3-super-120b-a12b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "nvidia/nemotron-3-super-120b-a12b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.65 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Super 120B A12B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "nvidia/nemotron-3-super-120b-a12b", "modelKey": "nvidia/nemotron-3-super-120b-a12b", "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-11", "openWeights": false, "releaseDate": "2026-03-18" } } ] }, { "id": "vercel/nemotron-3-ultra-550b-a55b", "provider": "vercel", "model": "nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/nvidia/nemotron-3-ultra-550b-a55b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 65000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "nvidia/nemotron-3-ultra-550b-a55b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.4 } } ] }, "metadata": { "displayNames": [ "Nemotron 3 Ultra" ], "families": [ "nemotron" ], "releaseDate": "2026-06-04", "lastUpdated": "2026-06-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "nvidia/nemotron-3-ultra-550b-a55b", "modelKey": "nvidia/nemotron-3-ultra-550b-a55b", "displayName": "Nemotron 3 Ultra", "family": "nemotron", "metadata": { "lastUpdated": "2026-06-04", "openWeights": false, "releaseDate": "2026-06-04", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/nemotron-nano-12b-v2-vl", "provider": "vercel", "model": "nemotron-nano-12b-v2-vl", "displayName": "Nvidia Nemotron Nano 12B V2 VL", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/nvidia/nemotron-nano-12b-v2-vl" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "nvidia/nemotron-nano-12b-v2-vl", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron Nano 12B V2 VL" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-01", "lastUpdated": "2025-10-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "nvidia/nemotron-nano-12b-v2-vl", "modelKey": "nvidia/nemotron-nano-12b-v2-vl", "displayName": "Nvidia Nemotron Nano 12B V2 VL", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-28", "openWeights": false, "releaseDate": "2024-12-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/nemotron-nano-9b-v2", "provider": "vercel", "model": "nemotron-nano-9b-v2", "displayName": "Nvidia Nemotron Nano 9B V2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/nvidia/nemotron-nano-9b-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "nvidia/nemotron-nano-9b-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.23 } } ] }, "metadata": { "displayNames": [ "Nvidia Nemotron Nano 9B V2" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-08-18", "lastUpdated": "2025-08-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "nvidia/nemotron-nano-9b-v2", "modelKey": "nvidia/nemotron-nano-9b-v2", "displayName": "Nvidia Nemotron Nano 9B V2", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-18", "openWeights": false, "releaseDate": "2025-08-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/recraft-v2", "provider": "vercel", "model": "recraft-v2", "displayName": "Recraft V2", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V2" ], "families": [ "recraft" ], "releaseDate": "2024-03-01", "lastUpdated": "2024-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v2", "modelKey": "recraft/recraft-v2", "displayName": "Recraft V2", "family": "recraft", "metadata": { "lastUpdated": "2024-03", "openWeights": false, "releaseDate": "2024-03-01" } } ] }, { "id": "vercel/recraft-v3", "provider": "vercel", "model": "recraft-v3", "displayName": "Recraft V3", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V3" ], "families": [ "recraft" ], "releaseDate": "2024-10-01", "lastUpdated": "2024-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v3", "modelKey": "recraft/recraft-v3", "displayName": "Recraft V3", "family": "recraft", "metadata": { "lastUpdated": "2024-10", "openWeights": false, "releaseDate": "2024-10-01" } } ] }, { "id": "vercel/recraft-v4", "provider": "vercel", "model": "recraft-v4", "displayName": "Recraft V4", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4" ], "families": [ "recraft" ], "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4", "modelKey": "recraft/recraft-v4", "displayName": "Recraft V4", "family": "recraft", "metadata": { "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "vercel/recraft-v4-pro", "provider": "vercel", "model": "recraft-v4-pro", "displayName": "Recraft V4 Pro", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4 Pro" ], "families": [ "recraft" ], "releaseDate": "2026-02-17", "lastUpdated": "2026-02-17", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4-pro", "modelKey": "recraft/recraft-v4-pro", "displayName": "Recraft V4 Pro", "family": "recraft", "metadata": { "lastUpdated": "2026-02-17", "openWeights": false, "releaseDate": "2026-02-17" } } ] }, { "id": "vercel/recraft-v4.1", "provider": "vercel", "model": "recraft-v4.1", "displayName": "Recraft V4.1", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4.1" ], "families": [ "recraft" ], "releaseDate": "2026-05-14", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4.1", "modelKey": "recraft/recraft-v4.1", "displayName": "Recraft V4.1", "family": "recraft", "metadata": { "lastUpdated": "2026-05-14", "openWeights": false, "releaseDate": "2026-05-14" } } ] }, { "id": "vercel/recraft-v4.1-pro", "provider": "vercel", "model": "recraft-v4.1-pro", "displayName": "Recraft V4.1 Pro", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4.1-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4.1 Pro" ], "families": [ "recraft" ], "releaseDate": "2026-05-14", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4.1-pro", "modelKey": "recraft/recraft-v4.1-pro", "displayName": "Recraft V4.1 Pro", "family": "recraft", "metadata": { "lastUpdated": "2026-05-14", "openWeights": false, "releaseDate": "2026-05-14" } } ] }, { "id": "vercel/recraft-v4.1-utility", "provider": "vercel", "model": "recraft-v4.1-utility", "displayName": "Recraft V4.1 Utility", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4.1-utility" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4.1 Utility" ], "families": [ "recraft" ], "releaseDate": "2026-05-14", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4.1-utility", "modelKey": "recraft/recraft-v4.1-utility", "displayName": "Recraft V4.1 Utility", "family": "recraft", "metadata": { "lastUpdated": "2026-05-14", "openWeights": false, "releaseDate": "2026-05-14" } } ] }, { "id": "vercel/recraft-v4.1-utility-pro", "provider": "vercel", "model": "recraft-v4.1-utility-pro", "displayName": "Recraft V4.1 Utility Pro", "family": "recraft", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/recraft/recraft-v4.1-utility-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Recraft V4.1 Utility Pro" ], "families": [ "recraft" ], "releaseDate": "2026-05-14", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "recraft/recraft-v4.1-utility-pro", "modelKey": "recraft/recraft-v4.1-utility-pro", "displayName": "Recraft V4.1 Utility Pro", "family": "recraft", "metadata": { "lastUpdated": "2026-05-14", "openWeights": false, "releaseDate": "2026-05-14" } } ] }, { "id": "vercel/rerank-2.5", "provider": "vercel", "model": "rerank-2.5", "displayName": "Voyage Rerank 2.5", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/rerank-2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Voyage Rerank 2.5" ], "families": [ "voyage" ], "releaseDate": "2025-08-11", "lastUpdated": "2025-08-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/rerank-2.5", "modelKey": "voyage/rerank-2.5", "displayName": "Voyage Rerank 2.5", "family": "voyage", "metadata": { "lastUpdated": "2025-08-11", "openWeights": false, "releaseDate": "2025-08-11" } } ] }, { "id": "vercel/rerank-2.5-lite", "provider": "vercel", "model": "rerank-2.5-lite", "displayName": "Voyage Rerank 2.5 Lite", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/rerank-2.5-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Voyage Rerank 2.5 Lite" ], "families": [ "voyage" ], "releaseDate": "2025-08-11", "lastUpdated": "2025-08-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/rerank-2.5-lite", "modelKey": "voyage/rerank-2.5-lite", "displayName": "Voyage Rerank 2.5 Lite", "family": "voyage", "metadata": { "lastUpdated": "2025-08-11", "openWeights": false, "releaseDate": "2025-08-11" } } ] }, { "id": "vercel/seed-1.6", "provider": "vercel", "model": "seed-1.6", "displayName": "Seed 1.6", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seed-1.6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "bytedance/seed-1.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "Seed 1.6" ], "families": [ "seed" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-09-01", "lastUpdated": "2025-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seed-1.6", "modelKey": "bytedance/seed-1.6", "displayName": "Seed 1.6", "family": "seed", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09", "openWeights": false, "releaseDate": "2025-09-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/seed-1.8", "provider": "vercel", "model": "seed-1.8", "displayName": "Seed 1.8", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seed-1.8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "bytedance/seed-1.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.25, "output": 2 } } ] }, "metadata": { "displayNames": [ "Seed 1.8" ], "families": [ "seed" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-09-01", "lastUpdated": "2025-10", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seed-1.8", "modelKey": "bytedance/seed-1.8", "displayName": "Seed 1.8", "family": "seed", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10", "openWeights": false, "releaseDate": "2025-09-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "vercel/seedance-2.0", "provider": "vercel", "model": "seedance-2.0", "displayName": "Seedance 2.0", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-2.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance 2.0" ], "families": [ "seed" ], "releaseDate": "2026-04-14", "lastUpdated": "2026-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-2.0", "modelKey": "bytedance/seedance-2.0", "displayName": "Seedance 2.0", "family": "seed", "metadata": { "lastUpdated": "2026-04-14", "openWeights": false, "releaseDate": "2026-04-14" } } ] }, { "id": "vercel/seedance-2.0-fast", "provider": "vercel", "model": "seedance-2.0-fast", "displayName": "Seedance 2.0 Fast", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-2.0-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance 2.0 Fast" ], "families": [ "seed" ], "releaseDate": "2026-04-14", "lastUpdated": "2026-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-2.0-fast", "modelKey": "bytedance/seedance-2.0-fast", "displayName": "Seedance 2.0 Fast", "family": "seed", "metadata": { "lastUpdated": "2026-04-14", "openWeights": false, "releaseDate": "2026-04-14" } } ] }, { "id": "vercel/seedance-v1.0-lite-i2v", "provider": "vercel", "model": "seedance-v1.0-lite-i2v", "displayName": "Seedance v1.0 Lite Image-to-Video", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-v1.0-lite-i2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance v1.0 Lite Image-to-Video" ], "families": [ "seed" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-v1.0-lite-i2v", "modelKey": "bytedance/seedance-v1.0-lite-i2v", "displayName": "Seedance v1.0 Lite Image-to-Video", "family": "seed", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "vercel/seedance-v1.0-lite-t2v", "provider": "vercel", "model": "seedance-v1.0-lite-t2v", "displayName": "Seedance v1.0 Lite Text-to-Video", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-v1.0-lite-t2v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance v1.0 Lite Text-to-Video" ], "families": [ "seed" ], "releaseDate": "2025-06-01", "lastUpdated": "2025-06-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-v1.0-lite-t2v", "modelKey": "bytedance/seedance-v1.0-lite-t2v", "displayName": "Seedance v1.0 Lite Text-to-Video", "family": "seed", "metadata": { "lastUpdated": "2025-06-01", "openWeights": false, "releaseDate": "2025-06-01" } } ] }, { "id": "vercel/seedance-v1.0-pro", "provider": "vercel", "model": "seedance-v1.0-pro", "displayName": "Seedance v1.0 Pro", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-v1.0-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance v1.0 Pro" ], "families": [ "seed" ], "releaseDate": "2025-06-11", "lastUpdated": "2025-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-v1.0-pro", "modelKey": "bytedance/seedance-v1.0-pro", "displayName": "Seedance v1.0 Pro", "family": "seed", "metadata": { "lastUpdated": "2025-06-11", "openWeights": false, "releaseDate": "2025-06-11" } } ] }, { "id": "vercel/seedance-v1.0-pro-fast", "provider": "vercel", "model": "seedance-v1.0-pro-fast", "displayName": "Seedance v1.0 Pro Fast", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-v1.0-pro-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance v1.0 Pro Fast" ], "families": [ "seed" ], "releaseDate": "2025-10-31", "lastUpdated": "2025-10-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-v1.0-pro-fast", "modelKey": "bytedance/seedance-v1.0-pro-fast", "displayName": "Seedance v1.0 Pro Fast", "family": "seed", "metadata": { "lastUpdated": "2025-10-31", "openWeights": false, "releaseDate": "2025-10-31" } } ] }, { "id": "vercel/seedance-v1.5-pro", "provider": "vercel", "model": "seedance-v1.5-pro", "displayName": "Seedance v1.5 Pro", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedance-v1.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedance v1.5 Pro" ], "families": [ "seed" ], "releaseDate": "2025-12-16", "lastUpdated": "2025-12-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedance-v1.5-pro", "modelKey": "bytedance/seedance-v1.5-pro", "displayName": "Seedance v1.5 Pro", "family": "seed", "metadata": { "lastUpdated": "2025-12-16", "openWeights": false, "releaseDate": "2025-12-16" } } ] }, { "id": "vercel/seedream-4.0", "provider": "vercel", "model": "seedream-4.0", "displayName": "Seedream 4.0", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedream-4.0" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedream 4.0" ], "families": [ "seed" ], "releaseDate": "2025-08-28", "lastUpdated": "2025-08-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedream-4.0", "modelKey": "bytedance/seedream-4.0", "displayName": "Seedream 4.0", "family": "seed", "metadata": { "lastUpdated": "2025-08-28", "openWeights": false, "releaseDate": "2025-08-28" } } ] }, { "id": "vercel/seedream-4.5", "provider": "vercel", "model": "seedream-4.5", "displayName": "Seedream 4.5", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedream-4.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedream 4.5" ], "families": [ "seed" ], "releaseDate": "2025-11-28", "lastUpdated": "2025-11-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedream-4.5", "modelKey": "bytedance/seedream-4.5", "displayName": "Seedream 4.5", "family": "seed", "metadata": { "lastUpdated": "2025-11-28", "openWeights": false, "releaseDate": "2025-11-28" } } ] }, { "id": "vercel/seedream-5.0-lite", "provider": "vercel", "model": "seedream-5.0-lite", "displayName": "Seedream 5.0 Lite", "family": "seed", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/bytedance/seedream-5.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Seedream 5.0 Lite" ], "families": [ "seed" ], "releaseDate": "2026-01-28", "lastUpdated": "2026-01-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "bytedance/seedream-5.0-lite", "modelKey": "bytedance/seedream-5.0-lite", "displayName": "Seedream 5.0 Lite", "family": "seed", "metadata": { "lastUpdated": "2026-01-28", "openWeights": false, "releaseDate": "2026-01-28" } } ] }, { "id": "vercel/step-3.5-flash", "provider": "vercel", "model": "step-3.5-flash", "displayName": "StepFun 3.5 Flash", "family": "step", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262114, "outputTokens": 262114, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "stepfun/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.09, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "StepFun 3.5 Flash" ], "families": [ "step" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-01-29", "lastUpdated": "2026-02-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "stepfun/step-3.5-flash", "modelKey": "stepfun/step-3.5-flash", "displayName": "StepFun 3.5 Flash", "family": "step", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "openWeights": false, "releaseDate": "2026-01-29", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } } ] }, { "id": "vercel/step-3.7-flash", "provider": "vercel", "model": "step-3.7-flash", "displayName": "Step 3.7 Flash", "family": "step", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/stepfun/step-3.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "stepfun/step-3.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.04, "input": 0.2, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash" ], "families": [ "step" ], "knowledgeCutoff": "2026-01-01", "releaseDate": "2026-05-28", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "stepfun/step-3.7-flash", "modelKey": "stepfun/step-3.7-flash", "displayName": "Step 3.7 Flash", "family": "step", "metadata": { "knowledgeCutoff": "2026-01-01", "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-28", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "vercel/trinity-large-preview", "provider": "vercel", "model": "trinity-large-preview", "displayName": "Trinity Large Preview", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/arcee-ai/trinity-large-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "arcee-ai/trinity-large-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 1 } } ] }, "metadata": { "displayNames": [ "Trinity Large Preview" ], "families": [ "trinity" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-01-01", "lastUpdated": "2025-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "arcee-ai/trinity-large-preview", "modelKey": "arcee-ai/trinity-large-preview", "displayName": "Trinity Large Preview", "family": "trinity", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01", "openWeights": false, "releaseDate": "2025-01-01" } } ] }, { "id": "vercel/trinity-large-thinking", "provider": "vercel", "model": "trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/arcee-ai/trinity-large-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262100, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "arcee-ai/trinity-large-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.25, "output": 0.8999999999999999 } } ] }, "metadata": { "displayNames": [ "Trinity Large Thinking" ], "families": [ "trinity" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "arcee-ai/trinity-large-thinking", "modelKey": "arcee-ai/trinity-large-thinking", "displayName": "Trinity Large Thinking", "family": "trinity", "metadata": { "lastUpdated": "2026-04-03", "openWeights": true, "releaseDate": "2026-04-01" } } ] }, { "id": "vercel/trinity-mini", "provider": "vercel", "model": "trinity-mini", "displayName": "Trinity Mini", "family": "trinity", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/arcee-ai/trinity-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "arcee-ai/trinity-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.045, "output": 0.15 } } ] }, "metadata": { "displayNames": [ "Trinity Mini" ], "families": [ "trinity" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-01", "lastUpdated": "2025-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "arcee-ai/trinity-mini", "modelKey": "arcee-ai/trinity-mini", "displayName": "Trinity Mini", "family": "trinity", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12", "openWeights": false, "releaseDate": "2025-12-01" } } ] }, { "id": "vercel/voyage-3-large", "provider": "vercel", "model": "voyage-3-large", "displayName": "voyage-3-large", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-3-large" ], "families": [ "voyage" ], "releaseDate": "2024-09-01", "lastUpdated": "2024-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-3-large", "modelKey": "voyage/voyage-3-large", "displayName": "voyage-3-large", "family": "voyage", "metadata": { "lastUpdated": "2024-09", "openWeights": false, "releaseDate": "2024-09-01" } } ] }, { "id": "vercel/voyage-3.5", "provider": "vercel", "model": "voyage-3.5", "displayName": "voyage-3.5", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-3.5" ], "families": [ "voyage" ], "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-3.5", "modelKey": "voyage/voyage-3.5", "displayName": "voyage-3.5", "family": "voyage", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "vercel/voyage-3.5-lite", "provider": "vercel", "model": "voyage-3.5-lite", "displayName": "voyage-3.5-lite", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-3.5-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-3.5-lite" ], "families": [ "voyage" ], "releaseDate": "2025-05-20", "lastUpdated": "2025-05-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-3.5-lite", "modelKey": "voyage/voyage-3.5-lite", "displayName": "voyage-3.5-lite", "family": "voyage", "metadata": { "lastUpdated": "2025-05-20", "openWeights": false, "releaseDate": "2025-05-20" } } ] }, { "id": "vercel/voyage-4", "provider": "vercel", "model": "voyage-4", "displayName": "voyage-4", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-4" ], "families": [ "voyage" ], "releaseDate": "2026-03-06", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-4", "modelKey": "voyage/voyage-4", "displayName": "voyage-4", "family": "voyage", "metadata": { "lastUpdated": "2026-03-06", "openWeights": false, "releaseDate": "2026-03-06" } } ] }, { "id": "vercel/voyage-4-large", "provider": "vercel", "model": "voyage-4-large", "displayName": "voyage-4-large", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-4-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-4-large" ], "families": [ "voyage" ], "releaseDate": "2026-03-06", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-4-large", "modelKey": "voyage/voyage-4-large", "displayName": "voyage-4-large", "family": "voyage", "metadata": { "lastUpdated": "2026-03-06", "openWeights": false, "releaseDate": "2026-03-06" } } ] }, { "id": "vercel/voyage-4-lite", "provider": "vercel", "model": "voyage-4-lite", "displayName": "voyage-4-lite", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-4-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-4-lite" ], "families": [ "voyage" ], "releaseDate": "2026-03-06", "lastUpdated": "2026-03-06", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-4-lite", "modelKey": "voyage/voyage-4-lite", "displayName": "voyage-4-lite", "family": "voyage", "metadata": { "lastUpdated": "2026-03-06", "openWeights": false, "releaseDate": "2026-03-06" } } ] }, { "id": "vercel/voyage-code-2", "provider": "vercel", "model": "voyage-code-2", "displayName": "voyage-code-2", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-code-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-code-2" ], "families": [ "voyage" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-code-2", "modelKey": "voyage/voyage-code-2", "displayName": "voyage-code-2", "family": "voyage", "metadata": { "lastUpdated": "2024-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "vercel/voyage-code-3", "provider": "vercel", "model": "voyage-code-3", "displayName": "voyage-code-3", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-code-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-code-3" ], "families": [ "voyage" ], "releaseDate": "2024-09-01", "lastUpdated": "2024-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-code-3", "modelKey": "voyage/voyage-code-3", "displayName": "voyage-code-3", "family": "voyage", "metadata": { "lastUpdated": "2024-09", "openWeights": false, "releaseDate": "2024-09-01" } } ] }, { "id": "vercel/voyage-finance-2", "provider": "vercel", "model": "voyage-finance-2", "displayName": "voyage-finance-2", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-finance-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-finance-2" ], "families": [ "voyage" ], "releaseDate": "2024-03-01", "lastUpdated": "2024-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-finance-2", "modelKey": "voyage/voyage-finance-2", "displayName": "voyage-finance-2", "family": "voyage", "metadata": { "lastUpdated": "2024-03", "openWeights": false, "releaseDate": "2024-03-01" } } ] }, { "id": "vercel/voyage-law-2", "provider": "vercel", "model": "voyage-law-2", "displayName": "voyage-law-2", "family": "voyage", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/voyage/voyage-law-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 1536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "voyage-law-2" ], "families": [ "voyage" ], "releaseDate": "2024-03-01", "lastUpdated": "2024-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "voyage/voyage-law-2", "modelKey": "voyage/voyage-law-2", "displayName": "voyage-law-2", "family": "voyage", "metadata": { "lastUpdated": "2024-03", "openWeights": false, "releaseDate": "2024-03-01" } } ] }, { "id": "vertex-ai-ai21-models/jamba-1.5", "provider": "vertex-ai-ai21-models", "model": "jamba-1.5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-ai21_models" ], "aliases": [ "vertex_ai-ai21_models/vertex_ai/jamba-1.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5", "mode": "chat" } ] }, { "id": "vertex-ai-ai21-models/jamba-1.5-large", "provider": "vertex-ai-ai21-models", "model": "jamba-1.5-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-ai21_models" ], "aliases": [ "vertex_ai-ai21_models/vertex_ai/jamba-1.5-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-large", "mode": "chat" } ] }, { "id": "vertex-ai-ai21-models/jamba-1.5-large@001", "provider": "vertex-ai-ai21-models", "model": "jamba-1.5-large@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-ai21_models" ], "aliases": [ "vertex_ai-ai21_models/vertex_ai/jamba-1.5-large@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-large@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-large@001", "mode": "chat" } ] }, { "id": "vertex-ai-ai21-models/jamba-1.5-mini", "provider": "vertex-ai-ai21-models", "model": "jamba-1.5-mini", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-ai21_models" ], "aliases": [ "vertex_ai-ai21_models/vertex_ai/jamba-1.5-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-mini", "mode": "chat" } ] }, { "id": "vertex-ai-ai21-models/jamba-1.5-mini@001", "provider": "vertex-ai-ai21-models", "model": "jamba-1.5-mini@001", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-ai21_models" ], "aliases": [ "vertex_ai-ai21_models/vertex_ai/jamba-1.5-mini@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-mini@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-ai21_models", "model": "vertex_ai/jamba-1.5-mini@001", "mode": "chat" } ] }, { "id": "vertex-ai-embedding-models/multimodalembedding", "provider": "vertex-ai-embedding-models", "model": "multimodalembedding", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/multimodalembedding" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "multimodalembedding", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0 }, "perImage": { "input": 0.0001 }, "perVideoSecond": { "input": 0.0005, "inputAbove8SInterval": 0.001, "inputAbove15SInterval": 0.002 }, "perCharacter": { "input": 2e-7 } } ] }, "metadata": { "modes": [ "embedding" ], "supportedEndpoints": [ "/v1/embeddings" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "multimodalembedding", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supportedEndpoints": [ "/v1/embeddings" ] } } ] }, { "id": "vertex-ai-embedding-models/multimodalembedding@001", "provider": "vertex-ai-embedding-models", "model": "multimodalembedding@001", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/multimodalembedding@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "multimodalembedding@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 0 }, "perImage": { "input": 0.0001 }, "perVideoSecond": { "input": 0.0005, "inputAbove8SInterval": 0.001, "inputAbove15SInterval": 0.002 }, "perCharacter": { "input": 2e-7 } } ] }, "metadata": { "modes": [ "embedding" ], "supportedEndpoints": [ "/v1/embeddings" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "multimodalembedding@001", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supportedEndpoints": [ "/v1/embeddings" ] } } ] }, { "id": "vertex-ai-embedding-models/text-multilingual-embedding-002", "provider": "vertex-ai-embedding-models", "model": "text-multilingual-embedding-002", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "vertex_ai-embedding-models" ], "aliases": [ "vertex_ai-embedding-models/text-multilingual-embedding-002" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2048, "inputTokens": 2048, "maxTokens": 2048, "outputTokens": 2048, "outputVectorSize": 768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-embedding-models", "model": "text-multilingual-embedding-002", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 }, "perCharacter": { "input": 2.5e-8 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-embedding-models", "model": "text-multilingual-embedding-002", "mode": "embedding", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } } ] }, { "id": "vertex-ai-image-models/imagegeneration@006", "provider": "vertex-ai-image-models", "model": "imagegeneration@006", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "vertex_ai-image-models" ], "aliases": [ "vertex_ai-image-models/vertex_ai/imagegeneration@006" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": true, "imageInput": false, "imageOutput": true, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagegeneration@006", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perImage": { "output": 0.02 } } ] }, "metadata": { "modes": [ "image_generation" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-image-models", "model": "vertex_ai/imagegeneration@006", "mode": "image_generation", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } } ] }, { "id": "vertex-ai-language-models/deep-research-pro-preview-12-2025", "provider": "vertex-ai-language-models", "model": "deep-research-pro-preview-12-2025", "mode": "image_generation", "sources": [ "litellm" ], "providers": [ "vertex_ai-language-models" ], "aliases": [ "vertex_ai-language-models/deep-research-pro-preview-12-2025", "vertex_ai-language-models/vertex_ai/deep-research-pro-preview-12-2025" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": true, "imageInput": true, "imageOutput": true, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-language-models", "model": "deep-research-pro-preview-12-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } }, { "source": "litellm", "provider": "vertex_ai-language-models", "model": "vertex_ai/deep-research-pro-preview-12-2025", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 12, "outputImage": 120 }, "perImage": { "input": 0.0011, "output": 0.134 }, "extra": { "input_cost_per_token_batches": 0.000001, "output_cost_per_token_batches": 0.000006 } } ] }, "metadata": { "modes": [ "image_generation" ], "supportedEndpoints": [ "/v1/batch", "/v1/chat/completions", "/v1/completions" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "deep-research-pro-preview-12-2025", "mode": "image_generation", "metadata": { "source": "https://ai.google.dev/gemini-api/docs/pricing", "supportedEndpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "vertex_ai/deep-research-pro-preview-12-2025", "mode": "image_generation", "metadata": { "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" } } ] }, { "id": "vertex-ai-language-models/medlm-large", "provider": "vertex-ai-language-models", "model": "medlm-large", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-language-models" ], "aliases": [ "vertex_ai-language-models/medlm-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-language-models", "model": "medlm-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.000005, "output": 0.000015 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "medlm-large", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "vertex-ai-language-models/medlm-medium", "provider": "vertex-ai-language-models", "model": "medlm-medium", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vertex_ai-language-models" ], "aliases": [ "vertex_ai-language-models/medlm-medium" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-language-models", "model": "medlm-medium", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 5e-7, "output": 0.000001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-language-models", "model": "medlm-medium", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "vertex-ai-text-models/text-unicorn", "provider": "vertex-ai-text-models", "model": "text-unicorn", "mode": "completion", "sources": [ "litellm" ], "providers": [ "vertex_ai-text-models" ], "aliases": [ "vertex_ai-text-models/text-unicorn" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-text-models", "model": "text-unicorn", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 28 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-text-models", "model": "text-unicorn", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "vertex-ai-text-models/text-unicorn@001", "provider": "vertex-ai-text-models", "model": "text-unicorn@001", "mode": "completion", "sources": [ "litellm" ], "providers": [ "vertex_ai-text-models" ], "aliases": [ "vertex_ai-text-models/text-unicorn@001" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai-text-models", "model": "text-unicorn@001", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 10, "output": 28 } } ] }, "metadata": { "modes": [ "completion" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-text-models", "model": "text-unicorn@001", "mode": "completion", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } } ] }, { "id": "vertex-ai/chirp", "provider": "vertex-ai", "model": "chirp", "mode": "audio_speech", "sources": [ "litellm" ], "providers": [ "vertex_ai" ], "aliases": [ "vertex_ai/chirp" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "audioInput": false, "audioOutput": true, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/chirp", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perCharacter": { "input": 0.00003 } } ] }, "metadata": { "modes": [ "audio_speech" ], "supportedEndpoints": [ "/v1/audio/speech" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/chirp", "mode": "audio_speech", "metadata": { "source": "https://cloud.google.com/text-to-speech/pricing", "supportedEndpoints": [ "/v1/audio/speech" ] } } ] }, { "id": "vertex-ai/search-api", "provider": "vertex-ai", "model": "search-api", "mode": "vector_store", "sources": [ "litellm" ], "providers": [ "vertex_ai" ], "aliases": [ "vertex_ai/search_api" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/search_api", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0.0015 } } ] }, "metadata": { "modes": [ "vector_store" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/search_api", "mode": "vector_store" } ] }, { "id": "volcengine/doubao-embedding", "provider": "volcengine", "model": "doubao-embedding", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-embedding" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 2560, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "doubao-embedding", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "doubao-embedding", "mode": "embedding", "metadata": { "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" } } } ] }, { "id": "volcengine/doubao-embedding-large", "provider": "volcengine", "model": "doubao-embedding-large", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-embedding-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "doubao-embedding-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "doubao-embedding-large", "mode": "embedding", "metadata": { "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" } } } ] }, { "id": "volcengine/doubao-embedding-large-text-240915", "provider": "volcengine", "model": "doubao-embedding-large-text-240915", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-embedding-large-text-240915" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "doubao-embedding-large-text-240915", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "doubao-embedding-large-text-240915", "mode": "embedding", "metadata": { "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" } } } ] }, { "id": "volcengine/doubao-embedding-large-text-250515", "provider": "volcengine", "model": "doubao-embedding-large-text-250515", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-embedding-large-text-250515" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 2048, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "doubao-embedding-large-text-250515", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "doubao-embedding-large-text-250515", "mode": "embedding", "metadata": { "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" } } } ] }, { "id": "volcengine/doubao-embedding-text-240715", "provider": "volcengine", "model": "doubao-embedding-text-240715", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-embedding-text-240715" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "outputVectorSize": 2560, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "doubao-embedding-text-240715", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "doubao-embedding-text-240715", "mode": "embedding", "metadata": { "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" } } } ] }, { "id": "volcengine/doubao-seed-2-0-code-preview-260215", "provider": "volcengine", "model": "doubao-seed-2-0-code-preview-260215", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-seed-2-0-code-preview-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-code-preview-260215", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-code-preview-260215", "mode": "chat", "metadata": { "source": "https://www.volcengine.com/docs/82379/1330310" } } ] }, { "id": "volcengine/doubao-seed-2-0-lite-260215", "provider": "volcengine", "model": "doubao-seed-2-0-lite-260215", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-seed-2-0-lite-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-lite-260215", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-lite-260215", "mode": "chat", "metadata": { "source": "https://www.volcengine.com/docs/82379/1330310" } } ] }, { "id": "volcengine/doubao-seed-2-0-mini-260215", "provider": "volcengine", "model": "doubao-seed-2-0-mini-260215", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-seed-2-0-mini-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-mini-260215", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-mini-260215", "mode": "chat", "metadata": { "source": "https://www.volcengine.com/docs/82379/1330310" } } ] }, { "id": "volcengine/doubao-seed-2-0-pro-260215", "provider": "volcengine", "model": "doubao-seed-2-0-pro-260215", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/doubao-seed-2-0-pro-260215" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "toolChoice": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-pro-260215", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields" } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "volcengine/doubao-seed-2-0-pro-260215", "mode": "chat", "metadata": { "source": "https://www.volcengine.com/docs/82379/1330310" } } ] }, { "id": "voyage/rerank-2", "provider": "voyage", "model": "rerank-2", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/rerank-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "maxQueryTokens": 16000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/rerank-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/rerank-2", "mode": "rerank" } ] }, { "id": "voyage/rerank-2-lite", "provider": "voyage", "model": "rerank-2-lite", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/rerank-2-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "maxQueryTokens": 8000, "maxTokens": 8000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/rerank-2-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/rerank-2-lite", "mode": "rerank" } ] }, { "id": "voyage/rerank-2.5", "provider": "voyage", "model": "rerank-2.5", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/rerank-2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxQueryTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/rerank-2.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.05, "output": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/rerank-2.5", "mode": "rerank" } ] }, { "id": "voyage/rerank-2.5-lite", "provider": "voyage", "model": "rerank-2.5-lite", "mode": "rerank", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/rerank-2.5-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxQueryTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "score" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": true, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/rerank-2.5-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "modes": [ "rerank" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/rerank-2.5-lite", "mode": "rerank" } ] }, { "id": "voyage/voyage-2", "provider": "voyage", "model": "voyage-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "inputTokens": 4000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-2", "mode": "embedding" } ] }, { "id": "voyage/voyage-3", "provider": "voyage", "model": "voyage-3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-3", "mode": "embedding" } ] }, { "id": "voyage/voyage-3-large", "provider": "voyage", "model": "voyage-3-large", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-3-large" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-3-large", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-3-large", "mode": "embedding" } ] }, { "id": "voyage/voyage-3-lite", "provider": "voyage", "model": "voyage-3-lite", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-3-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-3-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-3-lite", "mode": "embedding" } ] }, { "id": "voyage/voyage-3.5", "provider": "voyage", "model": "voyage-3.5", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-3.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-3.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-3.5", "mode": "embedding" } ] }, { "id": "voyage/voyage-3.5-lite", "provider": "voyage", "model": "voyage-3.5-lite", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-3.5-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-3.5-lite", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.02, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-3.5-lite", "mode": "embedding" } ] }, { "id": "voyage/voyage-code-2", "provider": "voyage", "model": "voyage-code-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-code-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-code-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-code-2", "mode": "embedding" } ] }, { "id": "voyage/voyage-code-3", "provider": "voyage", "model": "voyage-code-3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-code-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-code-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-code-3", "mode": "embedding" } ] }, { "id": "voyage/voyage-context-3", "provider": "voyage", "model": "voyage-context-3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-context-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 120000, "inputTokens": 120000, "maxTokens": 120000, "outputTokens": 120000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-context-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.18, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-context-3", "mode": "embedding" } ] }, { "id": "voyage/voyage-finance-2", "provider": "voyage", "model": "voyage-finance-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-finance-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-finance-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-finance-2", "mode": "embedding" } ] }, { "id": "voyage/voyage-large-2", "provider": "voyage", "model": "voyage-large-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-large-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-large-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-large-2", "mode": "embedding" } ] }, { "id": "voyage/voyage-law-2", "provider": "voyage", "model": "voyage-law-2", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-law-2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 16000, "inputTokens": 16000, "maxTokens": 16000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-law-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-law-2", "mode": "embedding" } ] }, { "id": "voyage/voyage-lite-01", "provider": "voyage", "model": "voyage-lite-01", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-lite-01" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4096, "inputTokens": 4096, "maxTokens": 4096, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-lite-01", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-lite-01", "mode": "embedding" } ] }, { "id": "voyage/voyage-lite-02-instruct", "provider": "voyage", "model": "voyage-lite-02-instruct", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-lite-02-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 4000, "inputTokens": 4000, "maxTokens": 4000, "outputTokens": 4000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-lite-02-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-lite-02-instruct", "mode": "embedding" } ] }, { "id": "voyage/voyage-multimodal-3", "provider": "voyage", "model": "voyage-multimodal-3", "mode": "embedding", "sources": [ "litellm" ], "providers": [ "voyage" ], "aliases": [ "voyage/voyage-multimodal-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "maxTokens": 32000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "voyage", "model": "voyage/voyage-multimodal-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.12, "output": 0 } } ] }, "metadata": { "modes": [ "embedding" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "voyage", "model": "voyage/voyage-multimodal-3", "mode": "embedding" } ] }, { "id": "vultr/nemotron-3-nano-omni-30b-a3b-reasoning-bf16", "provider": "vultr", "model": "nemotron-3-nano-omni-30b-a3b-reasoning-bf16", "displayName": "NVIDIA Nemotron 3 Nano Omni", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vultr" ], "aliases": [ "vultr/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vultr", "model": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.38 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Nano Omni" ], "families": [ "nemotron" ], "knowledgeCutoff": "2025-05", "releaseDate": "2026-04-28", "lastUpdated": "2026-04-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "modelKey": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "displayName": "NVIDIA Nemotron 3 Nano Omni", "family": "nemotron", "metadata": { "knowledgeCutoff": "2025-05", "lastUpdated": "2026-04-28", "openWeights": true, "releaseDate": "2026-04-28" } } ] }, { "id": "vultr/nemotron-cascade-2-30b-a3b", "provider": "vultr", "model": "nemotron-cascade-2-30b-a3b", "displayName": "NVIDIA Nemotron Cascade 2", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "vultr" ], "aliases": [ "vultr/nvidia/Nemotron-Cascade-2-30B-A3B" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vultr", "model": "nvidia/Nemotron-Cascade-2-30B-A3B", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron Cascade 2" ], "families": [ "nemotron" ], "knowledgeCutoff": "2024-07", "releaseDate": "2025-12-01", "lastUpdated": "2025-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "nvidia/Nemotron-Cascade-2-30B-A3B", "modelKey": "nvidia/Nemotron-Cascade-2-30B-A3B", "displayName": "NVIDIA Nemotron Cascade 2", "family": "nemotron", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "openWeights": true, "releaseDate": "2025-12-01" } } ] }, { "id": "wandb/nvidia-nemotron-3-super-120b-a12b-fp8", "provider": "wandb", "model": "nvidia-nemotron-3-super-120b-a12b-fp8", "displayName": "NVIDIA Nemotron 3 Super 120B", "family": "nemotron", "sources": [ "models.dev" ], "providers": [ "wandb" ], "aliases": [ "wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "wandb", "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "NVIDIA Nemotron 3 Super 120B" ], "families": [ "nemotron" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "modelKey": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "displayName": "NVIDIA Nemotron 3 Super 120B", "family": "nemotron", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-03-11" } } ] }, { "id": "wandb/phi-4-mini-instruct", "provider": "wandb", "model": "phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "family": "phi", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "wandb" ], "aliases": [ "wandb/microsoft/Phi-4-mini-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "wandb", "model": "microsoft/Phi-4-mini-instruct", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.08, "output": 0.35 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/microsoft/Phi-4-mini-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 8000, "output": 35000 } } ] }, "metadata": { "displayNames": [ "Phi-4-mini-instruct" ], "families": [ "phi" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10", "releaseDate": "2024-12-11", "lastUpdated": "2026-03-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "microsoft/Phi-4-mini-instruct", "modelKey": "microsoft/Phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "family": "phi", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2024-12-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/microsoft/Phi-4-mini-instruct", "mode": "chat" } ] }, { "id": "watsonx/allam-1-13b-instruct", "provider": "watsonx", "model": "allam-1-13b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/sdaia/allam-1-13b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/sdaia/allam-1-13b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.8, "output": 1.8 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/sdaia/allam-1-13b-instruct", "mode": "chat" } ] }, { "id": "watsonx/granite-13b-chat-v2", "provider": "watsonx", "model": "granite-13b-chat-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-13b-chat-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-13b-chat-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-13b-chat-v2", "mode": "chat" } ] }, { "id": "watsonx/granite-13b-instruct-v2", "provider": "watsonx", "model": "granite-13b-instruct-v2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-13b-instruct-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-13b-instruct-v2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 0.6 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-13b-instruct-v2", "mode": "chat" } ] }, { "id": "watsonx/granite-3-3-8b-instruct", "provider": "watsonx", "model": "granite-3-3-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-3-3-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-3-3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-3-3-8b-instruct", "mode": "chat" } ] }, { "id": "watsonx/granite-3-8b-instruct", "provider": "watsonx", "model": "granite-3-8b-instruct", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-3-8b-instruct" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 1024, "outputTokens": 1024, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "systemMessages": true, "toolChoice": true, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-3-8b-instruct", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-3-8b-instruct", "mode": "chat" } ] }, { "id": "watsonx/granite-4-h-small", "provider": "watsonx", "model": "granite-4-h-small", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-4-h-small" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 20480, "inputTokens": 20480, "maxTokens": 20480, "outputTokens": 20480, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-4-h-small", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.06, "output": 0.25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-4-h-small", "mode": "chat" } ] }, { "id": "watsonx/granite-guardian-3-2-2b", "provider": "watsonx", "model": "granite-guardian-3-2-2b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-guardian-3-2-2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-guardian-3-2-2b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-guardian-3-2-2b", "mode": "chat" } ] }, { "id": "watsonx/granite-guardian-3-3-8b", "provider": "watsonx", "model": "granite-guardian-3-3-8b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-guardian-3-3-8b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-guardian-3-3-8b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-guardian-3-3-8b", "mode": "chat" } ] }, { "id": "watsonx/granite-ttm-1024-96-r2", "provider": "watsonx", "model": "granite-ttm-1024-96-r2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-ttm-1024-96-r2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-1024-96-r2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.38, "output": 0.38 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-1024-96-r2", "mode": "chat" } ] }, { "id": "watsonx/granite-ttm-1536-96-r2", "provider": "watsonx", "model": "granite-ttm-1536-96-r2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-ttm-1536-96-r2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-1536-96-r2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.38, "output": 0.38 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-1536-96-r2", "mode": "chat" } ] }, { "id": "watsonx/granite-ttm-512-96-r2", "provider": "watsonx", "model": "granite-ttm-512-96-r2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-ttm-512-96-r2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 512, "inputTokens": 512, "maxTokens": 512, "outputTokens": 512, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-512-96-r2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.38, "output": 0.38 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-ttm-512-96-r2", "mode": "chat" } ] }, { "id": "watsonx/granite-vision-3-2-2b", "provider": "watsonx", "model": "granite-vision-3-2-2b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/ibm/granite-vision-3-2-2b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/ibm/granite-vision-3-2-2b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/ibm/granite-vision-3-2-2b", "mode": "chat" } ] }, { "id": "watsonx/jais-13b-chat", "provider": "watsonx", "model": "jais-13b-chat", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/core42/jais-13b-chat" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/core42/jais-13b-chat", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 500, "output": 2000 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/core42/jais-13b-chat", "mode": "chat" } ] }, { "id": "watsonx/mt0-xxl-13b", "provider": "watsonx", "model": "mt0-xxl-13b", "mode": "chat", "sources": [ "litellm" ], "providers": [ "watsonx" ], "aliases": [ "watsonx/bigscience/mt0-xxl-13b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "vision": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "watsonx", "model": "watsonx/bigscience/mt0-xxl-13b", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 500, "output": 2000 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "watsonx", "model": "watsonx/bigscience/mt0-xxl-13b", "mode": "chat" } ] }, { "id": "x-ai/grok-2", "provider": "x-ai", "model": "grok-2", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway", "xai" ], "aliases": [ "vercel_ai_gateway/xai/grok-2", "xai/grok-2" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-2", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-2", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2", "mode": "chat" } ] }, { "id": "x-ai/grok-2-1212", "provider": "x-ai", "model": "grok-2-1212", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-2-1212" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-2-1212", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2-1212", "mode": "chat" } ] }, { "id": "x-ai/grok-2-latest", "provider": "x-ai", "model": "grok-2-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-2-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-2-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2-latest", "mode": "chat" } ] }, { "id": "x-ai/grok-2-vision", "provider": "x-ai", "model": "grok-2-vision", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway", "xai" ], "aliases": [ "vercel_ai_gateway/xai/grok-2-vision", "xai/grok-2-vision" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "supports1MContext": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-2-vision", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-2-vision", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 }, "perImage": { "input": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-2-vision", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2-vision", "mode": "chat" } ] }, { "id": "x-ai/grok-2-vision-1212", "provider": "x-ai", "model": "grok-2-vision-1212", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-2-vision-1212" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-2-vision-1212", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 }, "perImage": { "input": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-02-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2-vision-1212", "mode": "chat", "metadata": { "deprecationDate": "2026-02-28" } } ] }, { "id": "x-ai/grok-2-vision-latest", "provider": "x-ai", "model": "grok-2-vision-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-2-vision-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32768, "inputTokens": 32768, "maxTokens": 32768, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-2-vision-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2, "output": 10 }, "perImage": { "input": 0.000002 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-2-vision-latest", "mode": "chat" } ] }, { "id": "x-ai/grok-3", "provider": "x-ai", "model": "grok-3", "displayName": "Grok 3", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure_ai", "github-models", "helicone", "poe", "vercel_ai_gateway", "xai" ], "aliases": [ "azure_ai/global/grok-3", "azure_ai/grok-3", "github-models/xai/grok-3", "helicone/grok-3", "poe/xai/grok-3", "vercel_ai_gateway/xai/grok-3", "xai/grok-3" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "xai/grok-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/global/grok-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Grok 3", "xAI Grok 3" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-09", "lastUpdated": "2024-12-09", "deprecationDate": "2026-05-15", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "xai/grok-3", "modelKey": "xai/grok-3", "displayName": "Grok 3", "family": "grok", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-09", "openWeights": false, "releaseDate": "2024-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-3", "modelKey": "grok-3", "displayName": "xAI Grok 3", "family": "grok", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-3", "modelKey": "xai/grok-3", "displayName": "Grok 3", "family": "grok", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/global/grok-3", "mode": "chat", "metadata": { "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-3", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-beta", "provider": "x-ai", "model": "grok-3-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-beta", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-fast", "provider": "x-ai", "model": "grok-3-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway" ], "aliases": [ "vercel_ai_gateway/xai/grok-3-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-fast", "mode": "chat" } ] }, { "id": "x-ai/grok-3-fast-beta", "provider": "x-ai", "model": "grok-3-fast-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-fast-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-fast-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-fast-beta", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-fast-latest", "provider": "x-ai", "model": "grok-3-fast-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-fast-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-fast-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 1.25, "input": 5, "output": 25 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-fast-latest", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-latest", "provider": "x-ai", "model": "grok-3-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-latest", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini", "provider": "x-ai", "model": "grok-3-mini", "displayName": "Grok 3 Mini", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure_ai", "github-models", "helicone", "poe", "vercel_ai_gateway", "xai" ], "aliases": [ "azure_ai/global/grok-3-mini", "azure_ai/grok-3-mini", "github-models/xai/grok-3-mini", "helicone/grok-3-mini", "poe/xai/grok-3-mini", "vercel_ai_gateway/xai/grok-3-mini", "xai/grok-3-mini" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "github-models", "model": "xai/grok-3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 0.5 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-3-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 0.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/global/grok-3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.27 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.25, "output": 1.27 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.3, "output": 0.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Grok 3 Mini", "xAI Grok 3 Mini" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2024-12-09", "lastUpdated": "2024-12-09", "deprecationDate": "2026-02-28", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "github-models", "providerName": "GitHub Models", "providerApi": "https://models.github.ai/inference", "providerDoc": "https://docs.github.com/en/github-models", "model": "xai/grok-3-mini", "modelKey": "xai/grok-3-mini", "displayName": "Grok 3 Mini", "family": "grok", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-09", "openWeights": false, "releaseDate": "2024-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-3-mini", "modelKey": "grok-3-mini", "displayName": "xAI Grok 3 Mini", "family": "grok", "metadata": { "knowledgeCutoff": "2024-06", "lastUpdated": "2024-06-01", "openWeights": false, "releaseDate": "2024-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-3-mini", "modelKey": "xai/grok-3-mini", "displayName": "Grok 3 Mini", "family": "grok", "metadata": { "lastUpdated": "2025-04-11", "openWeights": false, "releaseDate": "2025-04-11" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/global/grok-3-mini", "mode": "chat", "metadata": { "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-3-mini", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-mini", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini", "mode": "chat", "metadata": { "deprecationDate": "2026-02-28", "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini-beta", "provider": "x-ai", "model": "grok-3-mini-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-mini-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-02-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini-beta", "mode": "chat", "metadata": { "deprecationDate": "2026-02-28", "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini-fast", "provider": "x-ai", "model": "grok-3-mini-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "vercel_ai_gateway", "xai" ], "aliases": [ "vercel_ai_gateway/xai/grok-3-mini-fast", "xai/grok-3-mini-fast" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false, "promptCaching": true, "reasoning": true, "responseSchema": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-mini-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 4 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-3-mini-fast", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini-fast", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini-fast-beta", "provider": "x-ai", "model": "grok-3-mini-fast-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-mini-fast-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini-fast-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini-fast-beta", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini-fast-latest", "provider": "x-ai", "model": "grok-3-mini-fast-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-mini-fast-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini-fast-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.15, "input": 0.6, "output": 4 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini-fast-latest", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-3-mini-latest", "provider": "x-ai", "model": "grok-3-mini-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-3-mini-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-3-mini-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.075, "input": 0.3, "output": 0.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-3-mini-latest", "mode": "chat", "metadata": { "source": "https://x.ai/api#pricing" } } ] }, { "id": "x-ai/grok-4", "provider": "x-ai", "model": "grok-4", "displayName": "Grok 4", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "azure_ai", "fastrouter", "helicone", "openrouter", "poe", "replicate", "requesty", "vercel_ai_gateway", "xai", "zenmux" ], "aliases": [ "azure_ai/grok-4", "fastrouter/x-ai/grok-4", "helicone/grok-4", "openrouter/x-ai/grok-4", "poe/xai/grok-4", "replicate/xai/grok-4", "requesty/xai/grok-4", "vercel_ai_gateway/xai/grok-4", "xai/grok-4", "zenmux/x-ai/grok-4" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "systemMessages": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "x-ai/grok-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "cacheWrite": 15, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "requesty", "model": "xai/grok-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "cacheWrite": 3, "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.75, "input": 3, "output": 15 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/x-ai/grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "replicate", "model": "replicate/xai/grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 7.2, "output": 36 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 } } ] }, "metadata": { "displayNames": [ "Grok 4", "Grok-4", "xAI Grok 4" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-07", "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "x-ai/grok-4", "modelKey": "x-ai/grok-4", "displayName": "Grok 4", "family": "grok", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-4", "modelKey": "grok-4", "displayName": "xAI Grok 4", "family": "grok", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-09", "openWeights": false, "releaseDate": "2024-07-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4", "modelKey": "xai/grok-4", "displayName": "Grok-4", "family": "grok", "metadata": { "lastUpdated": "2025-07-10", "openWeights": false, "releaseDate": "2025-07-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "xai/grok-4", "modelKey": "xai/grok-4", "displayName": "Grok 4", "family": "grok", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-09", "openWeights": false, "releaseDate": "2025-09-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4", "modelKey": "x-ai/grok-4", "displayName": "Grok 4", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-4", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/x-ai/grok-4", "mode": "chat", "metadata": { "source": "https://openrouter.ai/x-ai/grok-4" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "replicate", "model": "replicate/xai/grok-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/xai/grok-4", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4-0709", "provider": "x-ai", "model": "grok-4-0709", "displayName": "Grok 4", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "jiekou", "llmgateway", "xai" ], "aliases": [ "abacus/grok-4-0709", "jiekou/grok-4-0709", "llmgateway/grok-4-0709", "xai/grok-4-0709" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "grok-4-0709", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-4-0709", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.7, "output": 13.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-0709", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 15 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4-0709", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "extra": { "input_cost_per_token_above_128k_tokens": 0.000006, "output_cost_per_token_above_128k_tokens": 0.00003 } } ] }, "metadata": { "displayNames": [ "Grok 4", "Grok 4 (0709)", "grok-4-0709" ], "families": [ "grok" ], "modes": [ "chat" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "deprecationDate": "2026-05-15", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "grok-4-0709", "modelKey": "grok-4-0709", "displayName": "Grok 4", "family": "grok", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-4-0709", "modelKey": "grok-4-0709", "displayName": "grok-4-0709", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-0709", "modelKey": "grok-4-0709", "displayName": "Grok 4 (0709)", "family": "grok", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-0709", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4-1-fast", "provider": "x-ai", "model": "grok-4-1-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4-1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-4-1-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-1-fast", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" } } ] }, { "id": "x-ai/grok-4-1-fast-non-reasoning", "provider": "x-ai", "model": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "azure", "azure_ai", "frogbot", "helicone", "jiekou", "perplexity-agent", "xai" ], "aliases": [ "302ai/grok-4-1-fast-non-reasoning", "abacus/grok-4-1-fast-non-reasoning", "azure/grok-4-1-fast-non-reasoning", "azure_ai/grok-4-1-fast-non-reasoning", "frogbot/grok-4-1-fast-non-reasoning", "helicone/grok-4-1-fast-non-reasoning", "jiekou/grok-4-1-fast-non-reasoning", "perplexity-agent/xai/grok-4-1-fast-non-reasoning", "xai/grok-4-1-fast-non-reasoning" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "abacus", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "azure", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "frogbot", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.45 } }, { "source": "models.dev", "provider": "perplexity-agent", "model": "xai/grok-4-1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-4-1-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4-1-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast (Non-Reasoning)", "grok-4-1-fast-non-reasoning", "xAI Grok 4.1 Fast Non-Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-11-20", "lastUpdated": "2025-11-20", "deprecationDate": "2026-05-15", "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "Grok 4.1 Fast (Non-Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2025-11-17", "openWeights": false, "releaseDate": "2025-11-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "Grok 4.1 Fast (Non-Reasoning)", "family": "grok", "status": "beta", "metadata": { "lastUpdated": "2025-06-27", "openWeights": false, "releaseDate": "2025-06-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "Grok 4.1 Fast (Non-Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "xAI Grok 4.1 Fast Non-Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-17", "openWeights": false, "releaseDate": "2025-11-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-4-1-fast-non-reasoning", "modelKey": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "perplexity-agent", "providerName": "Perplexity Agent", "providerApi": "https://api.perplexity.ai/v1", "providerDoc": "https://docs.perplexity.ai/docs/agent-api/models", "model": "xai/grok-4-1-fast-non-reasoning", "modelKey": "xai/grok-4-1-fast-non-reasoning", "displayName": "Grok 4.1 Fast (Non-Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-4-1-fast-non-reasoning", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-1-fast-non-reasoning", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning" } } ] }, { "id": "x-ai/grok-4-1-fast-non-reasoning-latest", "provider": "x-ai", "model": "grok-4-1-fast-non-reasoning-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4-1-fast-non-reasoning-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-4-1-fast-non-reasoning-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-05-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-1-fast-non-reasoning-latest", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning" } } ] }, { "id": "x-ai/grok-4-1-fast-reasoning", "provider": "x-ai", "model": "grok-4-1-fast-reasoning", "displayName": "grok-4-1-fast-reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "azure", "azure_ai", "frogbot", "helicone", "jiekou", "llmgateway", "xai" ], "aliases": [ "302ai/grok-4-1-fast-reasoning", "azure/grok-4-1-fast-reasoning", "azure_ai/grok-4-1-fast-reasoning", "frogbot/grok-4-1-fast-reasoning", "helicone/grok-4-1-fast-reasoning", "jiekou/grok-4-1-fast-reasoning", "llmgateway/grok-4-1-fast-reasoning", "xai/grok-4-1-fast-reasoning" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "azure", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "frogbot", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.45 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-4-1-fast-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4-1-fast-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast (Reasoning)", "Grok 4.1 Fast Reasoning", "grok-4-1-fast-reasoning", "xAI Grok 4.1 Fast Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-11-20", "lastUpdated": "2025-11-20", "deprecationDate": "2026-05-15", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "grok-4-1-fast-reasoning", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "Grok 4.1 Fast (Reasoning)", "family": "grok", "status": "beta", "metadata": { "lastUpdated": "2025-06-27", "openWeights": false, "releaseDate": "2025-06-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "Grok 4.1 Fast (Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-11-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "xAI Grok 4.1 Fast Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2025-11-17", "openWeights": false, "releaseDate": "2025-11-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "grok-4-1-fast-reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-1-fast-reasoning", "modelKey": "grok-4-1-fast-reasoning", "displayName": "Grok 4.1 Fast Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-4-1-fast-reasoning", "mode": "chat", "metadata": { "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-1-fast-reasoning", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" } } ] }, { "id": "x-ai/grok-4-1-fast-reasoning-latest", "provider": "x-ai", "model": "grok-4-1-fast-reasoning-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4-1-fast-reasoning-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": true, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-4-1-fast-reasoning-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-05-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-1-fast-reasoning-latest", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" } } ] }, { "id": "x-ai/grok-4-20", "provider": "x-ai", "model": "grok-4-20", "displayName": "Grok 4.20", "family": "grok", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/grok-4-20" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "grok-4-20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.23, "input": 1.42, "output": 2.83 }, "tiered": { "contextOver200K": { "input": 2.83, "output": 5.67, "cache_read": 0.45 }, "tiers": [ { "input": 2.83, "output": 5.67, "cache_read": 0.45, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20" ], "families": [ "grok" ], "releaseDate": "2026-03-12", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "grok-4-20", "modelKey": "grok-4-20", "displayName": "Grok 4.20", "family": "grok", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-12" } } ] }, { "id": "x-ai/grok-4-20-beta-0309-non-reasoning", "provider": "x-ai", "model": "grok-4-20-beta-0309-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/grok-4-20-beta-0309-non-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-20-beta-0309-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Non-Reasoning)" ], "families": [ "grok" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-20-beta-0309-non-reasoning", "modelKey": "grok-4-20-beta-0309-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09" } } ] }, { "id": "x-ai/grok-4-20-beta-0309-reasoning", "provider": "x-ai", "model": "grok-4-20-beta-0309-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/grok-4-20-beta-0309-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-20-beta-0309-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Reasoning)" ], "families": [ "grok" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-20-beta-0309-reasoning", "modelKey": "grok-4-20-beta-0309-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "x-ai/grok-4-20-multi-agent", "provider": "x-ai", "model": "grok-4-20-multi-agent", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "sources": [ "models.dev" ], "providers": [ "venice" ], "aliases": [ "venice/grok-4-20-multi-agent" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "venice", "model": "grok-4-20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.23, "input": 1.42, "output": 2.83 }, "tiered": { "contextOver200K": { "input": 2.83, "output": 5.67, "cache_read": 0.45 }, "tiers": [ { "input": 2.83, "output": 5.67, "cache_read": 0.45, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Multi-Agent" ], "families": [ "grok" ], "releaseDate": "2026-03-12", "lastUpdated": "2026-06-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "grok-4-20-multi-agent", "modelKey": "grok-4-20-multi-agent", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-03-12" } } ] }, { "id": "x-ai/grok-4-20-non-reasoning", "provider": "x-ai", "model": "grok-4-20-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "sources": [ "models.dev" ], "providers": [ "azure", "llmgateway" ], "aliases": [ "azure/grok-4-20-non-reasoning", "llmgateway/grok-4-20-non-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "grok-4-20-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-20-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Non-Reasoning)" ], "families": [ "grok" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-09", "releaseDate": "2026-04-08", "lastUpdated": "2026-04-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-20-non-reasoning", "modelKey": "grok-4-20-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "status": "beta", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-04-08", "openWeights": false, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-20-non-reasoning", "modelKey": "grok-4-20-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09" } } ] }, { "id": "x-ai/grok-4-20-reasoning", "provider": "x-ai", "model": "grok-4-20-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "sources": [ "models.dev" ], "providers": [ "azure", "llmgateway" ], "aliases": [ "azure/grok-4-20-reasoning", "llmgateway/grok-4-20-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "azure", "model": "grok-4-20-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-20-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Reasoning)" ], "families": [ "grok" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-09", "releaseDate": "2026-04-08", "lastUpdated": "2026-04-08", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-20-reasoning", "modelKey": "grok-4-20-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "status": "beta", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2026-04-08", "openWeights": false, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-20-reasoning", "modelKey": "grok-4-20-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "x-ai/grok-4-3", "provider": "x-ai", "model": "grok-4-3", "displayName": "Grok 4.3", "family": "grok", "sources": [ "models.dev" ], "providers": [ "frogbot", "llmgateway", "venice" ], "aliases": [ "frogbot/grok-4-3", "llmgateway/grok-4-3", "venice/grok-4-3" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "frogbot", "model": "grok-4-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "venice", "model": "grok-4-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.23, "input": 1.42, "output": 2.83 }, "tiered": { "contextOver200K": { "input": 2.83, "output": 5.67, "cache_read": 0.45 }, "tiers": [ { "input": 2.83, "output": 5.67, "cache_read": 0.45, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.3" ], "families": [ "grok" ], "knowledgeCutoff": "2024-11", "releaseDate": "2026-04-30", "lastUpdated": "2026-04-30", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "grok-4-3", "modelKey": "grok-4-3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "knowledgeCutoff": "2024-11", "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-3", "modelKey": "grok-4-3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "grok-4-3", "modelKey": "grok-4-3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-04-18" } } ] }, { "id": "x-ai/grok-4-fast", "provider": "x-ai", "model": "grok-4-fast", "displayName": "Grok 4 Fast", "family": "grok", "sources": [ "models.dev" ], "providers": [ "qiniu-ai", "requesty", "zenmux" ], "aliases": [ "qiniu-ai/x-ai/grok-4-fast", "requesty/xai/grok-4-fast", "zenmux/x-ai/grok-4-fast" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "requesty", "model": "xai/grok-4-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0.2, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Grok 4 Fast", "x-AI/Grok-4-Fast" ], "families": [ "grok" ], "knowledgeCutoff": "2025-01", "releaseDate": "2025-09-20", "lastUpdated": "2025-09-20", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4-fast", "modelKey": "x-ai/grok-4-fast", "displayName": "x-AI/Grok-4-Fast", "metadata": { "lastUpdated": "2025-09-20", "openWeights": false, "releaseDate": "2025-09-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "requesty", "providerName": "Requesty", "providerApi": "https://router.requesty.ai/v1", "providerDoc": "https://requesty.ai/solution/llm-routing/models", "model": "xai/grok-4-fast", "modelKey": "xai/grok-4-fast", "displayName": "Grok 4 Fast", "family": "grok", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4-fast", "modelKey": "x-ai/grok-4-fast", "displayName": "Grok 4 Fast", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "x-ai/grok-4-fast-non-reasoning", "provider": "x-ai", "model": "grok-4-fast-non-reasoning", "displayName": "grok-4-fast-non-reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "abacus", "azure_ai", "helicone", "jiekou", "poe", "qiniu-ai", "xai" ], "aliases": [ "302ai/grok-4-fast-non-reasoning", "abacus/grok-4-fast-non-reasoning", "azure_ai/grok-4-fast-non-reasoning", "helicone/grok-4-fast-non-reasoning", "jiekou/grok-4-fast-non-reasoning", "poe/xai/grok-4-fast-non-reasoning", "qiniu-ai/x-ai/grok-4-fast-non-reasoning", "xai/grok-4-fast-non-reasoning" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "abacus", "model": "grok-4-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-4-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-4-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.45 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-4-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-4-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "displayNames": [ "Grok 4 Fast (Non-Reasoning)", "Grok-4-Fast-Non-Reasoning", "X-Ai/Grok-4-Fast-Non-Reasoning", "grok-4-fast-non-reasoning", "xAI Grok 4 Fast Non-Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "deprecationDate": "2026-05-15", "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4-fast-non-reasoning", "modelKey": "grok-4-fast-non-reasoning", "displayName": "grok-4-fast-non-reasoning", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "grok-4-fast-non-reasoning", "modelKey": "grok-4-fast-non-reasoning", "displayName": "Grok 4 Fast (Non-Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-4-fast-non-reasoning", "modelKey": "grok-4-fast-non-reasoning", "displayName": "xAI Grok 4 Fast Non-Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-4-fast-non-reasoning", "modelKey": "grok-4-fast-non-reasoning", "displayName": "grok-4-fast-non-reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4-fast-non-reasoning", "modelKey": "xai/grok-4-fast-non-reasoning", "displayName": "Grok-4-Fast-Non-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-09-16", "openWeights": false, "releaseDate": "2025-09-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4-fast-non-reasoning", "modelKey": "x-ai/grok-4-fast-non-reasoning", "displayName": "X-Ai/Grok-4-Fast-Non-Reasoning", "metadata": { "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-4-fast-non-reasoning", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-fast-non-reasoning", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4-fast-reasoning", "provider": "x-ai", "model": "grok-4-fast-reasoning", "displayName": "grok-4-fast-reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "azure", "azure-cognitive-services", "azure_ai", "helicone", "jiekou", "llmgateway", "poe", "qiniu-ai", "xai" ], "aliases": [ "302ai/grok-4-fast-reasoning", "azure-cognitive-services/grok-4-fast-reasoning", "azure/grok-4-fast-reasoning", "azure_ai/grok-4-fast-reasoning", "helicone/grok-4-fast-reasoning", "jiekou/grok-4-fast-reasoning", "llmgateway/grok-4-fast-reasoning", "poe/xai/grok-4-fast-reasoning", "qiniu-ai/x-ai/grok-4-fast-reasoning", "xai/grok-4-fast-reasoning" ], "mergedProviderModelRecords": 10, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "azure-cognitive-services", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "azure", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 0.45 } }, { "source": "models.dev", "provider": "llmgateway", "model": "grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-4-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-4-fast-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4-fast-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 }, "extra": { "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } } ] }, "metadata": { "displayNames": [ "Grok 4 Fast (Reasoning)", "Grok 4 Fast Reasoning", "Grok-4-Fast-Reasoning", "X-Ai/Grok-4-Fast-Reasoning", "grok-4-fast-reasoning", "xAI: Grok 4 Fast Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-09-23", "lastUpdated": "2025-09-23", "deprecationDate": "2026-05-15", "providerModelRecordCount": 10 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "grok-4-fast-reasoning", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-09-23", "openWeights": false, "releaseDate": "2025-09-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure-cognitive-services", "providerName": "Azure Cognitive Services", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "Grok 4 Fast (Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "azure", "providerName": "Azure", "providerDoc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "Grok 4 Fast (Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-19", "openWeights": false, "releaseDate": "2025-09-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "xAI: Grok 4 Fast Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2025-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "grok-4-fast-reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-4-fast-reasoning", "modelKey": "grok-4-fast-reasoning", "displayName": "Grok 4 Fast Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4-fast-reasoning", "modelKey": "xai/grok-4-fast-reasoning", "displayName": "Grok-4-Fast-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-09-16", "openWeights": false, "releaseDate": "2025-09-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4-fast-reasoning", "modelKey": "x-ai/grok-4-fast-reasoning", "displayName": "X-Ai/Grok-4-Fast-Reasoning", "metadata": { "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-4-fast-reasoning", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-fast-reasoning", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4-latest", "provider": "x-ai", "model": "grok-4-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-4-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 3, "output": 15 }, "extra": { "input_cost_per_token_above_128k_tokens": 0.000006, "output_cost_per_token_above_128k_tokens": 0.00003 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4-latest", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4.1", "provider": "x-ai", "model": "grok-4.1", "displayName": "grok-4.1", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/grok-4.1" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 10 } } ] }, "metadata": { "displayNames": [ "grok-4.1" ], "knowledgeCutoff": "2025-06", "releaseDate": "2025-11-18", "lastUpdated": "2025-11-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4.1", "modelKey": "grok-4.1", "displayName": "grok-4.1", "metadata": { "knowledgeCutoff": "2025-06", "lastUpdated": "2025-11-18", "openWeights": false, "releaseDate": "2025-11-18" } } ] }, { "id": "x-ai/grok-4.1-fast", "provider": "x-ai", "model": "grok-4.1-fast", "displayName": "Grok 4.1 Fast", "sources": [ "models.dev" ], "providers": [ "qiniu-ai", "zenmux" ], "aliases": [ "qiniu-ai/x-ai/grok-4.1-fast", "zenmux/x-ai/grok-4.1-fast" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4.1-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast", "x-AI/Grok-4.1-Fast" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-11-20", "lastUpdated": "2025-11-20", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4.1-fast", "modelKey": "x-ai/grok-4.1-fast", "displayName": "x-AI/Grok-4.1-Fast", "metadata": { "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4.1-fast", "modelKey": "x-ai/grok-4.1-fast", "displayName": "Grok 4.1 Fast", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "x-ai/grok-4.1-fast-non-reasoning", "provider": "x-ai", "model": "grok-4.1-fast-non-reasoning", "displayName": "Grok 4.1 Fast Non-Reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "poe", "qiniu-ai", "vercel", "vertex_ai", "zenmux" ], "aliases": [ "poe/xai/grok-4.1-fast-non-reasoning", "qiniu-ai/x-ai/grok-4.1-fast-non-reasoning", "vercel/xai/grok-4.1-fast-non-reasoning", "vertex_ai/xai/grok-4.1-fast-non-reasoning", "zenmux/x-ai/grok-4.1-fast-non-reasoning" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4.1-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.1-fast-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast Non Reasoning", "Grok 4.1 Fast Non-Reasoning", "Grok-4.1-Fast-Non-Reasoning", "X-Ai/Grok 4.1 Fast Non Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-11-19", "lastUpdated": "2025-11-19", "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4.1-fast-non-reasoning", "modelKey": "xai/grok-4.1-fast-non-reasoning", "displayName": "Grok-4.1-Fast-Non-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4.1-fast-non-reasoning", "modelKey": "x-ai/grok-4.1-fast-non-reasoning", "displayName": "X-Ai/Grok 4.1 Fast Non Reasoning", "metadata": { "lastUpdated": "2025-12-19", "openWeights": false, "releaseDate": "2025-12-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.1-fast-non-reasoning", "modelKey": "xai/grok-4.1-fast-non-reasoning", "displayName": "Grok 4.1 Fast Non-Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4.1-fast-non-reasoning", "modelKey": "x-ai/grok-4.1-fast-non-reasoning", "displayName": "Grok 4.1 Fast Non Reasoning", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-20", "openWeights": false, "releaseDate": "2025-11-20" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.1-fast-non-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" } } ] }, { "id": "x-ai/grok-4.1-fast-reasoning", "provider": "x-ai", "model": "grok-4.1-fast-reasoning", "displayName": "Grok 4.1 Fast Reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "poe", "qiniu-ai", "vercel", "vertex_ai" ], "aliases": [ "poe/xai/grok-4.1-fast-reasoning", "qiniu-ai/x-ai/grok-4.1-fast-reasoning", "vercel/xai/grok-4.1-fast-reasoning", "vertex_ai/xai/grok-4.1-fast-reasoning" ], "mergedProviderModelRecords": 4, "limits": { "contextTokens": 20000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "structuredOutput": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.1-fast-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.1-fast-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.05, "input": 0.2, "output": 0.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast Reasoning", "Grok-4.1-Fast-Reasoning", "X-Ai/Grok 4.1 Fast Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-11-19", "lastUpdated": "2025-11-19", "providerModelRecordCount": 4 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4.1-fast-reasoning", "modelKey": "xai/grok-4.1-fast-reasoning", "displayName": "Grok-4.1-Fast-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2025-11-19", "openWeights": false, "releaseDate": "2025-11-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-4.1-fast-reasoning", "modelKey": "x-ai/grok-4.1-fast-reasoning", "displayName": "X-Ai/Grok 4.1 Fast Reasoning", "metadata": { "lastUpdated": "2025-12-19", "openWeights": false, "releaseDate": "2025-12-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.1-fast-reasoning", "modelKey": "xai/grok-4.1-fast-reasoning", "displayName": "Grok 4.1 Fast Reasoning", "family": "grok", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.1-fast-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" } } ] }, { "id": "x-ai/grok-4.2-fast", "provider": "x-ai", "model": "grok-4.2-fast", "displayName": "Grok 4.2 Fast", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/x-ai/grok-4.2-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4.2-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 9 } } ] }, "metadata": { "displayNames": [ "Grok 4.2 Fast" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-20", "lastUpdated": "2026-03-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4.2-fast", "modelKey": "x-ai/grok-4.2-fast", "displayName": "Grok 4.2 Fast", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "x-ai/grok-4.2-fast-non-reasoning", "provider": "x-ai", "model": "grok-4.2-fast-non-reasoning", "displayName": "Grok 4.2 Fast Non Reasoning", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/x-ai/grok-4.2-fast-non-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4.2-fast-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3, "output": 9 } } ] }, "metadata": { "displayNames": [ "Grok 4.2 Fast Non Reasoning" ], "knowledgeCutoff": "2025-08-31", "releaseDate": "2026-03-20", "lastUpdated": "2026-03-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4.2-fast-non-reasoning", "modelKey": "x-ai/grok-4.2-fast-non-reasoning", "displayName": "Grok 4.2 Fast Non Reasoning", "metadata": { "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "x-ai/grok-4.20", "provider": "x-ai", "model": "grok-4.20", "displayName": "xAI: Grok 4.20", "family": "grok", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter" ], "aliases": [ "kilo/x-ai/grok-4.20", "nano-gpt/x-ai/grok-4.20", "openrouter/x-ai/grok-4.20" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "x-ai/grok-4.20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "x-ai/grok-4.20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "openrouter", "model": "x-ai/grok-4.20", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "x-ai/grok-4.20", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Grok 4.20", "xAI: Grok 4.20" ], "families": [ "grok" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2026-03-31", "lastUpdated": "2026-04-11", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "x-ai/grok-4.20", "modelKey": "x-ai/grok-4.20", "displayName": "xAI: Grok 4.20", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "x-ai/grok-4.20", "modelKey": "x-ai/grok-4.20", "displayName": "Grok 4.20", "metadata": { "lastUpdated": "2026-03-31", "openWeights": false, "releaseDate": "2026-03-31", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "x-ai/grok-4.20", "modelKey": "x-ai/grok-4.20", "displayName": "Grok 4.20", "family": "grok", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2026-03-31", "openWeights": false, "releaseDate": "2026-03-31" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "x-ai/grok-4.20", "displayName": "xAI: Grok 4.20", "metadata": { "canonicalSlug": "x-ai/grok-4.20-20260309", "createdAt": "2026-03-31T17:43:39.000Z", "knowledgeCutoff": "2025-09-01", "links": { "details": "/api/v1/models/x-ai/grok-4.20-20260309/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": false }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Grok", "topProvider": { "context_length": 2000000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "x-ai/grok-4.20-0309-non-reasoning", "provider": "x-ai", "model": "grok-4.20-0309-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "sources": [ "models.dev" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4.20-0309-non-reasoning" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xai", "model": "grok-4.20-0309-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Non-Reasoning)" ], "families": [ "grok" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-4.20-0309-non-reasoning", "modelKey": "grok-4.20-0309-non-reasoning", "displayName": "Grok 4.20 (Non-Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09" } } ] }, { "id": "x-ai/grok-4.20-0309-reasoning", "provider": "x-ai", "model": "grok-4.20-0309-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "merge-gateway", "xai" ], "aliases": [ "merge-gateway/xai/grok-4.20-0309-reasoning", "xai/grok-4.20-0309-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "merge-gateway", "model": "xai/grok-4.20-0309-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "xai", "model": "grok-4.20-0309-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4.20-0309-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 (Reasoning)" ], "families": [ "grok" ], "modes": [ "chat" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-09", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "xai/grok-4.20-0309-reasoning", "modelKey": "xai/grok-4.20-0309-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-4.20-0309-reasoning", "modelKey": "grok-4.20-0309-reasoning", "displayName": "Grok 4.20 (Reasoning)", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.20-0309-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4.20-beta-0309-non-reasoning", "provider": "x-ai", "model": "grok-4.20-beta-0309-non-reasoning", "displayName": "grok-4.20-beta-0309-non-reasoning", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "xai" ], "aliases": [ "302ai/grok-4.20-beta-0309-non-reasoning", "xai/grok-4.20-beta-0309-non-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4.20-beta-0309-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4.20-beta-0309-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "grok-4.20-beta-0309-non-reasoning" ], "modes": [ "chat" ], "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4.20-beta-0309-non-reasoning", "modelKey": "grok-4.20-beta-0309-non-reasoning", "displayName": "grok-4.20-beta-0309-non-reasoning", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.20-beta-0309-non-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4.20-beta-0309-reasoning", "provider": "x-ai", "model": "grok-4.20-beta-0309-reasoning", "displayName": "grok-4.20-beta-0309-reasoning", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "xai" ], "aliases": [ "302ai/grok-4.20-beta-0309-reasoning", "xai/grok-4.20-beta-0309-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4.20-beta-0309-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4.20-beta-0309-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "grok-4.20-beta-0309-reasoning" ], "modes": [ "chat" ], "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4.20-beta-0309-reasoning", "modelKey": "grok-4.20-beta-0309-reasoning", "displayName": "grok-4.20-beta-0309-reasoning", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.20-beta-0309-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4.20-multi-agent", "provider": "x-ai", "model": "grok-4.20-multi-agent", "displayName": "xAI: Grok 4.20 Multi-Agent", "family": "grok", "sources": [ "models.dev", "openrouter" ], "providers": [ "kilo", "nano-gpt", "openrouter", "poe", "vercel" ], "aliases": [ "kilo/x-ai/grok-4.20-multi-agent", "nano-gpt/x-ai/grok-4.20-multi-agent", "openrouter/x-ai/grok-4.20-multi-agent", "poe/xai/grok-4.20-multi-agent", "vercel/xai/grok-4.20-multi-agent" ], "mergedProviderModelRecords": 5, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "file", "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "structuredOutput": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": false, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "x-ai/grok-4.20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "x-ai/grok-4.20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "openrouter", "model": "x-ai/grok-4.20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-4.20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } }, { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-multi-agent", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "openrouter", "provider": "openrouter", "model": "x-ai/grok-4.20-multi-agent", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Multi-Agent", "Grok-4.20-Multi-Agent", "xAI: Grok 4.20 Multi-Agent" ], "families": [ "grok" ], "knowledgeCutoff": "2025-09-01", "releaseDate": "2026-03-31", "lastUpdated": "2026-04-11", "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "providerModelRecordCount": 5 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "x-ai/grok-4.20-multi-agent", "modelKey": "x-ai/grok-4.20-multi-agent", "displayName": "xAI: Grok 4.20 Multi-Agent", "metadata": { "lastUpdated": "2026-04-11", "openWeights": false, "releaseDate": "2026-03-31" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "x-ai/grok-4.20-multi-agent", "modelKey": "x-ai/grok-4.20-multi-agent", "displayName": "Grok 4.20 Multi-Agent", "metadata": { "lastUpdated": "2026-03-31", "openWeights": false, "releaseDate": "2026-03-31", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "x-ai/grok-4.20-multi-agent", "modelKey": "x-ai/grok-4.20-multi-agent", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "metadata": { "knowledgeCutoff": "2025-09-01", "lastUpdated": "2026-03-31", "openWeights": false, "releaseDate": "2026-03-31", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-4.20-multi-agent", "modelKey": "xai/grok-4.20-multi-agent", "displayName": "Grok-4.20-Multi-Agent", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-multi-agent", "modelKey": "xai/grok-4.20-multi-agent", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "metadata": { "lastUpdated": "2026-03-23", "openWeights": false, "releaseDate": "2026-03-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "x-ai/grok-4.20-multi-agent", "displayName": "xAI: Grok 4.20 Multi-Agent", "metadata": { "canonicalSlug": "x-ai/grok-4.20-multi-agent-20260309", "createdAt": "2026-03-31T17:45:58.000Z", "knowledgeCutoff": "2025-09-01", "links": { "details": "/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints" }, "reasoning": { "mandatory": true, "default_enabled": true, "supported_efforts": [ "xhigh", "high", "medium", "low" ], "default_effort": "medium" }, "supportedParameters": [ "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "tokenizer": "Grok", "topProvider": { "context_length": 2000000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "x-ai/grok-4.20-multi-agent-0309", "provider": "x-ai", "model": "grok-4.20-multi-agent-0309", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "sources": [ "models.dev" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4.20-multi-agent-0309" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 30000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xai", "model": "grok-4.20-multi-agent-0309", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Multi-Agent" ], "families": [ "grok" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-4.20-multi-agent-0309", "modelKey": "grok-4.20-multi-agent-0309", "displayName": "Grok 4.20 Multi-Agent", "family": "grok", "metadata": { "lastUpdated": "2026-03-09", "openWeights": false, "releaseDate": "2026-03-09", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high", "xhigh" ] } ] } } ] }, { "id": "x-ai/grok-4.20-multi-agent-beta", "provider": "x-ai", "model": "grok-4.20-multi-agent-beta", "displayName": "Grok 4.20 Multi Agent Beta", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xai/grok-4.20-multi-agent-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-multi-agent-beta", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Multi Agent Beta" ], "families": [ "grok" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-multi-agent-beta", "modelKey": "xai/grok-4.20-multi-agent-beta", "displayName": "Grok 4.20 Multi Agent Beta", "family": "grok", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "high" ] } ] } } ] }, { "id": "x-ai/grok-4.20-multi-agent-beta-0309", "provider": "x-ai", "model": "grok-4.20-multi-agent-beta-0309", "displayName": "grok-4.20-multi-agent-beta-0309", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "xai" ], "aliases": [ "302ai/grok-4.20-multi-agent-beta-0309", "xai/grok-4.20-multi-agent-beta-0309" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "grok-4.20-multi-agent-beta-0309", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2, "output": 6 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4.20-multi-agent-beta-0309", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "grok-4.20-multi-agent-beta-0309" ], "modes": [ "chat" ], "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "grok-4.20-multi-agent-beta-0309", "modelKey": "grok-4.20-multi-agent-beta-0309", "displayName": "grok-4.20-multi-agent-beta-0309", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.20-multi-agent-beta-0309", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-4.20-non-reasoning", "provider": "x-ai", "model": "grok-4.20-non-reasoning", "displayName": "Grok 4.20 Non-Reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vertex_ai" ], "aliases": [ "vercel/xai/grok-4.20-non-reasoning", "vertex_ai/xai/grok-4.20-non-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-non-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.20-non-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Non-Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-non-reasoning", "modelKey": "xai/grok-4.20-non-reasoning", "displayName": "Grok 4.20 Non-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-03-23", "openWeights": false, "releaseDate": "2026-03-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.20-non-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" } } ] }, { "id": "x-ai/grok-4.20-non-reasoning-beta", "provider": "x-ai", "model": "grok-4.20-non-reasoning-beta", "displayName": "Grok 4.20 Beta Non-Reasoning", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xai/grok-4.20-non-reasoning-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-non-reasoning-beta", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.4, "input": 1.25, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Beta Non-Reasoning" ], "families": [ "grok" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-non-reasoning-beta", "modelKey": "xai/grok-4.20-non-reasoning-beta", "displayName": "Grok 4.20 Beta Non-Reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-11" } } ] }, { "id": "x-ai/grok-4.20-reasoning", "provider": "x-ai", "model": "grok-4.20-reasoning", "displayName": "Grok 4.20 Reasoning", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "vercel", "vertex_ai" ], "aliases": [ "vercel/xai/grok-4.20-reasoning", "vertex_ai/xai/grok-4.20-reasoning" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 2000000, "inputTokens": 2000000, "maxTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-reasoning", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "litellm", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.20-reasoning", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 2, "output": 6 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Reasoning" ], "families": [ "grok" ], "modes": [ "chat" ], "releaseDate": "2026-03-09", "lastUpdated": "2026-03-23", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-reasoning", "modelKey": "xai/grok-4.20-reasoning", "displayName": "Grok 4.20 Reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-03-23", "openWeights": false, "releaseDate": "2026-03-09" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai", "model": "vertex_ai/xai/grok-4.20-reasoning", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" } } ] }, { "id": "x-ai/grok-4.20-reasoning-beta", "provider": "x-ai", "model": "grok-4.20-reasoning-beta", "displayName": "Grok 4.20 Beta Reasoning", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xai/grok-4.20-reasoning-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 2000000, "outputTokens": 2000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.20-reasoning-beta", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.20 Beta Reasoning" ], "families": [ "grok" ], "releaseDate": "2026-03-11", "lastUpdated": "2026-03-13", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.20-reasoning-beta", "modelKey": "xai/grok-4.20-reasoning-beta", "displayName": "Grok 4.20 Beta Reasoning", "family": "grok", "metadata": { "lastUpdated": "2026-03-13", "openWeights": false, "releaseDate": "2026-03-11" } } ] }, { "id": "x-ai/grok-4.3", "provider": "x-ai", "model": "grok-4.3", "displayName": "Grok 4.3", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "aihubmix", "anyapi", "auriko", "fastrouter", "kilo", "merge-gateway", "nano-gpt", "openrouter", "orcarouter", "vercel", "xai", "zenmux" ], "aliases": [ "aihubmix/grok-4.3", "anyapi/xai/grok-4.3", "auriko/grok-4.3", "fastrouter/x-ai/grok-4.3", "kilo/x-ai/grok-4.3", "merge-gateway/xai/grok-4.3", "nano-gpt/x-ai/grok-4.3", "openrouter/x-ai/grok-4.3", "orcarouter/grok/grok-4.3", "vercel/xai/grok-4.3", "xai/grok-4.3", "zenmux/x-ai/grok-4.3" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "webSearch": true, "supports1MContext": true, "parallelFunctionCalling": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "aihubmix", "model": "grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "auriko", "model": "grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "fastrouter", "model": "x-ai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "kilo", "model": "x-ai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "xai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "nano-gpt", "model": "x-ai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "openrouter", "model": "x-ai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "orcarouter", "model": "grok/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "vercel", "model": "xai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } }, { "source": "models.dev", "provider": "xai", "model": "grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-4.3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1.25, "output": 2.5 }, "tiered": { "contextOver200K": { "input": 2.5, "output": 5, "cache_read": 0.4, "cache_write": 0 }, "tiers": [ { "input": 2.5, "output": 5, "cache_read": 0.4, "cache_write": 0, "tier": { "size": 200000 } } ] } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-4.3", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005 } }, { "source": "openrouter", "provider": "openrouter", "model": "x-ai/grok-4.3", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Grok 4.3", "xAI: Grok 4.3" ], "families": [ "grok" ], "modes": [ "chat" ], "releaseDate": "2026-05-01", "lastUpdated": "2026-05-01", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "grok-4.3", "modelKey": "grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "anyapi", "providerName": "AnyAPI", "providerApi": "https://api.anyapi.ai/v1", "providerDoc": "https://docs.anyapi.ai", "model": "xai/grok-4.3", "modelKey": "xai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "grok-4.3", "modelKey": "grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "x-ai/grok-4.3", "modelKey": "x-ai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "x-ai/grok-4.3", "modelKey": "x-ai/grok-4.3", "displayName": "xAI: Grok 4.3", "metadata": { "lastUpdated": "2026-05-01", "openWeights": false, "releaseDate": "2026-05-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "xai/grok-4.3", "modelKey": "xai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "x-ai/grok-4.3", "modelKey": "x-ai/grok-4.3", "displayName": "Grok 4.3", "metadata": { "lastUpdated": "2026-04-30", "openWeights": false, "releaseDate": "2026-04-30", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "x-ai/grok-4.3", "modelKey": "x-ai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "grok/grok-4.3", "modelKey": "grok/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-4.3", "modelKey": "xai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-30", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-4.3", "modelKey": "grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-4.3", "modelKey": "x-ai/grok-4.3", "displayName": "Grok 4.3", "family": "grok", "metadata": { "lastUpdated": "2026-04-17", "openWeights": false, "releaseDate": "2026-04-17", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.3", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "x-ai/grok-4.3", "displayName": "xAI: Grok 4.3", "metadata": { "canonicalSlug": "x-ai/grok-4.3-20260430", "createdAt": "2026-04-30T23:30:21.000Z", "links": { "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "high", "medium", "low", "none" ], "default_effort": "low" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Grok", "topProvider": { "context_length": 1000000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "x-ai/grok-4.3-latest", "provider": "x-ai", "model": "grok-4.3-latest", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-4.3-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "maxTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-4.3-latest", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 }, "extra": { "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-4.3-latest", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-beta", "provider": "x-ai", "model": "grok-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-beta", "mode": "chat" } ] }, { "id": "x-ai/grok-build-0-1", "provider": "x-ai", "model": "grok-build-0-1", "displayName": "Grok Build 0.1", "family": "grok-build", "sources": [ "models.dev" ], "providers": [ "llmgateway", "venice" ], "aliases": [ "llmgateway/grok-build-0-1", "venice/grok-build-0-1" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "grok-build-0-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 }, "tiered": { "contextOver200K": { "input": 2, "output": 4, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 4, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "venice", "model": "grok-build-0-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 }, "tiered": { "contextOver200K": { "input": 2, "output": 4, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 4, "cache_read": 0.4, "tier": { "size": 200000 } } ] } } ] }, "metadata": { "displayNames": [ "Grok Build 0.1" ], "families": [ "grok-build" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "grok-build-0-1", "modelKey": "grok-build-0-1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "venice", "providerName": "Venice AI", "providerDoc": "https://docs.venice.ai", "model": "grok-build-0-1", "modelKey": "grok-build-0-1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-06-11", "openWeights": false, "releaseDate": "2026-05-21" } } ] }, { "id": "x-ai/grok-build-0.1", "provider": "x-ai", "model": "grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "sources": [ "models.dev", "openrouter" ], "providers": [ "fastrouter", "kilo", "nano-gpt", "opencode", "openrouter", "vercel", "xai", "zenmux" ], "aliases": [ "fastrouter/x-ai/grok-build-0.1", "kilo/x-ai/grok-build-0.1", "nano-gpt/x-ai/grok-build-0.1", "opencode/grok-build-0.1", "openrouter/x-ai/grok-build-0.1", "vercel/xai/grok-build-0.1", "xai/grok-build-0.1", "zenmux/x-ai/grok-build-0.1" ], "mergedProviderModelRecords": 8, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fastrouter", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "kilo", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "opencode", "model": "grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "openrouter", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "vercel", "model": "xai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "models.dev", "provider": "xai", "model": "grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 }, "tiered": { "contextOver200K": { "input": 2, "output": 4, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 4, "cache_read": 0.4, "tier": { "size": 200000 } } ] } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 } }, { "source": "openrouter", "provider": "openrouter", "model": "x-ai/grok-build-0.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 2 }, "other": { "webSearch": 0.005 } } ] }, "metadata": { "displayNames": [ "Grok Build 0.1", "xAI: Grok Build 0.1" ], "families": [ "grok-build" ], "releaseDate": "2026-04-16", "lastUpdated": "2026-04-16", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "providerModelRecordCount": 8 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "x-ai/grok-build-0.1", "modelKey": "x-ai/grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "x-ai/grok-build-0.1", "modelKey": "x-ai/grok-build-0.1", "displayName": "xAI: Grok Build 0.1", "metadata": { "lastUpdated": "2026-05-27", "openWeights": false, "releaseDate": "2026-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "x-ai/grok-build-0.1", "modelKey": "x-ai/grok-build-0.1", "displayName": "Grok Build 0.1", "metadata": { "lastUpdated": "2026-05-20", "openWeights": false, "releaseDate": "2026-05-20", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "grok-build-0.1", "modelKey": "grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-05-20", "openWeights": false, "releaseDate": "2026-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "x-ai/grok-build-0.1", "modelKey": "x-ai/grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-build-0.1", "modelKey": "xai/grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-05-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-build-0.1", "modelKey": "grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-build-0.1", "modelKey": "x-ai/grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "metadata": { "lastUpdated": "2026-04-16", "openWeights": false, "releaseDate": "2026-04-16" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "x-ai/grok-build-0.1", "displayName": "xAI: Grok Build 0.1", "metadata": { "canonicalSlug": "x-ai/grok-build-0.1-20260520", "createdAt": "2026-05-20T17:28:43.000Z", "links": { "details": "/api/v1/models/x-ai/grok-build-0.1-20260520/endpoints" }, "reasoning": { "mandatory": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ], "tokenizer": "Grok", "topProvider": { "context_length": 256000, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "x-ai/grok-code", "provider": "x-ai", "model": "grok-code", "displayName": "Grok Code Fast 1", "family": "grok", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/grok-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "grok-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Grok Code Fast 1" ], "families": [ "grok" ], "statuses": [ "deprecated" ], "releaseDate": "2025-08-20", "lastUpdated": "2025-08-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "grok-code", "modelKey": "grok-code", "displayName": "Grok Code Fast 1", "family": "grok", "status": "deprecated", "metadata": { "lastUpdated": "2025-08-20", "openWeights": false, "releaseDate": "2025-08-20" } } ] }, { "id": "x-ai/grok-code-fast", "provider": "x-ai", "model": "grok-code-fast", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-code-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-code-fast", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-code-fast", "mode": "chat", "metadata": { "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-code-fast-1", "provider": "x-ai", "model": "grok-code-fast-1", "displayName": "Grok Code Fast 1", "family": "grok", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "abacus", "azure_ai", "frogbot", "helicone", "jiekou", "poe", "qiniu-ai", "xai", "zenmux" ], "aliases": [ "abacus/grok-code-fast-1", "azure_ai/grok-code-fast-1", "frogbot/grok-code-fast-1", "helicone/grok-code-fast-1", "jiekou/grok-code-fast-1", "poe/xai/grok-code-fast-1", "qiniu-ai/x-ai/grok-code-fast-1", "xai/grok-code-fast-1", "zenmux/x-ai/grok-code-fast-1" ], "mergedProviderModelRecords": 9, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "webSearch": true, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "abacus", "model": "grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "frogbot", "model": "grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "helicone", "model": "grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.19999999999999998, "output": 1.5 } }, { "source": "models.dev", "provider": "jiekou", "model": "grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.18, "output": 1.35 } }, { "source": "models.dev", "provider": "poe", "model": "xai/grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } }, { "source": "models.dev", "provider": "zenmux", "model": "x-ai/grok-code-fast-1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } }, { "source": "litellm", "provider": "azure_ai", "model": "azure_ai/grok-code-fast-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.5 } }, { "source": "litellm", "provider": "xai", "model": "xai/grok-code-fast-1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "Grok 4.1 Fast (Reasoning)", "Grok Code Fast 1", "grok-code-fast-1", "x-AI/Grok-Code-Fast 1", "xAI Grok Code Fast 1" ], "families": [ "grok" ], "modes": [ "chat" ], "knowledgeCutoff": "2023-10", "releaseDate": "2025-09-01", "lastUpdated": "2025-09-01", "deprecationDate": "2026-05-15", "providerModelRecordCount": 9 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "grok-code-fast-1", "modelKey": "grok-code-fast-1", "displayName": "Grok Code Fast 1", "family": "grok", "metadata": { "lastUpdated": "2025-09-01", "openWeights": false, "releaseDate": "2025-09-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "frogbot", "providerName": "FrogBot", "providerApi": "https://app.frogbot.ai/api/v1", "providerDoc": "https://docs.frogbot.ai", "model": "grok-code-fast-1", "modelKey": "grok-code-fast-1", "displayName": "Grok 4.1 Fast (Reasoning)", "family": "grok", "metadata": { "knowledgeCutoff": "2023-10", "lastUpdated": "2025-08-28", "openWeights": false, "releaseDate": "2025-08-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "grok-code-fast-1", "modelKey": "grok-code-fast-1", "displayName": "xAI Grok Code Fast 1", "family": "grok", "metadata": { "knowledgeCutoff": "2024-08", "lastUpdated": "2024-08-25", "openWeights": false, "releaseDate": "2024-08-25" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "grok-code-fast-1", "modelKey": "grok-code-fast-1", "displayName": "grok-code-fast-1", "family": "grok", "metadata": { "lastUpdated": "2026-01", "openWeights": false, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "xai/grok-code-fast-1", "modelKey": "xai/grok-code-fast-1", "displayName": "Grok Code Fast 1", "family": "grok", "metadata": { "lastUpdated": "2025-08-22", "openWeights": false, "releaseDate": "2025-08-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "x-ai/grok-code-fast-1", "modelKey": "x-ai/grok-code-fast-1", "displayName": "x-AI/Grok-Code-Fast 1", "metadata": { "lastUpdated": "2025-09-02", "openWeights": false, "releaseDate": "2025-09-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "x-ai/grok-code-fast-1", "modelKey": "x-ai/grok-code-fast-1", "displayName": "Grok Code Fast 1", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-08-26", "openWeights": false, "releaseDate": "2025-08-26" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "azure_ai", "model": "azure_ai/grok-code-fast-1", "mode": "chat", "metadata": { "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-code-fast-1", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-code-fast-1-0825", "provider": "x-ai", "model": "grok-code-fast-1-0825", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-code-fast-1-0825" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "maxTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-code-fast-1-0825", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.02, "input": 0.2, "output": 1.5 } } ] }, "metadata": { "modes": [ "chat" ], "deprecationDate": "2026-05-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-code-fast-1-0825", "mode": "chat", "metadata": { "deprecationDate": "2026-05-15", "source": "https://docs.x.ai/docs/models" } } ] }, { "id": "x-ai/grok-imagine-image", "provider": "x-ai", "model": "grok-imagine-image", "displayName": "Grok Imagine Image", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel", "xai" ], "aliases": [ "vercel/xai/grok-imagine-image", "xai/grok-imagine-image" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 8000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "pdf", "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Grok Imagine Image" ], "families": [ "grok" ], "releaseDate": "2026-01-28", "lastUpdated": "2026-02-19", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-imagine-image", "modelKey": "xai/grok-imagine-image", "displayName": "Grok Imagine Image", "family": "grok", "metadata": { "lastUpdated": "2026-02-19", "openWeights": false, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-imagine-image", "modelKey": "grok-imagine-image", "displayName": "Grok Imagine Image", "family": "grok", "metadata": { "lastUpdated": "2026-01-28", "openWeights": false, "releaseDate": "2026-01-28" } } ] }, { "id": "x-ai/grok-imagine-image-quality", "provider": "x-ai", "model": "grok-imagine-image-quality", "displayName": "Grok Imagine Image Quality", "family": "grok", "sources": [ "models.dev" ], "providers": [ "xai" ], "aliases": [ "xai/grok-imagine-image-quality" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "pdf" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": true, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Grok Imagine Image Quality" ], "families": [ "grok" ], "releaseDate": "2026-04-03", "lastUpdated": "2026-04-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-imagine-image-quality", "modelKey": "grok-imagine-image-quality", "displayName": "Grok Imagine Image Quality", "family": "grok", "metadata": { "lastUpdated": "2026-04-03", "openWeights": false, "releaseDate": "2026-04-03" } } ] }, { "id": "x-ai/grok-imagine-video", "provider": "x-ai", "model": "grok-imagine-video", "displayName": "Grok Imagine", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel", "xai" ], "aliases": [ "vercel/xai/grok-imagine-video", "xai/grok-imagine-video" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 1024, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "video" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "metadata": { "displayNames": [ "Grok Imagine", "Grok Imagine Video" ], "families": [ "grok" ], "releaseDate": "2026-01-28", "lastUpdated": "2026-01-28", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-imagine-video", "modelKey": "xai/grok-imagine-video", "displayName": "Grok Imagine", "family": "grok", "metadata": { "lastUpdated": "2026-01-28", "openWeights": false, "releaseDate": "2026-01-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xai", "providerName": "xAI", "providerDoc": "https://docs.x.ai/docs/models", "model": "grok-imagine-video", "modelKey": "grok-imagine-video", "displayName": "Grok Imagine Video", "family": "grok", "metadata": { "lastUpdated": "2026-01-28", "openWeights": false, "releaseDate": "2026-01-28" } } ] }, { "id": "x-ai/grok-imagine-video-1.5-preview", "provider": "x-ai", "model": "grok-imagine-video-1.5-preview", "displayName": "Grok Imagine Video 1.5 Preview", "family": "grok", "sources": [ "models.dev" ], "providers": [ "vercel" ], "aliases": [ "vercel/xai/grok-imagine-video-1.5-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 0, "outputTokens": 0, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Grok Imagine Video 1.5 Preview" ], "families": [ "grok" ], "releaseDate": "2026-05-30", "lastUpdated": "2026-05-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "xai/grok-imagine-video-1.5-preview", "modelKey": "xai/grok-imagine-video-1.5-preview", "displayName": "Grok Imagine Video 1.5 Preview", "family": "grok", "metadata": { "lastUpdated": "2026-05-30", "openWeights": false, "releaseDate": "2026-05-30" } } ] }, { "id": "x-ai/grok-latest", "provider": "x-ai", "model": "grok-latest", "displayName": "Grok Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/x-ai/grok-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 1000000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "x-ai/grok-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.25, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "Grok Latest" ], "releaseDate": "2026-05-03", "lastUpdated": "2026-05-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "x-ai/grok-latest", "modelKey": "x-ai/grok-latest", "displayName": "Grok Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "x-ai/grok-vision-beta", "provider": "x-ai", "model": "grok-vision-beta", "mode": "chat", "sources": [ "litellm" ], "providers": [ "xai" ], "aliases": [ "xai/grok-vision-beta" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "inputTokens": 8192, "maxTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": true, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "vision": true, "webSearch": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "xai", "model": "xai/grok-vision-beta", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 5, "output": 15 }, "perImage": { "input": 0.000005 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "xai", "model": "xai/grok-vision-beta", "mode": "chat" } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2-omni", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2-pro", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2-tts", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-tts", "modelKey": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2.5", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2.5-pro", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2.5-tts", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2.5-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts", "modelKey": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2.5-tts-voiceclone", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2.5-tts-voiceclone" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts-voiceclone", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceClone" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voiceclone", "modelKey": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-ams" ], "aliases": [ "xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-ams", "model": "mimo-v2.5-tts-voicedesign", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceDesign" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-ams", "providerName": "Xiaomi Token Plan (Europe)", "providerApi": "https://token-plan-ams.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voicedesign", "modelKey": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2-omni", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2-pro", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2-tts", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-tts", "modelKey": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2.5", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2.5-pro", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2.5-tts", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2.5-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts", "modelKey": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2.5-tts-voiceclone", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2.5-tts-voiceclone" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts-voiceclone", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceClone" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voiceclone", "modelKey": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-cn" ], "aliases": [ "xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-cn", "model": "mimo-v2.5-tts-voicedesign", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceDesign" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-cn", "providerName": "Xiaomi Token Plan (China)", "providerApi": "https://token-plan-cn.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voicedesign", "modelKey": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2-omni", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2-pro", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2-tts", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-tts", "modelKey": "mimo-v2-tts", "displayName": "MiMo-V2-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-03-18", "openWeights": true, "releaseDate": "2026-03-18" } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5-pro", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5-tts", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2.5-tts" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts", "modelKey": "mimo-v2.5-tts", "displayName": "MiMo-V2.5-TTS", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5-tts-voiceclone", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2.5-tts-voiceclone" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts-voiceclone", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceClone" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voiceclone", "modelKey": "mimo-v2.5-tts-voiceclone", "displayName": "MiMo-V2.5-TTS-VoiceClone", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi-token-plan-sgp" ], "aliases": [ "xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8192, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": true, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi-token-plan-sgp", "model": "mimo-v2.5-tts-voicedesign", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-TTS-VoiceDesign" ], "families": [ "mimo" ], "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi-token-plan-sgp", "providerName": "Xiaomi Token Plan (Singapore)", "providerApi": "https://token-plan-sgp.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-tts-voicedesign", "modelKey": "mimo-v2.5-tts-voicedesign", "displayName": "MiMo-V2.5-TTS-VoiceDesign", "family": "mimo", "metadata": { "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22" } } ] }, { "id": "xiaomi/mimo-v2-flash", "provider": "xiaomi", "model": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-flash", "modelKey": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi/mimo-v2-omni", "provider": "xiaomi", "model": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-omni", "modelKey": "mimo-v2-omni", "displayName": "MiMo-V2-Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi/mimo-v2-pro", "provider": "xiaomi", "model": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2-pro", "modelKey": "mimo-v2-pro", "displayName": "MiMo-V2-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi/mimo-v2.5", "provider": "xiaomi", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 }, "tiered": { "contextOver200K": { "input": 0.8, "output": 4, "cache_read": 0.16 }, "tiers": [ { "input": 0.8, "output": 4, "cache_read": 0.16, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5", "modelKey": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi/mimo-v2.5-pro", "provider": "xiaomi", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-pro", "modelKey": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xiaomi/mimo-v2.5-pro-ultraspeed", "provider": "xiaomi", "model": "mimo-v2.5-pro-ultraspeed", "displayName": "MiMo-V2.5-Pro-UltraSpeed", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "xiaomi" ], "aliases": [ "xiaomi/mimo-v2.5-pro-ultraspeed" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xiaomi", "model": "mimo-v2.5-pro-ultraspeed", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0108, "input": 1.305, "output": 2.61 } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro-UltraSpeed" ], "families": [ "mimo" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-06-08", "lastUpdated": "2026-06-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xiaomi", "providerName": "Xiaomi", "providerApi": "https://api.xiaomimimo.com/v1", "providerDoc": "https://platform.xiaomimimo.com/#/docs", "model": "mimo-v2.5-pro-ultraspeed", "modelKey": "mimo-v2.5-pro-ultraspeed", "displayName": "MiMo-V2.5-Pro-UltraSpeed", "family": "mimo", "status": "beta", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-06-09", "openWeights": true, "releaseDate": "2026-06-08", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "xpersona/xpersona-frieren-coder", "provider": "xpersona", "model": "xpersona-frieren-coder", "displayName": "Xpersona Frieren 1", "sources": [ "models.dev" ], "providers": [ "xpersona" ], "aliases": [ "xpersona/xpersona-frieren-coder" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 384000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xpersona", "model": "xpersona-frieren-coder", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 1.5, "output": 6, "reasoningOutput": 6 } } ] }, "metadata": { "displayNames": [ "Xpersona Frieren 1" ], "knowledgeCutoff": "2025-12-30", "releaseDate": "2026-05-01", "lastUpdated": "2026-05-25", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xpersona", "providerName": "Xpersona", "providerApi": "https://www.xpersona.co/v1", "providerDoc": "https://www.xpersona.co/docs", "model": "xpersona-frieren-coder", "modelKey": "xpersona-frieren-coder", "displayName": "Xpersona Frieren 1", "metadata": { "knowledgeCutoff": "2025-12-30", "lastUpdated": "2026-05-25", "openWeights": false, "releaseDate": "2026-05-01" } } ] }, { "id": "xpersona/xpersona-gpt-5.5", "provider": "xpersona", "model": "xpersona-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "sources": [ "models.dev" ], "providers": [ "xpersona" ], "aliases": [ "xpersona/xpersona-gpt-5.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 128000, "supports1MContext": true }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "xpersona", "model": "xpersona-gpt-5.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 3, "output": 18, "reasoningOutput": 18 } } ] }, "metadata": { "displayNames": [ "GPT-5.5" ], "families": [ "gpt" ], "knowledgeCutoff": "2025-12-30", "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "xpersona", "providerName": "Xpersona", "providerApi": "https://www.xpersona.co/v1", "providerDoc": "https://www.xpersona.co/docs", "model": "xpersona-gpt-5.5", "modelKey": "xpersona-gpt-5.5", "displayName": "GPT-5.5", "family": "gpt", "metadata": { "knowledgeCutoff": "2025-12-30", "lastUpdated": "2026-05-29", "openWeights": false, "releaseDate": "2026-05-29" } } ] }, { "id": "you-com/search", "provider": "you-com", "model": "search", "mode": "search", "sources": [ "litellm" ], "providers": [ "you_com" ], "aliases": [ "you_com/search" ], "mergedProviderModelRecords": 1, "limits": { "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "you_com", "model": "you_com/search", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "perQuery": { "input": 0 } } ] }, "metadata": { "modes": [ "search" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "you_com", "model": "you_com/search", "mode": "search" } ] }, { "id": "z-ai/autoglm-phone-9b", "provider": "z-ai", "model": "autoglm-phone-9b", "displayName": "Z-Ai/Autoglm Phone 9b", "sources": [ "models.dev" ], "providers": [ "qiniu-ai" ], "aliases": [ "qiniu-ai/z-ai/autoglm-phone-9b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 12800, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "Z-Ai/Autoglm Phone 9b" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "z-ai/autoglm-phone-9b", "modelKey": "z-ai/autoglm-phone-9b", "displayName": "Z-Ai/Autoglm Phone 9b", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } } ] }, { "id": "z-ai/autoglm-phone-9b-multilingual", "provider": "z-ai", "model": "autoglm-phone-9b-multilingual", "displayName": "AutoGLM-Phone-9B-Multilingual", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "novita", "novita-ai" ], "aliases": [ "novita-ai/zai-org/autoglm-phone-9b-multilingual", "novita/zai-org/autoglm-phone-9b-multilingual" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 65536, "inputTokens": 65536, "maxTokens": 65536, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": false, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/autoglm-phone-9b-multilingual", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.035, "output": 0.138 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/autoglm-phone-9b-multilingual", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.035, "output": 0.138 } } ] }, "metadata": { "displayNames": [ "AutoGLM-Phone-9B-Multilingual" ], "modes": [ "chat" ], "releaseDate": "2025-12-10", "lastUpdated": "2025-12-10", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/autoglm-phone-9b-multilingual", "modelKey": "zai-org/autoglm-phone-9b-multilingual", "displayName": "AutoGLM-Phone-9B-Multilingual", "metadata": { "lastUpdated": "2025-12-10", "openWeights": true, "releaseDate": "2025-12-10" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/autoglm-phone-9b-multilingual", "mode": "chat" } ] }, { "id": "z-ai/glm-4", "provider": "z-ai", "model": "glm-4", "displayName": "GLM-4", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 14.994, "output": 14.994 } } ] }, "metadata": { "displayNames": [ "GLM-4" ], "releaseDate": "2024-01-16", "lastUpdated": "2024-01-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4", "modelKey": "glm-4", "displayName": "GLM-4", "metadata": { "lastUpdated": "2024-01-16", "openWeights": false, "releaseDate": "2024-01-16" } } ] }, { "id": "z-ai/glm-4-32b", "provider": "z-ai", "model": "glm-4-32b", "displayName": "Z.ai: GLM 4 32B", "sources": [ "models.dev" ], "providers": [ "kilo" ], "aliases": [ "kilo/z-ai/glm-4-32b" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 32768, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4-32b", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "Z.ai: GLM 4 32B" ], "releaseDate": "2025-07-25", "lastUpdated": "2026-03-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4-32b", "modelKey": "z-ai/glm-4-32b", "displayName": "Z.ai: GLM 4 32B", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-25" } } ] }, { "id": "z-ai/glm-4-32b-0414", "provider": "z-ai", "model": "glm-4-32b-0414", "displayName": "GLM 4 32B 0414", "family": "glm", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/THUDM/GLM-4-32B-0414" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "THUDM/GLM-4-32B-0414", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "GLM 4 32B 0414" ], "families": [ "glm" ], "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "THUDM/GLM-4-32B-0414", "modelKey": "THUDM/GLM-4-32B-0414", "displayName": "GLM 4 32B 0414", "family": "glm", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } } ] }, { "id": "z-ai/glm-4-32b-0414-128k", "provider": "z-ai", "model": "glm-4-32b-0414-128k", "displayName": "GLM-4 32B (0414-128k)", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "zai" ], "aliases": [ "llmgateway/glm-4-32b-0414-128k", "zai/glm-4-32b-0414-128k" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "glm-4-32b-0414-128k", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.1 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4-32b-0414-128k", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.1, "output": 0.1 } } ] }, "metadata": { "displayNames": [ "GLM-4 32B (0414-128k)" ], "families": [ "glm" ], "modes": [ "chat" ], "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4-32b-0414-128k", "modelKey": "glm-4-32b-0414-128k", "displayName": "GLM-4 32B (0414-128k)", "family": "glm", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4-32b-0414-128k", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } } ] }, { "id": "z-ai/glm-4-7-251222", "provider": "z-ai", "model": "glm-4-7-251222", "mode": "chat", "sources": [ "litellm" ], "providers": [ "volcengine" ], "aliases": [ "volcengine/glm-4-7-251222" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "inputTokens": 204800, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "assistantPrefill": true, "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "volcengine", "model": "glm-4-7-251222", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "volcengine", "model": "glm-4-7-251222", "mode": "chat" } ] }, { "id": "z-ai/glm-4-9b-0414", "provider": "z-ai", "model": "glm-4-9b-0414", "displayName": "GLM 4 9B 0414", "family": "glm", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/THUDM/GLM-4-9B-0414" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "THUDM/GLM-4-9B-0414", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "GLM 4 9B 0414" ], "families": [ "glm" ], "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "THUDM/GLM-4-9B-0414", "modelKey": "THUDM/GLM-4-9B-0414", "displayName": "GLM 4 9B 0414", "family": "glm", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } } ] }, { "id": "z-ai/glm-4-air", "provider": "z-ai", "model": "glm-4-air", "displayName": "GLM-4 Air", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-air" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "GLM-4 Air" ], "releaseDate": "2024-06-05", "lastUpdated": "2024-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-air", "modelKey": "glm-4-air", "displayName": "GLM-4 Air", "metadata": { "lastUpdated": "2024-06-05", "openWeights": false, "releaseDate": "2024-06-05" } } ] }, { "id": "z-ai/glm-4-air-0111", "provider": "z-ai", "model": "glm-4-air-0111", "displayName": "GLM 4 Air 0111", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-air-0111" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-air-0111", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1394, "output": 0.1394 } } ] }, "metadata": { "displayNames": [ "GLM 4 Air 0111" ], "releaseDate": "2025-01-11", "lastUpdated": "2025-01-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-air-0111", "modelKey": "glm-4-air-0111", "displayName": "GLM 4 Air 0111", "metadata": { "lastUpdated": "2025-01-11", "openWeights": false, "releaseDate": "2025-01-11" } } ] }, { "id": "z-ai/glm-4-airx", "provider": "z-ai", "model": "glm-4-airx", "displayName": "GLM-4 AirX", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-airx" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-airx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 2.006, "output": 2.006 } } ] }, "metadata": { "displayNames": [ "GLM-4 AirX" ], "releaseDate": "2024-06-05", "lastUpdated": "2024-06-05", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-airx", "modelKey": "glm-4-airx", "displayName": "GLM-4 AirX", "metadata": { "lastUpdated": "2024-06-05", "openWeights": false, "releaseDate": "2024-06-05" } } ] }, { "id": "z-ai/glm-4-flash", "provider": "z-ai", "model": "glm-4-flash", "displayName": "GLM-4 Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1003, "output": 0.1003 } } ] }, "metadata": { "displayNames": [ "GLM-4 Flash" ], "releaseDate": "2024-08-01", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-flash", "modelKey": "glm-4-flash", "displayName": "GLM-4 Flash", "metadata": { "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "z-ai/glm-4-long", "provider": "z-ai", "model": "glm-4-long", "displayName": "GLM-4 Long", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-long" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "inputTokens": 1000000, "outputTokens": 4096, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-long", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2006, "output": 0.2006 } } ] }, "metadata": { "displayNames": [ "GLM-4 Long" ], "releaseDate": "2024-08-01", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-long", "modelKey": "glm-4-long", "displayName": "GLM-4 Long", "metadata": { "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "z-ai/glm-4-plus", "provider": "z-ai", "model": "glm-4-plus", "displayName": "GLM-4 Plus", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-plus" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-plus", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 7.497, "output": 7.497 } } ] }, "metadata": { "displayNames": [ "GLM-4 Plus" ], "releaseDate": "2024-08-01", "lastUpdated": "2024-08-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-plus", "modelKey": "glm-4-plus", "displayName": "GLM-4 Plus", "metadata": { "lastUpdated": "2024-08-01", "openWeights": false, "releaseDate": "2024-08-01" } } ] }, { "id": "z-ai/glm-4-plus-0111", "provider": "z-ai", "model": "glm-4-plus-0111", "displayName": "GLM 4 Plus 0111", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4-plus-0111" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4-plus-0111", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 9.996, "output": 9.996 } } ] }, "metadata": { "displayNames": [ "GLM 4 Plus 0111" ], "releaseDate": "2025-02-19", "lastUpdated": "2025-02-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4-plus-0111", "modelKey": "glm-4-plus-0111", "displayName": "GLM 4 Plus 0111", "metadata": { "lastUpdated": "2025-02-19", "openWeights": false, "releaseDate": "2025-02-19" } } ] }, { "id": "z-ai/glm-4.1v-thinking-flash", "provider": "z-ai", "model": "glm-4.1v-thinking-flash", "displayName": "GLM 4.1V Thinking Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4.1v-thinking-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4.1v-thinking-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "GLM 4.1V Thinking Flash" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4.1v-thinking-flash", "modelKey": "glm-4.1v-thinking-flash", "displayName": "GLM 4.1V Thinking Flash", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "z-ai/glm-4.1v-thinking-flashx", "provider": "z-ai", "model": "glm-4.1v-thinking-flashx", "displayName": "GLM 4.1V Thinking FlashX", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-4.1v-thinking-flashx" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-4.1v-thinking-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "GLM 4.1V Thinking FlashX" ], "releaseDate": "2025-07-09", "lastUpdated": "2025-07-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-4.1v-thinking-flashx", "modelKey": "glm-4.1v-thinking-flashx", "displayName": "GLM 4.1V Thinking FlashX", "metadata": { "lastUpdated": "2025-07-09", "openWeights": false, "releaseDate": "2025-07-09" } } ] }, { "id": "z-ai/glm-4.5", "provider": "z-ai", "model": "glm-4.5", "displayName": "GLM-4.5", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "cortecs", "deepinfra", "jiekou", "kilo", "llmgateway", "merge-gateway", "modelscope", "nano-gpt", "novita", "novita-ai", "openrouter", "orcarouter", "qiniu-ai", "siliconflow", "vercel", "vercel_ai_gateway", "wandb", "zai", "zenmux", "zhipuai" ], "aliases": [ "302ai/glm-4.5", "abacus/zai-org/glm-4.5", "cortecs/glm-4.5", "deepinfra/zai-org/GLM-4.5", "jiekou/zai-org/glm-4.5", "kilo/z-ai/glm-4.5", "llmgateway/glm-4.5", "merge-gateway/zai/glm-4.5", "modelscope/ZhipuAI/GLM-4.5", "nano-gpt/zai-org/glm-4.5", "novita-ai/zai-org/glm-4.5", "novita/zai-org/glm-4.5", "openrouter/z-ai/glm-4.5", "orcarouter/z-ai/glm-4.5", "qiniu-ai/glm-4.5", "siliconflow/zai-org/GLM-4.5", "vercel/zai/glm-4.5", "vercel_ai_gateway/zai/glm-4.5", "wandb/zai-org/GLM-4.5", "zai/glm-4.5", "zenmux/z-ai/glm-4.5", "zhipuai/glm-4.5" ], "mergedProviderModelRecords": 22, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "interleaved": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.286, "output": 1.142 } }, { "source": "models.dev", "provider": "abacus", "model": "zai-org/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.67, "output": 2.46 } }, { "source": "models.dev", "provider": "jiekou", "model": "zai-org/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "modelscope", "model": "ZhipuAI/GLM-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.3 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 2 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.35, "output": 1.54 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "deepinfra", "model": "deepinfra/zai-org/GLM-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.6 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 }, "extra": { "input_cost_per_token_cache_hit": 1.1e-7 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "wandb", "model": "wandb/zai-org/GLM-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 55000, "output": 200000 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "GLM 4.5", "GLM-4.5", "Z.ai: GLM 4.5", "zai-org/GLM-4.5" ], "families": [ "glm" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-29", "lastUpdated": "2025-07-29", "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 22 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "zai-org/glm-4.5", "modelKey": "zai-org/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM 4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "zai-org/glm-4.5", "modelKey": "zai-org/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.5", "modelKey": "z-ai/glm-4.5", "displayName": "Z.ai: GLM 4.5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-4.5", "modelKey": "zai/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "ZhipuAI/GLM-4.5", "modelKey": "ZhipuAI/GLM-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.5", "modelKey": "zai-org/glm-4.5", "displayName": "GLM 4.5", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.5", "modelKey": "zai-org/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.5", "modelKey": "z-ai/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-4.5", "modelKey": "z-ai/glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM 4.5", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.5", "modelKey": "zai-org/GLM-4.5", "displayName": "zai-org/GLM-4.5", "family": "glm", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.5", "modelKey": "zai/glm-4.5", "displayName": "GLM 4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.5", "modelKey": "z-ai/glm-4.5", "displayName": "GLM 4.5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-25", "openWeights": false, "releaseDate": "2025-07-25", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5", "modelKey": "glm-4.5", "displayName": "GLM-4.5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "deepinfra", "model": "deepinfra/zai-org/GLM-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "wandb", "model": "wandb/zai-org/GLM-4.5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.5", "displayName": "Z.ai: GLM 4.5", "metadata": { "canonicalSlug": "z-ai/glm-4.5", "createdAt": "2025-07-25T19:22:27.000Z", "expirationDate": "2026-12-31", "huggingFaceId": "zai-org/GLM-4.5", "knowledgeCutoff": "2024-12-31", "links": { "details": "/api/v1/models/z-ai/glm-4.5/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 98304, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.5-air", "provider": "z-ai", "model": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "cortecs", "kilo", "llmgateway", "merge-gateway", "nano-gpt", "novita", "novita-ai", "openrouter", "orcarouter", "qiniu-ai", "siliconflow", "siliconflow-cn", "submodel", "vercel", "vercel_ai_gateway", "zai", "zai-coding-plan", "zenmux", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-4.5-air", "cortecs/glm-4.5-air", "kilo/z-ai/glm-4.5-air", "llmgateway/glm-4.5-air", "merge-gateway/zai/glm-4.5-air", "nano-gpt/zai-org/GLM-4.5-Air", "novita-ai/zai-org/glm-4.5-air", "novita/zai-org/glm-4.5-air", "openrouter/z-ai/glm-4.5-air", "orcarouter/z-ai/glm-4.5-air", "qiniu-ai/glm-4.5-air", "siliconflow-cn/zai-org/GLM-4.5-Air", "siliconflow/zai-org/GLM-4.5-Air", "submodel/zai-org/GLM-4.5-Air", "vercel/zai/glm-4.5-air", "vercel_ai_gateway/zai/glm-4.5-air", "zai-coding-plan/glm-4.5-air", "zai/glm-4.5-air", "zenmux/z-ai/glm-4.5-air", "zhipuai-coding-plan/glm-4.5-air", "zhipuai/glm-4.5-air" ], "mergedProviderModelRecords": 21, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 98304, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": false, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1143, "output": 0.286 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.22, "output": 1.34 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.13, "output": 0.85 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/GLM-4.5-Air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.8 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.13, "output": 0.85 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.025, "input": 0.13, "output": 0.85 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "zai-org/GLM-4.5-Air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.86 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.5-Air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.86 } }, { "source": "models.dev", "provider": "submodel", "model": "zai-org/GLM-4.5-Air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.5 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.2, "output": 1.1 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "input": 0.11, "output": 0.56 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.5-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "cacheWrite": 0, "input": 0.2, "output": 1.1 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.5-air", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.13, "output": 0.85 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.5-air", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.1 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5-air", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.1 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.5-air", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.025, "input": 0.13, "output": 0.85 } } ] }, "metadata": { "displayNames": [ "GLM 4.5 Air", "GLM-4.5-Air", "Z.ai: GLM 4.5 Air", "glm-4.5-air", "zai-org/GLM-4.5-Air" ], "families": [ "glm-air" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-29", "lastUpdated": "2025-07-29", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 21 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "glm-4.5-air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-29", "openWeights": true, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM 4.5 Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-01", "openWeights": true, "releaseDate": "2025-08-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.5-air", "modelKey": "z-ai/glm-4.5-air", "displayName": "Z.ai: GLM 4.5 Air", "metadata": { "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-4.5-air", "modelKey": "zai/glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/GLM-4.5-Air", "modelKey": "zai-org/GLM-4.5-Air", "displayName": "GLM 4.5 Air", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.5-air", "modelKey": "zai-org/glm-4.5-air", "displayName": "GLM 4.5 Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-10-13", "openWeights": true, "releaseDate": "2025-10-13", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.5-air", "modelKey": "z-ai/glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-4.5-air", "modelKey": "z-ai/glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM 4.5 Air", "metadata": { "lastUpdated": "2025-08-05", "openWeights": false, "releaseDate": "2025-08-05" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.5-Air", "modelKey": "zai-org/GLM-4.5-Air", "displayName": "zai-org/GLM-4.5-Air", "family": "glm-air", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.5-Air", "modelKey": "zai-org/GLM-4.5-Air", "displayName": "zai-org/GLM-4.5-Air", "family": "glm-air", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "zai-org/GLM-4.5-Air", "modelKey": "zai-org/GLM-4.5-Air", "displayName": "GLM 4.5 Air", "family": "glm-air", "metadata": { "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.5-air", "modelKey": "zai/glm-4.5-air", "displayName": "GLM 4.5 Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.5-air", "modelKey": "z-ai/glm-4.5-air", "displayName": "GLM 4.5 Air", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-25", "openWeights": false, "releaseDate": "2025-07-25", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5-air", "modelKey": "glm-4.5-air", "displayName": "GLM-4.5-Air", "family": "glm-air", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.5-air", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.5-air", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5-air", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.5-air", "displayName": "Z.ai: GLM 4.5 Air", "metadata": { "canonicalSlug": "z-ai/glm-4.5-air", "createdAt": "2025-07-25T19:20:58.000Z", "huggingFaceId": "zai-org/GLM-4.5-Air", "knowledgeCutoff": "2024-12-31", "links": { "details": "/api/v1/models/z-ai/glm-4.5-air/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 98304, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.5-air-fp8", "provider": "z-ai", "model": "glm-4.5-air-fp8", "mode": "chat", "sources": [ "litellm" ], "providers": [ "together_ai" ], "aliases": [ "together_ai/zai-org/GLM-4.5-Air-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "parallelFunctionCalling": true, "pdfInput": false, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.5-Air-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.2, "output": 1.1 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.5-Air-FP8", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/glm-4-5-air" } } ] }, { "id": "z-ai/glm-4.5-air:thinking", "provider": "z-ai", "model": "glm-4.5-air:thinking", "displayName": "GLM 4.5 Air (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/GLM-4.5-Air:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 98304, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/GLM-4.5-Air:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "GLM 4.5 Air (Thinking)" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/GLM-4.5-Air:thinking", "modelKey": "zai-org/GLM-4.5-Air:thinking", "displayName": "GLM 4.5 Air (Thinking)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "z-ai/glm-4.5-airx", "provider": "z-ai", "model": "glm-4.5-airx", "displayName": "glm-4.5-airx", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "llmgateway", "zai" ], "aliases": [ "302ai/glm-4.5-airx", "llmgateway/glm-4.5-airx", "zai/glm-4.5-airx" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.5-airx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.572, "output": 1.714 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5-airx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.22, "input": 1.1, "output": 4.5 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5-airx", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.1, "output": 4.5 } } ] }, "metadata": { "displayNames": [ "GLM-4.5 AirX", "glm-4.5-airx" ], "families": [ "glm" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-29", "lastUpdated": "2025-07-29", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.5-airx", "modelKey": "glm-4.5-airx", "displayName": "glm-4.5-airx", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-29", "openWeights": false, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5-airx", "modelKey": "glm-4.5-airx", "displayName": "GLM-4.5 AirX", "family": "glm", "metadata": { "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5-airx", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } } ] }, { "id": "z-ai/glm-4.5-flash", "provider": "z-ai", "model": "glm-4.5-flash", "displayName": "GLM-4.5-Flash", "family": "glm-flash", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "llmgateway", "zai", "zhipuai" ], "aliases": [ "llmgateway/glm-4.5-flash", "zai/glm-4.5-flash", "zhipuai/glm-4.5-flash" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 131072, "inputTokens": 128000, "outputTokens": 98304, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM-4.5-Flash" ], "families": [ "glm-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-28", "lastUpdated": "2025-07-28", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5-flash", "modelKey": "glm-4.5-flash", "displayName": "GLM-4.5-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5-flash", "modelKey": "glm-4.5-flash", "displayName": "GLM-4.5-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5-flash", "modelKey": "glm-4.5-flash", "displayName": "GLM-4.5-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5-flash", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } } ] }, { "id": "z-ai/glm-4.5-fp8", "provider": "z-ai", "model": "glm-4.5-fp8", "displayName": "GLM 4.5 FP8", "family": "glm", "sources": [ "models.dev" ], "providers": [ "submodel" ], "aliases": [ "submodel/zai-org/GLM-4.5-FP8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "submodel", "model": "zai-org/GLM-4.5-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "GLM 4.5 FP8" ], "families": [ "glm" ], "releaseDate": "2025-07-28", "lastUpdated": "2025-07-28", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "submodel", "providerName": "submodel", "providerApi": "https://llm.submodel.ai/v1", "providerDoc": "https://submodel.gitbook.io", "model": "zai-org/GLM-4.5-FP8", "modelKey": "zai-org/GLM-4.5-FP8", "displayName": "GLM 4.5 FP8", "family": "glm", "metadata": { "lastUpdated": "2025-07-28", "openWeights": true, "releaseDate": "2025-07-28" } } ] }, { "id": "z-ai/glm-4.5-x", "provider": "z-ai", "model": "glm-4.5-x", "displayName": "glm-4.5-x", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "302ai", "llmgateway", "zai" ], "aliases": [ "302ai/glm-4.5-x", "llmgateway/glm-4.5-x", "zai/glm-4.5-x" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.5-x", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.143, "output": 2.29 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5-x", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.45, "input": 2.2, "output": 8.9 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5-x", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 2.2, "output": 8.9 } } ] }, "metadata": { "displayNames": [ "GLM-4.5 X", "glm-4.5-x" ], "families": [ "glm" ], "modes": [ "chat" ], "statuses": [ "beta" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-07-29", "lastUpdated": "2025-07-29", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.5-x", "modelKey": "glm-4.5-x", "displayName": "glm-4.5-x", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-29", "openWeights": false, "releaseDate": "2025-07-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5-x", "modelKey": "glm-4.5-x", "displayName": "GLM-4.5 X", "family": "glm", "status": "beta", "metadata": { "lastUpdated": "2025-07-28", "openWeights": false, "releaseDate": "2025-07-28" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5-x", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } } ] }, { "id": "z-ai/glm-4.5:thinking", "provider": "z-ai", "model": "glm-4.5:thinking", "displayName": "GLM 4.5 (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/GLM-4.5:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/GLM-4.5:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 1.3 } } ] }, "metadata": { "displayNames": [ "GLM 4.5 (Thinking)" ], "releaseDate": "2024-01-01", "lastUpdated": "2024-01-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/GLM-4.5:thinking", "modelKey": "zai-org/GLM-4.5:thinking", "displayName": "GLM 4.5 (Thinking)", "metadata": { "lastUpdated": "2024-01-01", "openWeights": false, "releaseDate": "2024-01-01" } } ] }, { "id": "z-ai/glm-4.5v", "provider": "z-ai", "model": "glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "jiekou", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "openrouter", "siliconflow", "siliconflow-cn", "vercel", "zai", "zhipuai" ], "aliases": [ "302ai/glm-4.5v", "jiekou/zai-org/glm-4.5v", "kilo/z-ai/glm-4.5v", "llmgateway/glm-4.5v", "nano-gpt/z-ai/glm-4.5v", "novita-ai/zai-org/glm-4.5v", "novita/zai-org/glm-4.5v", "openrouter/z-ai/glm-4.5v", "siliconflow-cn/zai-org/GLM-4.5V", "siliconflow/zai-org/GLM-4.5V", "vercel/zai/glm-4.5v", "zai/glm-4.5v", "zhipuai/glm-4.5v" ], "mergedProviderModelRecords": 13, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 16384, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.29, "output": 0.86 } }, { "source": "models.dev", "provider": "jiekou", "model": "zai-org/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.7999999999999998 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "zai-org/GLM-4.5V", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.86 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.5V", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.14, "output": 0.86 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.8 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.5v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.8 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.5v", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 }, "extra": { "input_cost_per_token_cache_hit": 1.1e-7 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.5v", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 1.8 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.5v", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 1.8 } } ] }, "metadata": { "displayNames": [ "GLM 4.5V", "GLM-4.5V", "Z.ai: GLM 4.5V", "zai-org/GLM-4.5V" ], "families": [ "glm", "glmv" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-08-12", "lastUpdated": "2025-08-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 13 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.5v", "modelKey": "glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-12", "openWeights": true, "releaseDate": "2025-08-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "zai-org/glm-4.5v", "modelKey": "zai-org/glm-4.5v", "displayName": "GLM 4.5V", "family": "glmv", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.5v", "modelKey": "z-ai/glm-4.5v", "displayName": "Z.ai: GLM 4.5V", "metadata": { "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.5v", "modelKey": "glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-4.5v", "modelKey": "z-ai/glm-4.5v", "displayName": "GLM 4.5V", "family": "glmv", "metadata": { "lastUpdated": "2025-11-22", "openWeights": false, "releaseDate": "2025-11-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.5v", "modelKey": "zai-org/glm-4.5v", "displayName": "GLM 4.5V", "family": "glmv", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.5v", "modelKey": "z-ai/glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.5V", "modelKey": "zai-org/GLM-4.5V", "displayName": "zai-org/GLM-4.5V", "family": "glm", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.5V", "modelKey": "zai-org/GLM-4.5V", "displayName": "zai-org/GLM-4.5V", "family": "glm", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-08-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.5v", "modelKey": "zai/glm-4.5v", "displayName": "GLM 4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5v", "modelKey": "glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.5v", "modelKey": "glm-4.5v", "displayName": "GLM-4.5V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "openWeights": true, "releaseDate": "2025-08-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.5v", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.5v", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.5v", "displayName": "Z.ai: GLM 4.5V", "metadata": { "canonicalSlug": "z-ai/glm-4.5v", "createdAt": "2025-08-11T14:24:48.000Z", "huggingFaceId": "zai-org/GLM-4.5V", "knowledgeCutoff": "2024-12-31", "links": { "details": "/api/v1/models/z-ai/glm-4.5v/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 65536, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.5v:thinking", "provider": "z-ai", "model": "glm-4.5v:thinking", "displayName": "GLM 4.5V Thinking", "family": "glmv", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/z-ai/glm-4.5v:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 64000, "inputTokens": 64000, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-4.5v:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 1.7999999999999998 } } ] }, "metadata": { "displayNames": [ "GLM 4.5V Thinking" ], "families": [ "glmv" ], "releaseDate": "2025-11-22", "lastUpdated": "2025-11-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-4.5v:thinking", "modelKey": "z-ai/glm-4.5v:thinking", "displayName": "GLM 4.5V Thinking", "family": "glmv", "metadata": { "lastUpdated": "2025-11-22", "openWeights": false, "releaseDate": "2025-11-22" } } ] }, { "id": "z-ai/glm-4.6", "provider": "z-ai", "model": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "baseten", "deepinfra", "helicone", "iflowcn", "io-net", "kilo", "llmgateway", "meganova", "merge-gateway", "modelscope", "nano-gpt", "novita", "novita-ai", "ollama-cloud", "opencode", "openrouter", "orcarouter", "poe", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "together_ai", "vercel", "vercel_ai_gateway", "zai", "zenmux", "zhipuai" ], "aliases": [ "302ai/glm-4.6", "abacus/zai-org/glm-4.6", "baseten/zai-org/GLM-4.6", "deepinfra/zai-org/GLM-4.6", "helicone/glm-4.6", "iflowcn/glm-4.6", "io-net/zai-org/GLM-4.6", "kilo/z-ai/glm-4.6", "llmgateway/glm-4.6", "meganova/zai-org/GLM-4.6", "merge-gateway/zai/glm-4.6", "modelscope/ZhipuAI/GLM-4.6", "nano-gpt/z-ai/glm-4.6", "novita-ai/zai-org/glm-4.6", "novita/zai-org/glm-4.6", "ollama-cloud/glm-4.6", "opencode/glm-4.6", "openrouter/z-ai/glm-4.6", "orcarouter/z-ai/glm-4.6", "poe/novita/glm-4.6", "qiniu-ai/z-ai/glm-4.6", "siliconflow-cn/zai-org/GLM-4.6", "siliconflow/zai-org/GLM-4.6", "synthetic/hf:zai-org/GLM-4.6", "together_ai/zai-org/GLM-4.6", "vercel/zai/glm-4.6", "vercel_ai_gateway/zai/glm-4.6", "zai/glm-4.6", "zenmux/z-ai/glm-4.6", "zhipuai/glm-4.6" ], "mergedProviderModelRecords": 30, "limits": { "contextTokens": 205000, "inputTokens": 204800, "maxTokens": 200000, "outputTokens": 205000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "supports1MContext": false, "interleaved": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.286, "output": 1.142 } }, { "source": "models.dev", "provider": "abacus", "model": "zai-org/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "deepinfra", "model": "zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.43, "output": 1.74 } }, { "source": "models.dev", "provider": "helicone", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.44999999999999996, "output": 1.5 } }, { "source": "models.dev", "provider": "iflowcn", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "io-net", "model": "zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0.8, "input": 0.4, "output": 1.75 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.175, "input": 0.39, "output": 1.9 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "meganova", "model": "zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.9 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "modelscope", "model": "ZhipuAI/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.5 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.55, "output": 2.2 } }, { "source": "models.dev", "provider": "opencode", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.43, "output": 1.74 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.9 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.5, "output": 1.9 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:zai-org/GLM-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.07, "input": 0.35, "output": 1.54 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.6", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/zai-org/GLM-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.55, "output": 2.2 }, "extra": { "input_cost_per_token_cache_hit": 1.1e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 1.75 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.45, "output": 1.8 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.6", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "input": 0.43, "output": 1.74 } } ] }, "metadata": { "displayNames": [ "GLM 4.6", "GLM-4.6", "Z-AI/GLM 4.6", "Z.ai: GLM 4.6", "Zai GLM-4.6", "glm-4.6", "zai-org/GLM-4.6" ], "families": [ "glm" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 30 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "glm-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "zai-org/glm-4.6", "modelKey": "zai-org/glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "lastUpdated": "2025-03-01", "openWeights": true, "releaseDate": "2025-03-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "zai-org/GLM-4.6", "modelKey": "zai-org/GLM-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "helicone", "providerName": "Helicone", "providerApi": "https://ai-gateway.helicone.ai/v1", "providerDoc": "https://helicone.ai/models", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "Zai GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2024-07", "lastUpdated": "2024-07-18", "openWeights": false, "releaseDate": "2024-07-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "iflowcn", "providerName": "iFlow", "providerApi": "https://apis.iflow.cn/v1", "providerDoc": "https://platform.iflow.cn/en/docs", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-11-13", "openWeights": false, "releaseDate": "2024-12-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "io-net", "providerName": "IO.NET", "providerApi": "https://api.intelligence.io.solutions/api/v1", "providerDoc": "https://io.net/docs/guides/intelligence/io-intelligence", "model": "zai-org/GLM-4.6", "modelKey": "zai-org/GLM-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2024-11-15", "openWeights": false, "releaseDate": "2024-11-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "Z.ai: GLM 4.6", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "zai-org/GLM-4.6", "modelKey": "zai-org/GLM-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-4.6", "modelKey": "zai/glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "modelscope", "providerName": "ModelScope", "providerApi": "https://api-inference.modelscope.cn/v1", "providerDoc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "model": "ZhipuAI/GLM-4.6", "modelKey": "ZhipuAI/GLM-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.6", "modelKey": "zai-org/glm-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "glm-4.6", "family": "glm", "status": "deprecated", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-09-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-4.6", "modelKey": "novita/glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "Z-AI/GLM 4.6", "metadata": { "lastUpdated": "2025-10-11", "openWeights": false, "releaseDate": "2025-10-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.6", "modelKey": "zai-org/GLM-4.6", "displayName": "zai-org/GLM-4.6", "family": "glm", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.6", "modelKey": "zai-org/GLM-4.6", "displayName": "zai-org/GLM-4.6", "family": "glm", "metadata": { "lastUpdated": "2025-11-25", "openWeights": false, "releaseDate": "2025-10-04" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:zai-org/GLM-4.6", "modelKey": "hf:zai-org/GLM-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.6", "modelKey": "zai/glm-4.6", "displayName": "GLM 4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.6", "modelKey": "z-ai/glm-4.6", "displayName": "GLM 4.6", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.6", "modelKey": "glm-4.6", "displayName": "GLM-4.6", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "openWeights": true, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/zai-org/GLM-4.6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.6", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.6", "mode": "chat", "metadata": { "source": "https://openrouter.ai/z-ai/glm-4.6" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.6", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/glm-4-6" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vercel_ai_gateway", "model": "vercel_ai_gateway/zai/glm-4.6", "mode": "chat", "metadata": { "source": "https://vercel.com/ai-gateway/models/glm-4.6" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.6", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.6", "displayName": "Z.ai: GLM 4.6", "metadata": { "canonicalSlug": "z-ai/glm-4.6", "createdAt": "2025-09-30T12:32:56.000Z", "huggingFaceId": "zai-org/GLM-4.6", "knowledgeCutoff": "2025-03-31", "links": { "details": "/api/v1/models/z-ai/glm-4.6/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 202752, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.6-derestricted-v5", "provider": "z-ai", "model": "glm-4.6-derestricted-v5", "displayName": "GLM 4.6 Derestricted v5", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/GLM-4.6-Derestricted-v5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "outputTokens": 8192, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "GLM-4.6-Derestricted-v5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "GLM 4.6 Derestricted v5" ], "releaseDate": "2025-12-23", "lastUpdated": "2025-12-23", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "GLM-4.6-Derestricted-v5", "modelKey": "GLM-4.6-Derestricted-v5", "displayName": "GLM 4.6 Derestricted v5", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } } ] }, { "id": "z-ai/glm-4.6-original", "provider": "z-ai", "model": "glm-4.6-original", "displayName": "GLM 4.6 Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.6-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.6-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.35, "output": 1.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.6 Original" ], "releaseDate": "2025-12-11", "lastUpdated": "2025-12-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.6-original", "modelKey": "zai-org/glm-4.6-original", "displayName": "GLM 4.6 Original", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } } ] }, { "id": "z-ai/glm-4.6-turbo", "provider": "z-ai", "model": "glm-4.6-turbo", "displayName": "GLM 4.6 Turbo", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/GLM-4.6-turbo" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 204800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/GLM-4.6-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "GLM 4.6 Turbo" ], "releaseDate": "2025-10-02", "lastUpdated": "2025-10-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/GLM-4.6-turbo", "modelKey": "zai-org/GLM-4.6-turbo", "displayName": "GLM 4.6 Turbo", "metadata": { "lastUpdated": "2025-10-02", "openWeights": false, "releaseDate": "2025-10-02" } } ] }, { "id": "z-ai/glm-4.6-turbo:thinking", "provider": "z-ai", "model": "glm-4.6-turbo:thinking", "displayName": "GLM 4.6 Turbo (Thinking)", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/GLM-4.6-turbo:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 204800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/GLM-4.6-turbo:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "GLM 4.6 Turbo (Thinking)" ], "releaseDate": "2025-10-02", "lastUpdated": "2025-10-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/GLM-4.6-turbo:thinking", "modelKey": "zai-org/GLM-4.6-turbo:thinking", "displayName": "GLM 4.6 Turbo (Thinking)", "metadata": { "lastUpdated": "2025-10-02", "openWeights": false, "releaseDate": "2025-10-02" } } ] }, { "id": "z-ai/glm-4.6:exacto", "provider": "z-ai", "model": "glm-4.6:exacto", "mode": "chat", "sources": [ "litellm" ], "providers": [ "openrouter" ], "aliases": [ "openrouter/z-ai/glm-4.6:exacto" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "inputTokens": 202800, "maxTokens": 131000, "outputTokens": 131000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.6:exacto", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 1.9 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.6:exacto", "mode": "chat", "metadata": { "source": "https://openrouter.ai/z-ai/glm-4.6:exacto" } } ] }, { "id": "z-ai/glm-4.6:thinking", "provider": "z-ai", "model": "glm-4.6:thinking", "displayName": "GLM 4.6 Thinking", "family": "glm", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/z-ai/glm-4.6:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-4.6:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.4, "output": 1.5 } } ] }, "metadata": { "displayNames": [ "GLM 4.6 Thinking" ], "families": [ "glm" ], "releaseDate": "2025-09-29", "lastUpdated": "2025-09-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-4.6:thinking", "modelKey": "z-ai/glm-4.6:thinking", "displayName": "GLM 4.6 Thinking", "family": "glm", "metadata": { "lastUpdated": "2025-09-29", "openWeights": false, "releaseDate": "2025-09-29" } } ] }, { "id": "z-ai/glm-4.6v", "provider": "z-ai", "model": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "chutes", "kilo", "llmgateway", "nano-gpt", "novita", "novita-ai", "openrouter", "poe", "siliconflow", "siliconflow-cn", "vercel", "zai", "zenmux", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-4.6v", "chutes/zai-org/GLM-4.6V", "kilo/z-ai/glm-4.6v", "llmgateway/glm-4.6v", "nano-gpt/zai-org/glm-4.6v", "novita-ai/zai-org/glm-4.6v", "novita/zai-org/glm-4.6v", "openrouter/z-ai/glm-4.6v", "poe/novita/glm-4.6v", "siliconflow-cn/zai-org/GLM-4.6V", "siliconflow/zai-org/GLM-4.6V", "vercel/zai/glm-4.6v", "zai/glm-4.6v", "zenmux/z-ai/glm-4.6v", "zhipuai-coding-plan/glm-4.6v", "zhipuai/glm-4.6v" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 200000, "inputTokens": 131072, "maxTokens": 32768, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "systemMessages": true, "transcription": false, "vision": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.145, "output": 0.43 } }, { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-4.6V", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.055, "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "zai-org/GLM-4.6V", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.6V", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.14, "output": 0.42 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.6v", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 0.9 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.6v", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.055, "input": 0.3, "output": 0.9 }, "extra": { "input_cost_per_token_cache_hit": 5.5e-8 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.6v", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.055, "input": 0.3, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "GLM 4.6V", "GLM-4.6V", "Z.ai: GLM 4.6V", "glm-4.6v", "zai-org/GLM-4.6V" ], "families": [ "glm", "glmv" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.6v", "modelKey": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-4.6V", "modelKey": "zai-org/GLM-4.6V", "displayName": "GLM 4.6V", "family": "glm", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2025-12-29", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.6v", "modelKey": "z-ai/glm-4.6v", "displayName": "Z.ai: GLM 4.6V", "metadata": { "lastUpdated": "2026-01-10", "openWeights": true, "releaseDate": "2025-09-30" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.6v", "modelKey": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.6v", "modelKey": "zai-org/glm-4.6v", "displayName": "GLM 4.6V", "metadata": { "lastUpdated": "2025-12-11", "openWeights": false, "releaseDate": "2025-12-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.6v", "modelKey": "zai-org/glm-4.6v", "displayName": "GLM 4.6V", "family": "glmv", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.6v", "modelKey": "z-ai/glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-4.6v", "modelKey": "novita/glm-4.6v", "displayName": "glm-4.6v", "metadata": { "lastUpdated": "2025-12-09", "openWeights": false, "releaseDate": "2025-12-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.6V", "modelKey": "zai-org/GLM-4.6V", "displayName": "zai-org/GLM-4.6V", "family": "glm", "metadata": { "lastUpdated": "2025-12-07", "openWeights": false, "releaseDate": "2025-12-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.6V", "modelKey": "zai-org/GLM-4.6V", "displayName": "zai-org/GLM-4.6V", "family": "glm", "metadata": { "lastUpdated": "2025-12-07", "openWeights": false, "releaseDate": "2025-12-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.6v", "modelKey": "zai/glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.6v", "modelKey": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.6v", "modelKey": "z-ai/glm-4.6v", "displayName": "GLM 4.6V", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-4.6v", "modelKey": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.6v", "modelKey": "glm-4.6v", "displayName": "GLM-4.6V", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.6v", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.6v", "displayName": "Z.ai: GLM 4.6V", "metadata": { "canonicalSlug": "z-ai/glm-4.6-20251208", "createdAt": "2025-12-08T15:24:22.000Z", "huggingFaceId": "zai-org/GLM-4.6V", "links": { "details": "/api/v1/models/z-ai/glm-4.6-20251208/endpoints" }, "reasoning": { "mandatory": false }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.6v-flash", "provider": "z-ai", "model": "glm-4.6v-flash", "displayName": "GLM-4.6V Flash", "family": "glm", "sources": [ "models.dev" ], "providers": [ "llmgateway", "vercel", "zenmux" ], "aliases": [ "llmgateway/glm-4.6v-flash", "vercel/zai/glm-4.6v-flash", "zenmux/z-ai/glm-4.6v-flash" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.6v-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.6v-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.0043, "input": 0.02, "output": 0.21 } } ] }, "metadata": { "displayNames": [ "GLM 4.6V FlashX", "GLM-4.6V Flash", "GLM-4.6V-Flash" ], "families": [ "glm" ], "statuses": [ "beta" ], "knowledgeCutoff": "2024-10", "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.6v-flash", "modelKey": "glm-4.6v-flash", "displayName": "GLM-4.6V Flash", "family": "glm", "status": "beta", "metadata": { "lastUpdated": "2025-12-08", "openWeights": true, "releaseDate": "2025-12-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.6v-flash", "modelKey": "zai/glm-4.6v-flash", "displayName": "GLM-4.6V-Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.6v-flash", "modelKey": "z-ai/glm-4.6v-flash", "displayName": "GLM 4.6V FlashX", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "z-ai/glm-4.6v-flash-free", "provider": "z-ai", "model": "glm-4.6v-flash-free", "displayName": "GLM 4.6V Flash (Free)", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/z-ai/glm-4.6v-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.6v-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM 4.6V Flash (Free)" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.6v-flash-free", "modelKey": "z-ai/glm-4.6v-flash-free", "displayName": "GLM 4.6V Flash (Free)", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "z-ai/glm-4.6v-flash-original", "provider": "z-ai", "model": "glm-4.6v-flash-original", "displayName": "GLM 4.6V Flash", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.6v-flash-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 24000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.6v-flash-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.6V Flash" ], "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.6v-flash-original", "modelKey": "zai-org/glm-4.6v-flash-original", "displayName": "GLM 4.6V Flash", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "z-ai/glm-4.6v-flashx", "provider": "z-ai", "model": "glm-4.6v-flashx", "displayName": "GLM-4.6V FlashX", "family": "glm", "sources": [ "models.dev" ], "providers": [ "llmgateway" ], "aliases": [ "llmgateway/glm-4.6v-flashx" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 16000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.6v-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.004, "input": 0.04, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM-4.6V FlashX" ], "families": [ "glm" ], "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.6v-flashx", "modelKey": "glm-4.6v-flashx", "displayName": "GLM-4.6V FlashX", "family": "glm", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "z-ai/glm-4.6v-original", "provider": "z-ai", "model": "glm-4.6v-original", "displayName": "GLM 4.6V Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.6v-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 24000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.6v-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 0.9 } } ] }, "metadata": { "displayNames": [ "GLM 4.6V Original" ], "releaseDate": "2025-12-08", "lastUpdated": "2025-12-08", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.6v-original", "modelKey": "zai-org/glm-4.6v-original", "displayName": "GLM 4.6V Original", "metadata": { "lastUpdated": "2025-12-08", "openWeights": false, "releaseDate": "2025-12-08" } } ] }, { "id": "z-ai/glm-4.7", "provider": "z-ai", "model": "glm-4.7", "displayName": "GLM 4.7", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "alibaba-coding-plan", "alibaba-coding-plan-cn", "baseten", "berget", "cortecs", "crof", "deepinfra", "dinference", "huggingface", "jiekou", "kilo", "kuae-cloud-coding-plan", "llmgateway", "meganova", "merge-gateway", "moark", "nano-gpt", "novita", "novita-ai", "ollama-cloud", "opencode", "openrouter", "orcarouter", "poe", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "together_ai", "vercel", "zai", "zai-coding-plan", "zenmux", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-4.7", "abacus/zai-org/glm-4.7", "alibaba-coding-plan-cn/glm-4.7", "alibaba-coding-plan/glm-4.7", "baseten/zai-org/GLM-4.7", "berget/zai-org/GLM-4.7", "cortecs/glm-4.7", "crof/glm-4.7", "deepinfra/zai-org/GLM-4.7", "dinference/glm-4.7", "huggingface/zai-org/GLM-4.7", "jiekou/zai-org/glm-4.7", "kilo/z-ai/glm-4.7", "kuae-cloud-coding-plan/GLM-4.7", "llmgateway/glm-4.7", "meganova/zai-org/GLM-4.7", "merge-gateway/zai/glm-4.7", "moark/GLM-4.7", "nano-gpt/TEE/glm-4.7", "nano-gpt/zai-org/glm-4.7", "novita-ai/zai-org/glm-4.7", "novita/zai-org/glm-4.7", "ollama-cloud/glm-4.7", "opencode/glm-4.7", "openrouter/z-ai/glm-4.7", "orcarouter/z-ai/glm-4.7", "poe/novita/glm-4.7", "qiniu-ai/z-ai/glm-4.7", "siliconflow-cn/Pro/zai-org/GLM-4.7", "siliconflow/zai-org/GLM-4.7", "synthetic/hf:zai-org/GLM-4.7", "together_ai/zai-org/GLM-4.7", "vercel/zai/glm-4.7", "zai-coding-plan/glm-4.7", "zai/glm-4.7", "zenmux/z-ai/glm-4.7", "zhipuai-coding-plan/glm-4.7", "zhipuai/glm-4.7" ], "mergedProviderModelRecords": 38, "limits": { "contextTokens": 205000, "inputTokens": 204800, "maxTokens": 200000, "outputTokens": 205000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "assistantPrefill": true, "functionCalling": true, "promptCaching": true, "toolChoice": true, "vision": true, "parallelFunctionCalling": true, "responseSchema": true, "webSearch": false, "interleaved": true, "systemMessages": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.286, "output": 1.142 } }, { "source": "models.dev", "provider": "abacus", "model": "zai-org/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "baseten", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "berget", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.77, "output": 2.75 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 2.23 } }, { "source": "models.dev", "provider": "crof", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.05, "cacheWrite": 0, "input": 0.25, "output": 1.1 } }, { "source": "models.dev", "provider": "deepinfra", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 1.75 } }, { "source": "models.dev", "provider": "dinference", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.45, "output": 1.65 } }, { "source": "models.dev", "provider": "huggingface", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "jiekou", "model": "zai-org/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.38, "output": 1.98 } }, { "source": "models.dev", "provider": "kuae-cloud-coding-plan", "model": "GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "meganova", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "moark", "model": "GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 3.5, "output": 14 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 3.3 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.8 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "opencode", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 1.75 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:zai-org/GLM-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.55, "output": 2.19 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 2.25, "input": 2.25, "output": 2.75 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.28, "output": 1.14 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.7", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/zai-org/GLM-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "novita", "model": "novita/zai-org/glm-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 }, "extra": { "input_cost_per_token_cache_hit": 1.1e-7 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0.4, "output": 1.5 } }, { "source": "litellm", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.45, "output": 2 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-4.7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.11, "cacheWrite": 0, "input": 0.6, "output": 2.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.7", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 1.75 } } ] }, "metadata": { "displayNames": [ "GLM 4.7", "GLM 4.7 TEE", "GLM-4.7", "Pro/zai-org/GLM-4.7", "Z-Ai/GLM 4.7", "Z.ai: GLM 4.7", "glm-4.7", "zai-org/GLM-4.7" ], "families": [ "glm" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 38 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "glm-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "zai-org/glm-4.7", "modelKey": "zai-org/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "lastUpdated": "2025-06-01", "openWeights": true, "releaseDate": "2025-06-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "berget", "providerName": "Berget.AI", "providerApi": "https://api.berget.ai/v1", "providerDoc": "https://api.berget.ai", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "dinference", "providerName": "DInference", "providerApi": "https://api.dinference.com/v1", "providerDoc": "https://dinference.com", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "zai-org/glm-4.7", "modelKey": "zai-org/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.7", "modelKey": "z-ai/glm-4.7", "displayName": "Z.ai: GLM 4.7", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kuae-cloud-coding-plan", "providerName": "KUAE Cloud Coding Plan", "providerApi": "https://coding-plan-endpoint.kuaecloud.net/v1", "providerDoc": "https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/", "model": "GLM-4.7", "modelKey": "GLM-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-4.7", "modelKey": "zai/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "moark", "providerName": "Moark", "providerApi": "https://moark.com/v1", "providerDoc": "https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90", "model": "GLM-4.7", "modelKey": "GLM-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/glm-4.7", "modelKey": "TEE/glm-4.7", "displayName": "GLM 4.7 TEE", "family": "glm", "metadata": { "lastUpdated": "2026-01-29", "openWeights": false, "releaseDate": "2026-01-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7", "modelKey": "zai-org/glm-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "lastUpdated": "2026-01-29", "openWeights": true, "releaseDate": "2026-01-29" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.7", "modelKey": "zai-org/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "glm-4.7", "family": "glm", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.7", "modelKey": "z-ai/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-4.7", "modelKey": "z-ai/glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-4.7", "modelKey": "novita/glm-4.7", "displayName": "glm-4.7", "status": "deprecated", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "z-ai/glm-4.7", "modelKey": "z-ai/glm-4.7", "displayName": "Z-Ai/GLM 4.7", "metadata": { "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/zai-org/GLM-4.7", "modelKey": "Pro/zai-org/GLM-4.7", "displayName": "Pro/zai-org/GLM-4.7", "family": "glm", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-4.7", "modelKey": "zai-org/GLM-4.7", "displayName": "zai-org/GLM-4.7", "family": "glm", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:zai-org/GLM-4.7", "modelKey": "hf:zai-org/GLM-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.7", "modelKey": "zai/glm-4.7", "displayName": "GLM 4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.7", "modelKey": "z-ai/glm-4.7", "displayName": "GLM 4.7", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-23", "openWeights": false, "releaseDate": "2025-12-23" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7", "modelKey": "glm-4.7", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/zai-org/GLM-4.7", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "novita", "model": "novita/zai-org/glm-4.7", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.7", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "together_ai", "model": "together_ai/zai-org/GLM-4.7", "mode": "chat", "metadata": { "source": "https://www.together.ai/models/glm-4-7" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-4.7", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.7", "displayName": "Z.ai: GLM 4.7", "metadata": { "canonicalSlug": "z-ai/glm-4.7-20251222", "createdAt": "2025-12-22T04:33:34.000Z", "huggingFaceId": "zai-org/GLM-4.7", "links": { "details": "/api/v1/models/z-ai/glm-4.7-20251222/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 202752, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.7-flash", "provider": "z-ai", "model": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "cortecs", "crof", "deepinfra", "huggingface", "jiekou", "kilo", "llmgateway", "nano-gpt", "novita-ai", "openrouter", "poe", "synthetic", "vercel", "zai", "zhipuai" ], "aliases": [ "cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-4.7-flash", "cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash", "cortecs/glm-4.7-flash", "crof/glm-4.7-flash", "deepinfra/zai-org/GLM-4.7-Flash", "huggingface/zai-org/GLM-4.7-Flash", "jiekou/zai-org/glm-4.7-flash", "kilo/z-ai/glm-4.7-flash", "llmgateway/glm-4.7-flash", "nano-gpt/TEE/glm-4.7-flash", "nano-gpt/zai-org/glm-4.7-flash", "novita-ai/zai-org/glm-4.7-flash", "openrouter/z-ai/glm-4.7-flash", "poe/novita/glm-4.7-flash", "synthetic/hf:zai-org/GLM-4.7-Flash", "vercel/zai/glm-4.7-flash", "zai/glm-4.7-flash", "zhipuai/glm-4.7-flash" ], "mergedProviderModelRecords": 18, "limits": { "contextTokens": 203000, "inputTokens": 203000, "maxTokens": 32000, "outputTokens": 203000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "vision": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "cloudflare-ai-gateway", "model": "workers-ai/@cf/zai-org/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/zai-org/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0605, "output": 0.4 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.09, "output": 0.53 } }, { "source": "models.dev", "provider": "crof", "model": "glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.008, "cacheWrite": 0, "input": 0.04, "output": 0.3 } }, { "source": "models.dev", "provider": "deepinfra", "model": "zai-org/GLM-4.7-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "huggingface", "model": "zai-org/GLM-4.7-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "jiekou", "model": "zai-org/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.15, "output": 0.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:zai-org/GLM-4.7-Flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.7-flash", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0.07, "output": 0.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-4.7-flash", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.01, "input": 0.06, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash", "GLM 4.7 Flash TEE", "GLM-4.7-Flash", "Z.ai: GLM 4.7 Flash", "glm-4.7-flash" ], "families": [ "glm", "glm-flash" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 18 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-ai-gateway", "providerName": "Cloudflare AI Gateway", "providerDoc": "https://developers.cloudflare.com/ai-gateway/", "model": "workers-ai/@cf/zai-org/glm-4.7-flash", "modelKey": "workers-ai/@cf/zai-org/glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/zai-org/glm-4.7-flash", "modelKey": "@cf/zai-org/glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-4.7-flash", "modelKey": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-08", "openWeights": true, "releaseDate": "2025-08-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "glm-4.7-flash", "modelKey": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "zai-org/GLM-4.7-Flash", "modelKey": "zai-org/GLM-4.7-Flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "zai-org/GLM-4.7-Flash", "modelKey": "zai-org/GLM-4.7-Flash", "displayName": "GLM-4.7-Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-08", "openWeights": true, "releaseDate": "2025-08-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "jiekou", "providerName": "Jiekou.AI", "providerApi": "https://api.jiekou.ai/openai", "providerDoc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "model": "zai-org/glm-4.7-flash", "modelKey": "zai-org/glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm", "metadata": { "lastUpdated": "2026-01", "openWeights": true, "releaseDate": "2026-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-4.7-flash", "modelKey": "z-ai/glm-4.7-flash", "displayName": "Z.ai: GLM 4.7 Flash", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.7-flash", "modelKey": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/glm-4.7-flash", "modelKey": "TEE/glm-4.7-flash", "displayName": "GLM 4.7 Flash TEE", "family": "glm-flash", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-flash", "modelKey": "zai-org/glm-4.7-flash", "displayName": "GLM 4.7 Flash", "family": "glm-flash", "metadata": { "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-4.7-flash", "modelKey": "zai-org/glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-4.7-flash", "modelKey": "z-ai/glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-4.7-flash", "modelKey": "novita/glm-4.7-flash", "displayName": "glm-4.7-flash", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:zai-org/GLM-4.7-Flash", "modelKey": "hf:zai-org/GLM-4.7-Flash", "displayName": "GLM-4.7-Flash", "family": "glm", "metadata": { "lastUpdated": "2026-01-18", "openWeights": true, "releaseDate": "2026-01-18" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.7-flash", "modelKey": "zai/glm-4.7-flash", "displayName": "GLM 4.7 Flash", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-03-13", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7-flash", "modelKey": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7-flash", "modelKey": "glm-4.7-flash", "displayName": "GLM-4.7-Flash", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/z-ai/glm-4.7-flash", "mode": "chat" }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-4.7-flash", "displayName": "Z.ai: GLM 4.7 Flash", "metadata": { "canonicalSlug": "z-ai/glm-4.7-flash-20260119", "createdAt": "2026-01-19T14:45:13.000Z", "huggingFaceId": "zai-org/GLM-4.7-Flash", "links": { "details": "/api/v1/models/z-ai/glm-4.7-flash-20260119/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 202752, "max_completion_tokens": 16384, "is_moderated": false } } } ] }, { "id": "z-ai/glm-4.7-flash-free", "provider": "z-ai", "model": "glm-4.7-flash-free", "displayName": "GLM 4.7 Flash (Free)", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/z-ai/glm-4.7-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.7-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash (Free)" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.7-flash-free", "modelKey": "z-ai/glm-4.7-flash-free", "displayName": "GLM 4.7 Flash (Free)", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } } ] }, { "id": "z-ai/glm-4.7-flash-original", "provider": "z-ai", "model": "glm-4.7-flash-original", "displayName": "GLM 4.7 Flash Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7-flash-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-flash-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash Original" ], "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-flash-original", "modelKey": "zai-org/glm-4.7-flash-original", "displayName": "GLM 4.7 Flash Original", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } } ] }, { "id": "z-ai/glm-4.7-flash-original:thinking", "provider": "z-ai", "model": "glm-4.7-flash-original:thinking", "displayName": "GLM 4.7 Flash Original Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7-flash-original:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-flash-original:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash Original Thinking" ], "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-flash-original:thinking", "modelKey": "zai-org/glm-4.7-flash-original:thinking", "displayName": "GLM 4.7 Flash Original Thinking", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } } ] }, { "id": "z-ai/glm-4.7-flash:thinking", "provider": "z-ai", "model": "glm-4.7-flash:thinking", "displayName": "GLM 4.7 Flash Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7-flash:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-flash:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Flash Thinking" ], "releaseDate": "2026-01-19", "lastUpdated": "2026-01-19", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-flash:thinking", "modelKey": "zai-org/glm-4.7-flash:thinking", "displayName": "GLM 4.7 Flash Thinking", "metadata": { "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } } ] }, { "id": "z-ai/glm-4.7-flashx", "provider": "z-ai", "model": "glm-4.7-flashx", "displayName": "glm-4.7-flashx", "family": "glm-flash", "sources": [ "models.dev" ], "providers": [ "302ai", "llmgateway", "merge-gateway", "vercel", "zai", "zenmux", "zhipuai" ], "aliases": [ "302ai/glm-4.7-flashx", "llmgateway/glm-4.7-flashx", "merge-gateway/zai/glm-4.7-flashx", "vercel/zai/glm-4.7-flashx", "zai/glm-4.7-flashx", "zenmux/z-ai/glm-4.7-flashx", "zhipuai/glm-4.7-flashx" ], "mergedProviderModelRecords": 7, "limits": { "contextTokens": 200000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "interleaved": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.0715, "output": 0.429 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.06, "output": 0.4 } }, { "source": "models.dev", "provider": "zai", "model": "glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.07, "output": 0.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.07, "output": 0.42 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-4.7-flashx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0, "input": 0.07, "output": 0.4 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 FlashX", "GLM-4.7-FlashX", "glm-4.7-flashx" ], "families": [ "glm-flash" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-20", "lastUpdated": "2026-01-20", "providerModelRecordCount": 7 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-4.7-flashx", "modelKey": "glm-4.7-flashx", "displayName": "glm-4.7-flashx", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-20", "openWeights": true, "releaseDate": "2026-01-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-4.7-flashx", "modelKey": "glm-4.7-flashx", "displayName": "GLM-4.7-FlashX", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-4.7-flashx", "modelKey": "zai/glm-4.7-flashx", "displayName": "GLM-4.7-FlashX", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-4.7-flashx", "modelKey": "zai/glm-4.7-flashx", "displayName": "GLM 4.7 FlashX", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2025-01-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7-flashx", "modelKey": "glm-4.7-flashx", "displayName": "GLM-4.7-FlashX", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-4.7-flashx", "modelKey": "z-ai/glm-4.7-flashx", "displayName": "GLM 4.7 FlashX", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-19", "openWeights": false, "releaseDate": "2026-01-19" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-4.7-flashx", "modelKey": "glm-4.7-flashx", "displayName": "GLM-4.7-FlashX", "family": "glm-flash", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "openWeights": true, "releaseDate": "2026-01-19", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-4.7-fp8", "provider": "z-ai", "model": "glm-4.7-fp8", "displayName": "GLM 4.7 FP8", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "chutes", "gmi" ], "aliases": [ "chutes/zai-org/GLM-4.7-FP8", "gmi/zai-org/GLM-4.7-FP8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 202752, "inputTokens": 202752, "maxTokens": 16384, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-4.7-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14945, "input": 0.2989, "output": 1.1957 } }, { "source": "litellm", "provider": "gmi", "model": "gmi/zai-org/GLM-4.7-FP8", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 FP8" ], "families": [ "glm" ], "modes": [ "chat" ], "releaseDate": "2026-01-27", "lastUpdated": "2026-04-25", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-4.7-FP8", "modelKey": "zai-org/GLM-4.7-FP8", "displayName": "GLM 4.7 FP8", "family": "glm", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2026-01-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "gmi", "model": "gmi/zai-org/GLM-4.7-FP8", "mode": "chat" } ] }, { "id": "z-ai/glm-4.7-free", "provider": "z-ai", "model": "glm-4.7-free", "displayName": "GLM-4.7 Free", "family": "glm-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/glm-4.7-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "glm-4.7-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM-4.7 Free" ], "families": [ "glm-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-4.7-free", "modelKey": "glm-4.7-free", "displayName": "GLM-4.7 Free", "family": "glm-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22" } } ] }, { "id": "z-ai/glm-4.7-maas", "provider": "z-ai", "model": "glm-4.7-maas", "displayName": "GLM-4.7", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-zai_models" ], "aliases": [ "google-vertex/zai-org/glm-4.7-maas", "vertex_ai-zai_models/vertex_ai/zai-org/glm-4.7-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 200000, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "zai-org/glm-4.7-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "vertex_ai-zai_models", "model": "vertex_ai/zai-org/glm-4.7-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "GLM-4.7" ], "families": [ "glm" ], "modes": [ "chat" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-01-06", "lastUpdated": "2026-01-06", "supportedRegions": [ "global" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "zai-org/glm-4.7-maas", "modelKey": "zai-org/glm-4.7-maas", "displayName": "GLM-4.7", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-06", "openWeights": true, "releaseDate": "2026-01-06", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-zai_models", "model": "vertex_ai/zai-org/glm-4.7-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supportedRegions": [ "global" ] } } ] }, { "id": "z-ai/glm-4.7-n", "provider": "z-ai", "model": "glm-4.7-n", "displayName": "glm-4.7-n", "sources": [ "models.dev" ], "providers": [ "poe" ], "aliases": [ "poe/novita/glm-4.7-n" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 205000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": false, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "metadata": { "displayNames": [ "glm-4.7-n" ], "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-4.7-n", "modelKey": "novita/glm-4.7-n", "displayName": "glm-4.7-n", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } } ] }, { "id": "z-ai/glm-4.7-original", "provider": "z-ai", "model": "glm-4.7-original", "displayName": "GLM 4.7 Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Original" ], "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-original", "modelKey": "zai-org/glm-4.7-original", "displayName": "GLM 4.7 Original", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } } ] }, { "id": "z-ai/glm-4.7-original:thinking", "provider": "z-ai", "model": "glm-4.7-original:thinking", "displayName": "GLM 4.7 Original Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7-original:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7-original:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.6, "output": 2.2 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Original Thinking" ], "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7-original:thinking", "modelKey": "zai-org/glm-4.7-original:thinking", "displayName": "GLM 4.7 Original Thinking", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } } ] }, { "id": "z-ai/glm-4.7-tee", "provider": "z-ai", "model": "glm-4.7-tee", "displayName": "GLM 4.7 TEE", "family": "glm", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/zai-org/GLM-4.7-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-4.7-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.195, "input": 0.39, "output": 1.75 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 TEE" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-4.7-TEE", "modelKey": "zai-org/GLM-4.7-TEE", "displayName": "GLM 4.7 TEE", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "openWeights": true, "releaseDate": "2025-12-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-4.7:thinking", "provider": "z-ai", "model": "glm-4.7:thinking", "displayName": "GLM 4.7 Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-4.7:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-4.7:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "GLM 4.7 Thinking" ], "releaseDate": "2025-12-22", "lastUpdated": "2025-12-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-4.7:thinking", "modelKey": "zai-org/glm-4.7:thinking", "displayName": "GLM 4.7 Thinking", "metadata": { "lastUpdated": "2025-12-22", "openWeights": false, "releaseDate": "2025-12-22" } } ] }, { "id": "z-ai/glm-4p5", "provider": "z-ai", "model": "glm-4p5", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/glm-4p5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 96000, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/glm-4p5" } } ] }, { "id": "z-ai/glm-4p5-air", "provider": "z-ai", "model": "glm-4p5-air", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/glm-4p5-air" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "maxTokens": 96000, "outputTokens": 96000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5-air", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.22, "output": 0.88 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5-air", "mode": "chat", "metadata": { "source": "https://artificialanalysis.ai/models/glm-4-5-air" } } ] }, { "id": "z-ai/glm-4p5v", "provider": "z-ai", "model": "glm-4p5v", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/glm-4p5v" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 131072, "inputTokens": 131072, "maxTokens": 131072, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "speech": false, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5v", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 1.2, "output": 1.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p5v", "mode": "chat" } ] }, { "id": "z-ai/glm-4p6", "provider": "z-ai", "model": "glm-4p6", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/glm-4p6" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "inputTokens": 202800, "maxTokens": 202800, "outputTokens": 202800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p6", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.55, "output": 2.19 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p6", "mode": "chat", "metadata": { "source": "https://fireworks.ai/pricing" } } ] }, { "id": "z-ai/glm-4p7", "provider": "z-ai", "model": "glm-4p7", "mode": "chat", "sources": [ "litellm" ], "providers": [ "fireworks_ai" ], "aliases": [ "fireworks_ai/accounts/fireworks/models/glm-4p7", "fireworks_ai/glm-4p7" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 202800, "inputTokens": 202800, "maxTokens": 202800, "outputTokens": 202800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "reasoning": true, "rerank": false, "responseSchema": true, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 0.6, "output": 2.2 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/glm-4p7", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "input": 0.6, "output": 2.2 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-4p7", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/glm-4p7" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/glm-4p7", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/glm-4p7" } } ] }, { "id": "z-ai/glm-5", "provider": "z-ai", "model": "glm-5", "displayName": "GLM 5", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev", "openrouter" ], "providers": [ "302ai", "abacus", "alibaba-cn", "alibaba-coding-plan", "alibaba-coding-plan-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "baseten", "cortecs", "crof", "deepinfra", "digitalocean", "dinference", "fastrouter", "friendli", "huggingface", "kilo", "llmgateway", "meganova", "merge-gateway", "nano-gpt", "nebius", "novita-ai", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "poe", "qiniu-ai", "siliconflow", "siliconflow-cn", "synthetic", "tencent-coding-plan", "togetherai", "vercel", "zai", "zenmux", "zhipuai" ], "aliases": [ "302ai/glm-5", "abacus/zai-org/glm-5", "alibaba-cn/glm-5", "alibaba-coding-plan-cn/glm-5", "alibaba-coding-plan/glm-5", "alibaba-token-plan-cn/glm-5", "alibaba-token-plan/glm-5", "baseten/zai-org/GLM-5", "cortecs/glm-5", "crof/glm-5", "deepinfra/zai-org/GLM-5", "digitalocean/glm-5", "dinference/glm-5", "fastrouter/z-ai/glm-5", "friendli/zai-org/GLM-5", "huggingface/zai-org/GLM-5", "kilo/z-ai/glm-5", "llmgateway/glm-5", "meganova/zai-org/GLM-5", "merge-gateway/zai/glm-5", "nano-gpt/TEE/glm-5", "nano-gpt/zai-org/glm-5", "nebius/zai-org/GLM-5", "novita-ai/zai-org/glm-5", "ollama-cloud/glm-5", "opencode-go/glm-5", "opencode/glm-5", "openrouter/z-ai/glm-5", "orcarouter/z-ai/glm-5", "poe/novita/glm-5", "qiniu-ai/z-ai/glm-5", "siliconflow-cn/Pro/zai-org/GLM-5", "siliconflow/zai-org/GLM-5", "synthetic/hf:zai-org/GLM-5", "tencent-coding-plan/glm-5", "togetherai/zai-org/GLM-5", "vercel/zai/glm-5", "zai/glm-5", "zenmux/z-ai/glm-5", "zhipuai/glm-5" ], "mergedProviderModelRecords": 40, "limits": { "contextTokens": 205000, "inputTokens": 203000, "maxTokens": 128000, "outputTokens": 205000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "embedding": false, "imageGeneration": false, "moderation": false, "rerank": false, "speech": false, "transcription": false, "supports1MContext": false, "functionCalling": true, "toolChoice": true, "parallelFunctionCalling": false, "responseSchema": true, "webSearch": false, "promptCaching": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.6, "output": 2.6 } }, { "source": "models.dev", "provider": "abacus", "model": "zai-org/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.86, "output": 3.15 } }, { "source": "models.dev", "provider": "alibaba-coding-plan-cn", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-coding-plan", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "baseten", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 0.95, "output": 3.15 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.08, "output": 3.44 } }, { "source": "models.dev", "provider": "crof", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 0, "input": 0.48, "output": 1.9 } }, { "source": "models.dev", "provider": "deepinfra", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 2.08 } }, { "source": "models.dev", "provider": "digitalocean", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "dinference", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.75, "output": 2.4 } }, { "source": "models.dev", "provider": "fastrouter", "model": "z-ai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 3.15 } }, { "source": "models.dev", "provider": "friendli", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.5, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "huggingface", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 2.3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "meganova", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.8, "output": 2.56 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.2, "output": 3.5 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.55 } }, { "source": "models.dev", "provider": "nebius", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 1, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "opencode-go", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "opencode", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 1.92 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "poe", "model": "novita/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.95, "output": 2.55 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "tencent-coding-plan", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "togetherai", "model": "zai-org/GLM-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "zai", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.14, "input": 0.58, "output": 2.6 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "litellm", "provider": "baseten", "model": "baseten/zai-org/GLM-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.95, "output": 3.15 } }, { "source": "litellm", "provider": "openrouter", "model": "openrouter/z-ai/glm-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "input": 0.8, "output": 2.56 } }, { "source": "litellm", "provider": "zai", "model": "zai/glm-5", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-5", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 1.92 } } ] }, "metadata": { "displayNames": [ "GLM 5", "GLM 5 TEE", "GLM-5", "Pro/zai-org/GLM-5", "Z-Ai/GLM 5", "Z.ai: GLM 5", "glm-5", "zai-org/GLM-5" ], "families": [ "glm" ], "modes": [ "chat" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2026-01", "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 40 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-5", "modelKey": "glm-5", "displayName": "glm-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "abacus", "providerName": "Abacus", "providerApi": "https://routellm.abacus.ai/v1", "providerDoc": "https://abacus.ai/help/api", "model": "zai-org/glm-5", "modelKey": "zai-org/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan-cn", "providerName": "Alibaba Coding Plan (China)", "providerApi": "https://coding.dashscope.aliyuncs.com/v1", "providerDoc": "https://help.aliyun.com/zh/model-studio/coding-plan", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-coding-plan", "providerName": "Alibaba Coding Plan", "providerApi": "https://coding-intl.dashscope.aliyuncs.com/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM 5", "family": "glm", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM 5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-12", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "digitalocean", "providerName": "DigitalOcean", "providerApi": "https://inference.do-ai.run/v1", "providerDoc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM 5", "family": "glm", "metadata": { "lastUpdated": "2026-04-16", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "dinference", "providerName": "DInference", "providerApi": "https://api.dinference.com/v1", "providerDoc": "https://dinference.com", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "Z.ai: GLM 5", "metadata": { "lastUpdated": "2026-03-15", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "meganova", "providerName": "Meganova", "providerApi": "https://api.meganova.ai/v1", "providerDoc": "https://docs.meganova.ai", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-5", "modelKey": "zai/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/glm-5", "modelKey": "TEE/glm-5", "displayName": "GLM 5 TEE", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5", "modelKey": "zai-org/glm-5", "displayName": "GLM 5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nebius", "providerName": "Nebius Token Factory", "providerApi": "https://api.tokenfactory.nebius.com/v1", "providerDoc": "https://docs.tokenfactory.nebius.com/", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "status": "deprecated", "metadata": { "knowledgeCutoff": "2026-01", "lastUpdated": "2026-03-10", "openWeights": false, "releaseDate": "2026-03-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-5", "modelKey": "zai-org/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "glm-5", "modelKey": "glm-5", "displayName": "glm-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "poe", "providerName": "Poe", "providerApi": "https://api.poe.com/v1", "providerDoc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "model": "novita/glm-5", "modelKey": "novita/glm-5", "displayName": "GLM-5", "metadata": { "lastUpdated": "2026-02-15", "openWeights": false, "releaseDate": "2026-02-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "qiniu-ai", "providerName": "Qiniu", "providerApi": "https://api.qnaigc.com/v1", "providerDoc": "https://developer.qiniu.com/aitokenapi", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "Z-Ai/GLM 5", "metadata": { "lastUpdated": "2026-02-12", "openWeights": false, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/zai-org/GLM-5", "modelKey": "Pro/zai-org/GLM-5", "displayName": "Pro/zai-org/GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "zai-org/GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-06-15", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:zai-org/GLM-5", "modelKey": "hf:zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-04-08", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "tencent-coding-plan", "providerName": "Tencent Coding Plan (China)", "providerApi": "https://api.lkeap.cloud.tencent.com/coding/v3", "providerDoc": "https://cloud.tencent.com/document/product/1772/128947", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "zai-org/GLM-5", "modelKey": "zai-org/GLM-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-5", "modelKey": "zai/glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-5", "modelKey": "z-ai/glm-5", "displayName": "GLM 5", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5", "modelKey": "glm-5", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "baseten", "model": "baseten/zai-org/GLM-5", "mode": "chat" }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "openrouter", "model": "openrouter/z-ai/glm-5", "mode": "chat", "metadata": { "source": "https://openrouter.ai/z-ai/glm-5" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-5", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-5", "displayName": "Z.ai: GLM 5", "metadata": { "canonicalSlug": "z-ai/glm-5-20260211", "createdAt": "2026-02-11T16:59:42.000Z", "huggingFaceId": "zai-org/GLM-5", "links": { "details": "/api/v1/models/z-ai/glm-5-20260211/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 202752, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "z-ai/glm-5-code", "provider": "z-ai", "model": "glm-5-code", "mode": "chat", "sources": [ "litellm" ], "providers": [ "zai" ], "aliases": [ "zai/glm-5-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "audioInput": false, "audioOutput": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "imageInput": false, "imageOutput": false, "moderation": false, "pdfInput": false, "promptCaching": true, "reasoning": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "litellm", "provider": "zai", "model": "zai/glm-5-code", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.3, "cacheWrite": 0, "input": 1.2, "output": 5 } } ] }, "metadata": { "modes": [ "chat" ], "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "zai", "model": "zai/glm-5-code", "mode": "chat", "metadata": { "source": "https://docs.z.ai/guides/overview/pricing" } } ] }, { "id": "z-ai/glm-5-fast", "provider": "z-ai", "model": "glm-5-fast", "displayName": "GLM 5 Fast", "family": "glm", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/glm-5-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202736, "outputTokens": 202736, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "glm-5-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "GLM 5 Fast" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "glm-5-fast", "modelKey": "glm-5-fast", "displayName": "GLM 5 Fast", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } } ] }, { "id": "z-ai/glm-5-fp8", "provider": "z-ai", "model": "glm-5-fp8", "displayName": "GLM-5", "family": "glm", "sources": [ "models.dev" ], "providers": [ "gmicloud", "wandb" ], "aliases": [ "gmicloud/zai-org/GLM-5-FP8", "wandb/zai-org/GLM-5-FP8" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 202752, "outputTokens": 200000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "gmicloud", "model": "zai-org/GLM-5-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.12, "input": 0.6, "output": 1.92 } }, { "source": "models.dev", "provider": "wandb", "model": "zai-org/GLM-5-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM 5", "GLM-5" ], "families": [ "glm" ], "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "zai-org/GLM-5-FP8", "modelKey": "zai-org/GLM-5-FP8", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "zai-org/GLM-5-FP8", "modelKey": "zai-org/GLM-5-FP8", "displayName": "GLM 5", "family": "glm", "metadata": { "lastUpdated": "2026-03-12", "openWeights": true, "releaseDate": "2026-02-11" } } ] }, { "id": "z-ai/glm-5-free", "provider": "z-ai", "model": "glm-5-free", "displayName": "GLM-5 Free", "family": "glm-free", "sources": [ "models.dev" ], "providers": [ "opencode" ], "aliases": [ "opencode/glm-5-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 204800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "opencode", "model": "glm-5-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "GLM-5 Free" ], "families": [ "glm-free" ], "statuses": [ "deprecated" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5-free", "modelKey": "glm-5-free", "displayName": "GLM-5 Free", "family": "glm-free", "status": "deprecated", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } } ] }, { "id": "z-ai/glm-5-maas", "provider": "z-ai", "model": "glm-5-maas", "displayName": "GLM-5", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "google-vertex", "vertex_ai-zai_models" ], "aliases": [ "google-vertex/zai-org/glm-5-maas", "vertex_ai-zai_models/vertex_ai/zai-org/glm-5-maas" ], "mergedProviderModelRecords": 2, "limits": { "contextTokens": 202752, "inputTokens": 200000, "maxTokens": 128000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": true, "imageGeneration": false, "moderation": false, "promptCaching": true, "rerank": false, "speech": false, "toolChoice": true, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "google-vertex", "model": "zai-org/glm-5-maas", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 3.2 } }, { "source": "litellm", "provider": "vertex_ai-zai_models", "model": "vertex_ai/zai-org/glm-5-maas", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.1, "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM-5" ], "families": [ "glm" ], "modes": [ "chat" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "supportedRegions": [ "global" ], "providerModelRecordCount": 2 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "google-vertex", "providerName": "Vertex", "providerDoc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "model": "zai-org/glm-5-maas", "modelKey": "zai-org/glm-5-maas", "displayName": "GLM-5", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "vertex_ai-zai_models", "model": "vertex_ai/zai-org/glm-5-maas", "mode": "chat", "metadata": { "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", "supportedRegions": [ "global" ] } } ] }, { "id": "z-ai/glm-5-original", "provider": "z-ai", "model": "glm-5-original", "displayName": "GLM 5 Original", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-5-original" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5-original", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM 5 Original" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5-original", "modelKey": "zai-org/glm-5-original", "displayName": "GLM 5 Original", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } } ] }, { "id": "z-ai/glm-5-original:thinking", "provider": "z-ai", "model": "glm-5-original:thinking", "displayName": "GLM 5 Original Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-5-original:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5-original:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } } ] }, "metadata": { "displayNames": [ "GLM 5 Original Thinking" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5-original:thinking", "modelKey": "zai-org/glm-5-original:thinking", "displayName": "GLM 5 Original Thinking", "metadata": { "lastUpdated": "2026-02-11", "openWeights": false, "releaseDate": "2026-02-11" } } ] }, { "id": "z-ai/glm-5-tee", "provider": "z-ai", "model": "glm-5-tee", "displayName": "GLM 5 TEE", "family": "glm", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/zai-org/GLM-5-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-5-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.475, "input": 0.95, "output": 2.55 } } ] }, "metadata": { "displayNames": [ "GLM 5 TEE" ], "families": [ "glm" ], "releaseDate": "2026-02-12", "lastUpdated": "2026-02-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-5-TEE", "modelKey": "zai-org/GLM-5-TEE", "displayName": "GLM 5 TEE", "family": "glm", "metadata": { "lastUpdated": "2026-02-12", "openWeights": true, "releaseDate": "2026-02-12", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-5-turbo", "provider": "z-ai", "model": "glm-5-turbo", "displayName": "glm-5-turbo", "family": "glm", "sources": [ "models.dev", "openrouter" ], "providers": [ "302ai", "chutes", "cortecs", "kilo", "merge-gateway", "nano-gpt", "openrouter", "vercel", "zai", "zai-coding-plan", "zenmux", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-5-turbo", "chutes/zai-org/GLM-5-Turbo", "cortecs/glm-5-turbo", "kilo/z-ai/glm-5-turbo", "merge-gateway/zai/glm-5-turbo", "nano-gpt/z-ai/glm-5-turbo", "openrouter/z-ai/glm-5-turbo", "vercel/zai/glm-5-turbo", "zai-coding-plan/glm-5-turbo", "zai/glm-5-turbo", "zenmux/z-ai/glm-5-turbo", "zhipuai-coding-plan/glm-5-turbo" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 262144, "inputTokens": 202800, "outputTokens": 131100, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 3.2 } }, { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-5-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24455, "input": 0.4891, "output": 1.9565 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.308, "cacheWrite": 1.544, "input": 1.235, "output": 4.118 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "cacheWrite": 0, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "cacheWrite": 0, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.88, "output": 3.48 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-5-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-5-turbo", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } } ] }, "metadata": { "displayNames": [ "GLM 5 Turbo", "GLM-5-Turbo", "Z.ai: GLM 5 Turbo", "glm-5-turbo" ], "families": [ "glm" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-03-16", "lastUpdated": "2026-03-16", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-5-turbo", "modelKey": "glm-5-turbo", "displayName": "glm-5-turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-5-Turbo", "modelKey": "zai-org/GLM-5-Turbo", "displayName": "GLM 5 Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-25", "openWeights": true, "releaseDate": "2026-03-11", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-5-turbo", "modelKey": "glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-5-turbo", "modelKey": "z-ai/glm-5-turbo", "displayName": "Z.ai: GLM 5 Turbo", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-03-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-5-turbo", "modelKey": "zai/glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-5-turbo", "modelKey": "z-ai/glm-5-turbo", "displayName": "GLM 5 Turbo", "metadata": { "lastUpdated": "2026-03-15", "openWeights": false, "releaseDate": "2026-03-15" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-5-turbo", "modelKey": "z-ai/glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-5-turbo", "modelKey": "zai/glm-5-turbo", "displayName": "GLM 5 Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-15", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-5-turbo", "modelKey": "glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5-turbo", "modelKey": "glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-5-turbo", "modelKey": "z-ai/glm-5-turbo", "displayName": "GLM 5 Turbo", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-5-turbo", "modelKey": "glm-5-turbo", "displayName": "GLM-5-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-03-16", "openWeights": false, "releaseDate": "2026-03-16", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-5-turbo", "displayName": "Z.ai: GLM 5 Turbo", "metadata": { "canonicalSlug": "z-ai/glm-5-turbo-20260315", "createdAt": "2026-03-15T14:06:13.000Z", "links": { "details": "/api/v1/models/z-ai/glm-5-turbo-20260315/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 262144, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "z-ai/glm-5:thinking", "provider": "z-ai", "model": "glm-5:thinking", "displayName": "GLM 5 Thinking", "family": "glm", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-5:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 128000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.55 } } ] }, "metadata": { "displayNames": [ "GLM 5 Thinking" ], "families": [ "glm" ], "releaseDate": "2026-02-11", "lastUpdated": "2026-02-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5:thinking", "modelKey": "zai-org/glm-5:thinking", "displayName": "GLM 5 Thinking", "family": "glm", "metadata": { "lastUpdated": "2026-02-11", "openWeights": true, "releaseDate": "2026-02-11" } } ] }, { "id": "z-ai/glm-5.1", "provider": "z-ai", "model": "glm-5.1", "displayName": "glm-5.1", "family": "glm", "sources": [ "models.dev", "openrouter" ], "providers": [ "302ai", "alibaba-cn", "alibaba-token-plan", "alibaba-token-plan-cn", "auriko", "baseten", "cortecs", "crof", "deepinfra", "dinference", "fastrouter", "friendli", "hpc-ai", "huggingface", "kilo", "lilac", "llmgateway", "merge-gateway", "nano-gpt", "novita-ai", "nvidia", "ollama-cloud", "opencode", "opencode-go", "openrouter", "orcarouter", "routing-run", "siliconflow", "siliconflow-cn", "synthetic", "togetherai", "vercel", "wafer.ai", "wandb", "zai", "zai-coding-plan", "zenmux", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-5.1", "alibaba-cn/glm-5.1", "alibaba-token-plan-cn/glm-5.1", "alibaba-token-plan/glm-5.1", "auriko/glm-5.1", "baseten/zai-org/GLM-5.1", "cortecs/glm-5.1", "crof/glm-5.1", "deepinfra/zai-org/GLM-5.1", "dinference/glm-5.1", "fastrouter/z-ai/glm-5.1", "friendli/zai-org/GLM-5.1", "hpc-ai/zai-org/glm-5.1", "huggingface/zai-org/GLM-5.1", "kilo/z-ai/glm-5.1", "lilac/zai-org/glm-5.1", "llmgateway/glm-5.1", "merge-gateway/zai/glm-5.1", "nano-gpt/TEE/glm-5.1", "nano-gpt/zai-org/glm-5.1", "novita-ai/zai-org/glm-5.1", "nvidia/z-ai/glm-5.1", "ollama-cloud/glm-5.1", "opencode-go/glm-5.1", "opencode/glm-5.1", "openrouter/z-ai/glm-5.1", "orcarouter/z-ai/glm-5.1", "routing-run/route/glm-5.1", "siliconflow-cn/Pro/zai-org/GLM-5.1", "siliconflow/zai-org/GLM-5.1", "synthetic/hf:zai-org/GLM-5.1", "togetherai/zai-org/GLM-5.1", "vercel/zai/glm-5.1", "wafer.ai/GLM-5.1", "wandb/zai-org/GLM-5.1", "zai-coding-plan/glm-5.1", "zai/glm-5.1", "zenmux/z-ai/glm-5.1", "zhipuai-coding-plan/glm-5.1", "zhipuai/glm-5.1" ], "mergedProviderModelRecords": 40, "limits": { "contextTokens": 205000, "inputTokens": 202752, "outputTokens": 205000, "supports1MContext": false }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "parallelFunctionCalling": true, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.86, "output": 3.5 } }, { "source": "models.dev", "provider": "alibaba-cn", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.17, "input": 0.87, "output": 3.48 } }, { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "auriko", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "baseten", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.3, "output": 4.3 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.31, "output": 4.1 } }, { "source": "models.dev", "provider": "crof", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "cacheWrite": 0, "input": 0.45, "output": 2.15 } }, { "source": "models.dev", "provider": "deepinfra", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.205, "input": 1.05, "output": 3.5 } }, { "source": "models.dev", "provider": "dinference", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.25, "output": 3.89 } }, { "source": "models.dev", "provider": "fastrouter", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.05, "output": 3.5 } }, { "source": "models.dev", "provider": "friendli", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "hpc-ai", "model": "zai-org/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.133, "input": 0.615, "output": 2.46 } }, { "source": "models.dev", "provider": "huggingface", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.26, "output": 3.96 } }, { "source": "models.dev", "provider": "lilac", "model": "zai-org/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.27, "input": 0.9, "output": 3 } }, { "source": "models.dev", "provider": "llmgateway", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.3, "cacheWrite": 0, "input": 6, "output": 24 } }, { "source": "models.dev", "provider": "merge-gateway", "model": "zai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 5.25 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.55 } }, { "source": "models.dev", "provider": "novita-ai", "model": "zai-org/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "nvidia", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "opencode-go", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "opencode", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.182, "input": 0.98, "output": 3.08 } }, { "source": "models.dev", "provider": "orcarouter", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "routing-run", "model": "route/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "Pro/zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "synthetic", "model": "hf:zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1, "input": 1, "output": 3 } }, { "source": "models.dev", "provider": "togetherai", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "wafer.ai", "model": "GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1, "cacheWrite": 0, "input": 1, "output": 3.2 } }, { "source": "models.dev", "provider": "wandb", "model": "zai-org/GLM-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1903, "input": 0.8781, "output": 3.5126 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-5.1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.3, "cacheWrite": 0, "input": 6, "output": 24 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-5.1", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.182, "input": 0.98, "output": 3.08 } } ] }, "metadata": { "displayNames": [ "GLM 5.1", "GLM 5.1 TEE", "GLM-5.1", "Pro/zai-org/GLM-5.1", "Z.ai: GLM 5.1", "glm-5.1", "zai-org/GLM-5.1" ], "families": [ "glm" ], "knowledgeCutoff": "2025-04", "releaseDate": "2026-04-10", "lastUpdated": "2026-04-10", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 40 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "glm-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-10", "openWeights": false, "releaseDate": "2026-04-10" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-cn", "providerName": "Alibaba (China)", "providerApi": "https://dashscope.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/models", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-14", "openWeights": true, "releaseDate": "2026-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "auriko", "providerName": "Auriko", "providerApi": "https://api.auriko.ai/v1", "providerDoc": "https://docs.auriko.ai", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-14", "openWeights": true, "releaseDate": "2026-04-14" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "deepinfra", "providerName": "Deep Infra", "providerDoc": "https://deepinfra.com/models", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "dinference", "providerName": "DInference", "providerApi": "https://api.dinference.com/v1", "providerDoc": "https://dinference.com", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fastrouter", "providerName": "FastRouter", "providerApi": "https://go.fastrouter.ai/api/v1", "providerDoc": "https://fastrouter.ai/models", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "friendli", "providerName": "Friendli", "providerApi": "https://api.friendli.ai/serverless/v1", "providerDoc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "hpc-ai", "providerName": "HPC-AI", "providerApi": "https://api.hpc-ai.com/inference/v1", "providerDoc": "https://www.hpc-ai.com/doc/docs/quickstart/", "model": "zai-org/glm-5.1", "modelKey": "zai-org/glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-04-08", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "huggingface", "providerName": "Hugging Face", "providerApi": "https://router.huggingface.co/v1", "providerDoc": "https://huggingface.co/docs/inference-providers", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-03", "openWeights": true, "releaseDate": "2026-04-03" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "Z.ai: GLM 5.1", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "lilac", "providerName": "Lilac", "providerApi": "https://api.getlilac.com/v1", "providerDoc": "https://docs.getlilac.com/inference/models", "model": "zai-org/glm-5.1", "modelKey": "zai-org/glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "llmgateway", "providerName": "LLM Gateway", "providerApi": "https://api.llmgateway.io/v1", "providerDoc": "https://llmgateway.io/docs", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "merge-gateway", "providerName": "Merge Gateway", "providerDoc": "https://docs.merge.dev/merge-gateway", "model": "zai/glm-5.1", "modelKey": "zai/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/glm-5.1", "modelKey": "TEE/glm-5.1", "displayName": "GLM 5.1 TEE", "metadata": { "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5.1", "modelKey": "zai-org/glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "novita-ai", "providerName": "NovitaAI", "providerApi": "https://api.novita.ai/openai", "providerDoc": "https://novita.ai/docs/guides/introduction", "model": "zai-org/glm-5.1", "modelKey": "zai-org/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nvidia", "providerName": "Nvidia", "providerApi": "https://integrate.api.nvidia.com/v1", "providerDoc": "https://docs.api.nvidia.com/nim/", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "glm-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode", "providerName": "OpenCode Zen", "providerApi": "https://opencode.ai/zen/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "orcarouter", "providerName": "OrcaRouter", "providerApi": "https://api.orcarouter.ai/v1", "providerDoc": "https://docs.orcarouter.ai", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/glm-5.1", "modelKey": "route/glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "Pro/zai-org/GLM-5.1", "modelKey": "Pro/zai-org/GLM-5.1", "displayName": "Pro/zai-org/GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-08", "openWeights": true, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "zai-org/GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-08", "openWeights": true, "releaseDate": "2026-04-08" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "synthetic", "providerName": "Synthetic", "providerApi": "https://api.synthetic.new/openai/v1", "providerDoc": "https://synthetic.new/pricing", "model": "hf:zai-org/GLM-5.1", "modelKey": "hf:zai-org/GLM-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-12", "openWeights": true, "releaseDate": "2026-03-27" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "togetherai", "providerName": "Together AI", "providerDoc": "https://docs.together.ai/docs/serverless-models", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-11", "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-5.1", "modelKey": "zai/glm-5.1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": false, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wafer.ai", "providerName": "Wafer", "providerApi": "https://pass.wafer.ai/v1", "providerDoc": "https://docs.wafer.ai/wafer-pass", "model": "GLM-5.1", "modelKey": "GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-01", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "wandb", "providerName": "Weights & Biases", "providerApi": "https://api.inference.wandb.ai/v1", "providerDoc": "https://docs.wandb.ai/guides/integrations/inference/", "model": "zai-org/GLM-5.1", "modelKey": "zai-org/GLM-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": false, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-5.1", "modelKey": "z-ai/glm-5.1", "displayName": "GLM-5.1", "metadata": { "lastUpdated": "2026-04-03", "openWeights": false, "releaseDate": "2026-04-03", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": false, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5.1", "modelKey": "glm-5.1", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": false, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-5.1", "displayName": "Z.ai: GLM 5.1", "metadata": { "canonicalSlug": "z-ai/glm-5.1-20260406", "createdAt": "2026-04-07T16:07:05.000Z", "huggingFaceId": "zai-org/GLM-5.1", "links": { "details": "/api/v1/models/z-ai/glm-5.1-20260406/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 202752, "max_completion_tokens": null, "is_moderated": false } } } ] }, { "id": "z-ai/glm-5.1-6bit", "provider": "z-ai", "model": "glm-5.1-6bit", "displayName": "GLM 5.1 6bit", "family": "glm", "sources": [ "models.dev" ], "providers": [ "routing-run" ], "aliases": [ "routing-run/route/glm-5.1-6bit" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "routing-run", "model": "route/glm-5.1-6bit", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1, "output": 3 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 6bit" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "routing-run", "providerName": "routing.run", "providerApi": "https://ai.routing.sh/v1", "providerDoc": "https://docs.routing.run/api-reference/models", "model": "route/glm-5.1-6bit", "modelKey": "route/glm-5.1-6bit", "displayName": "GLM 5.1 6bit", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } } ] }, { "id": "z-ai/glm-5.1-fast", "provider": "z-ai", "model": "glm-5.1-fast", "displayName": "GLM 5.1 Fast", "family": "glm", "sources": [ "models.dev" ], "providers": [ "neuralwatt" ], "aliases": [ "neuralwatt/glm-5.1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202736, "outputTokens": 202736, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "neuralwatt", "model": "glm-5.1-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.6 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 Fast" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "glm-5.1-fast", "modelKey": "glm-5.1-fast", "displayName": "GLM 5.1 Fast", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } } ] }, { "id": "z-ai/glm-5.1-fp8", "provider": "z-ai", "model": "glm-5.1-fp8", "displayName": "GLM 5.1", "family": "glm", "sources": [ "models.dev" ], "providers": [ "ambient", "gmicloud", "inceptron", "nearai", "neuralwatt", "vultr" ], "aliases": [ "ambient/zai-org/GLM-5.1-FP8", "gmicloud/zai-org/GLM-5.1-FP8", "inceptron/zai-org/GLM-5.1-FP8", "nearai/zai-org/GLM-5.1-FP8", "neuralwatt/zai-org/GLM-5.1-FP8", "vultr/zai-org/GLM-5.1-FP8" ], "mergedProviderModelRecords": 6, "limits": { "contextTokens": 202752, "outputTokens": 202752, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "ambient", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "gmicloud", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.182, "input": 0.98, "output": 3.08 } }, { "source": "models.dev", "provider": "inceptron", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "nearai", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 3.3 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.1, "output": 3.6 } }, { "source": "models.dev", "provider": "vultr", "model": "zai-org/GLM-5.1-FP8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.85, "output": 3.1 } } ] }, "metadata": { "displayNames": [ "GLM 5.1", "GLM 5.1 FP8", "GLM-5.1", "GLM-5.1 FP8" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 6 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ambient", "providerName": "Ambient", "providerApi": "https://api.ambient.xyz/v1", "providerDoc": "https://ambient.xyz", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "gmicloud", "providerName": "GMI Cloud", "providerApi": "https://api.gmi-serving.com/v1", "providerDoc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "inceptron", "providerName": "Inceptron", "providerApi": "https://api.inceptron.io/v1", "providerDoc": "https://docs.inceptron.io", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nearai", "providerName": "NEAR AI Cloud", "providerApi": "https://cloud-api.near.ai/v1", "providerDoc": "https://docs.near.ai/", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM-5.1 FP8", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM 5.1 FP8", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vultr", "providerName": "Vultr", "providerApi": "https://api.vultrinference.com/v1", "providerDoc": "https://api.vultrinference.com/", "model": "zai-org/GLM-5.1-FP8", "modelKey": "zai-org/GLM-5.1-FP8", "displayName": "GLM-5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07" } } ] }, { "id": "z-ai/glm-5.1-tee", "provider": "z-ai", "model": "glm-5.1-tee", "displayName": "GLM 5.1 TEE", "family": "glm", "sources": [ "models.dev" ], "providers": [ "chutes" ], "aliases": [ "chutes/zai-org/GLM-5.1-TEE" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "chutes", "model": "zai-org/GLM-5.1-TEE", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.525, "input": 1.05, "output": 3.5 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 TEE" ], "families": [ "glm" ], "releaseDate": "2026-04-07", "lastUpdated": "2026-04-07", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "chutes", "providerName": "Chutes", "providerApi": "https://llm.chutes.ai/v1", "providerDoc": "https://llm.chutes.ai/v1/models", "model": "zai-org/GLM-5.1-TEE", "modelKey": "zai-org/GLM-5.1-TEE", "displayName": "GLM 5.1 TEE", "family": "glm", "metadata": { "lastUpdated": "2026-04-07", "openWeights": true, "releaseDate": "2026-04-07", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-5.1-thinking", "provider": "z-ai", "model": "glm-5.1-thinking", "displayName": "GLM 5.1 Thinking TEE", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/TEE/glm-5.1-thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202752, "inputTokens": 202752, "outputTokens": 65535, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "TEE/glm-5.1-thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 5.25 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 Thinking TEE" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "TEE/glm-5.1-thinking", "modelKey": "TEE/glm-5.1-thinking", "displayName": "GLM 5.1 Thinking TEE", "metadata": { "lastUpdated": "2026-04-20", "openWeights": false, "releaseDate": "2026-04-20" } } ] }, { "id": "z-ai/glm-5.1:thinking", "provider": "z-ai", "model": "glm-5.1:thinking", "displayName": "GLM 5.1 Thinking", "family": "glm", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-5.1:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-5.1:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.3, "output": 2.55 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 Thinking" ], "families": [ "glm" ], "releaseDate": "2026-03-27", "lastUpdated": "2026-03-27", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-5.1:thinking", "modelKey": "zai-org/glm-5.1:thinking", "displayName": "GLM 5.1 Thinking", "family": "glm", "metadata": { "lastUpdated": "2026-03-27", "openWeights": true, "releaseDate": "2026-03-27" } } ] }, { "id": "z-ai/glm-5.2", "provider": "z-ai", "model": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "sources": [ "models.dev", "openrouter" ], "providers": [ "alibaba-token-plan", "alibaba-token-plan-cn", "baseten", "cloudflare-workers-ai", "cortecs", "crof", "neuralwatt", "ollama-cloud", "opencode-go", "openrouter", "siliconflow", "siliconflow-cn", "vercel", "zai-coding-plan", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "alibaba-token-plan-cn/glm-5.2", "alibaba-token-plan/glm-5.2", "baseten/zai-org/GLM-5.2", "cloudflare-workers-ai/@cf/zai-org/glm-5.2", "cortecs/glm-5.2", "crof/glm-5.2", "neuralwatt/glm-5.2", "ollama-cloud/glm-5.2", "opencode-go/glm-5.2", "openrouter/z-ai/glm-5.2", "siliconflow-cn/zai-org/GLM-5.2", "siliconflow/zai-org/GLM-5.2", "vercel/zai/glm-5.2", "zai-coding-plan/glm-5.2", "zhipuai-coding-plan/glm-5.2", "zhipuai/glm-5.2" ], "mergedProviderModelRecords": 16, "limits": { "contextTokens": 1048576, "outputTokens": 1048560, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true, "parallelFunctionCalling": false, "responseSchema": true, "toolChoice": true, "webSearch": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "alibaba-token-plan-cn", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "alibaba-token-plan", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "baseten", "model": "zai-org/GLM-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 4.5 } }, { "source": "models.dev", "provider": "cloudflare-workers-ai", "model": "@cf/zai-org/glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.39, "input": 1.44, "output": 4.53 } }, { "source": "models.dev", "provider": "crof", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.5, "output": 2.2 } }, { "source": "models.dev", "provider": "neuralwatt", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.45, "output": 4.5 } }, { "source": "models.dev", "provider": "opencode-go", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "openrouter", "model": "z-ai/glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1.2, "output": 4.1 } }, { "source": "models.dev", "provider": "siliconflow-cn", "model": "zai-org/GLM-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.3, "input": 1.5, "output": 4.5 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-5.2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "cacheWrite": 0, "input": 1.4, "output": 4.4 } }, { "source": "openrouter", "provider": "openrouter", "model": "z-ai/glm-5.2", "sourceUrl": "https://openrouter.ai/api/v1/models", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.2, "input": 1.2, "output": 4.1 } } ] }, "metadata": { "displayNames": [ "GLM 5.2", "GLM-5.2", "Glm 5.2", "Z.ai: GLM 5.2" ], "families": [ "glm" ], "releaseDate": "2026-06-13", "lastUpdated": "2026-06-13", "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "providerModelRecordCount": 16 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan-cn", "providerName": "Alibaba Token Plan (China)", "providerApi": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "alibaba-token-plan", "providerName": "Alibaba Token Plan", "providerApi": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "providerDoc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "baseten", "providerName": "Baseten", "providerApi": "https://inference.baseten.co/v1", "providerDoc": "https://docs.baseten.co/inference/model-apis/overview", "model": "zai-org/GLM-5.2", "modelKey": "zai-org/GLM-5.2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cloudflare-workers-ai", "providerName": "Cloudflare Workers AI", "providerApi": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "providerDoc": "https://developers.cloudflare.com/workers-ai/models/", "model": "@cf/zai-org/glm-5.2", "modelKey": "@cf/zai-org/glm-5.2", "displayName": "Glm 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "crof", "providerName": "CrofAI", "providerApi": "https://crof.ai/v1", "providerDoc": "https://crof.ai/docs", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "medium", "high" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "neuralwatt", "providerName": "Neuralwatt", "providerApi": "https://api.neuralwatt.com/v1", "providerDoc": "https://portal.neuralwatt.com/docs", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-17", "openWeights": true, "releaseDate": "2026-06-17", "reasoningOptions": [ { "type": "effort", "values": [ "minimal", "low", "medium", "high", "xhigh" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "ollama-cloud", "providerName": "Ollama Cloud", "providerApi": "https://ollama.com/v1", "providerDoc": "https://docs.ollama.com/cloud", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "opencode-go", "providerName": "OpenCode Go", "providerApi": "https://opencode.ai/zen/go/v1", "providerDoc": "https://opencode.ai/docs/zen", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "openrouter", "providerName": "OpenRouter", "providerApi": "https://openrouter.ai/api/v1", "providerDoc": "https://openrouter.ai/models", "model": "z-ai/glm-5.2", "modelKey": "z-ai/glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow-cn", "providerName": "SiliconFlow (China)", "providerApi": "https://api.siliconflow.cn/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-5.2", "modelKey": "zai-org/GLM-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-5.2", "modelKey": "zai-org/GLM-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-5.2", "modelKey": "zai/glm-5.2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-16" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": true, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5.2", "modelKey": "glm-5.2", "displayName": "GLM-5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-13", "openWeights": false, "releaseDate": "2026-06-13", "reasoningOptions": [ { "type": "effort", "values": [ "high", "max" ] } ] } }, { "source": "openrouter", "sourceUrl": "https://openrouter.ai/api/v1/models", "provider": "openrouter", "model": "z-ai/glm-5.2", "displayName": "Z.ai: GLM 5.2", "metadata": { "canonicalSlug": "z-ai/glm-5.2-20260616", "createdAt": "2026-06-16T17:45:30.000Z", "huggingFaceId": "zai-org/GLM-5.2", "links": { "details": "/api/v1/models/z-ai/glm-5.2-20260616/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, "supported_efforts": [ "xhigh", "high" ], "default_effort": "high" }, "supportedParameters": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "tokenizer": "Other", "topProvider": { "context_length": 1048576, "max_completion_tokens": 131072, "is_moderated": false } } } ] }, { "id": "z-ai/glm-5p1", "provider": "z-ai", "model": "glm-5p1", "displayName": "GLM 5.1", "family": "glm", "mode": "chat", "sources": [ "litellm", "models.dev" ], "providers": [ "fireworks-ai", "fireworks_ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/glm-5p1", "fireworks_ai/accounts/fireworks/models/glm-5p1", "fireworks_ai/glm-5p1" ], "mergedProviderModelRecords": 3, "limits": { "contextTokens": 202800, "inputTokens": 202800, "maxTokens": 202800, "outputTokens": 202800, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false, "embedding": false, "functionCalling": false, "imageGeneration": false, "moderation": false, "rerank": false, "responseSchema": false, "speech": false, "toolChoice": false, "transcription": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/glm-5p1", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-5p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } }, { "source": "litellm", "provider": "fireworks_ai", "model": "fireworks_ai/glm-5p1", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "sourceUnit": "usd_per_token_for_token_fields", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "GLM 5.1" ], "families": [ "glm" ], "modes": [ "chat" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "providerModelRecordCount": 3 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/glm-5p1", "modelKey": "accounts/fireworks/models/glm-5p1", "displayName": "GLM 5.1", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/accounts/fireworks/models/glm-5p1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/glm-5p1" } }, { "source": "litellm", "sourceUrl": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "provider": "fireworks_ai", "model": "fireworks_ai/glm-5p1", "mode": "chat", "metadata": { "source": "https://fireworks.ai/models/fireworks/glm-5p1" } } ] }, { "id": "z-ai/glm-5p1-fast", "provider": "z-ai", "model": "glm-5p1-fast", "displayName": "GLM 5.1 Fast", "family": "glm", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/routers/glm-5p1-fast" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/routers/glm-5p1-fast", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.52, "input": 2.8, "output": 8.8 } } ] }, "metadata": { "displayNames": [ "GLM 5.1 Fast" ], "families": [ "glm" ], "releaseDate": "2026-04-01", "lastUpdated": "2026-04-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/routers/glm-5p1-fast", "modelKey": "accounts/fireworks/routers/glm-5p1-fast", "displayName": "GLM 5.1 Fast", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": true, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-5p2", "provider": "z-ai", "model": "glm-5p2", "displayName": "GLM 5.2", "family": "glm", "sources": [ "models.dev" ], "providers": [ "fireworks-ai" ], "aliases": [ "fireworks-ai/accounts/fireworks/models/glm-5p2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "fireworks-ai", "model": "accounts/fireworks/models/glm-5p2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.26, "input": 1.4, "output": 4.4 } } ] }, "metadata": { "displayNames": [ "GLM 5.2" ], "families": [ "glm" ], "releaseDate": "2026-06-16", "lastUpdated": "2026-06-16", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "fireworks-ai", "providerName": "Fireworks AI", "providerApi": "https://api.fireworks.ai/inference/v1/", "providerDoc": "https://fireworks.ai/docs/", "model": "accounts/fireworks/models/glm-5p2", "modelKey": "accounts/fireworks/models/glm-5p2", "displayName": "GLM 5.2", "family": "glm", "metadata": { "lastUpdated": "2026-06-16", "openWeights": true, "releaseDate": "2026-06-16", "reasoningOptions": [ { "type": "toggle" }, { "type": "effort", "values": [ "high", "max" ] } ] } } ] }, { "id": "z-ai/glm-5v-turbo", "provider": "z-ai", "model": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "sources": [ "models.dev" ], "providers": [ "302ai", "aihubmix", "cortecs", "kilo", "nano-gpt", "siliconflow", "vercel", "zai", "zai-coding-plan", "zenmux", "zhipuai", "zhipuai-coding-plan" ], "aliases": [ "302ai/glm-5v-turbo", "aihubmix/glm-5v-turbo", "cortecs/glm-5v-turbo", "kilo/z-ai/glm-5v-turbo", "nano-gpt/z-ai/glm-5v-turbo", "siliconflow/zai-org/GLM-5V-Turbo", "vercel/zai/glm-5v-turbo", "zai-coding-plan/glm-5v-turbo", "zai/glm-5v-turbo", "zenmux/z-ai/glm-5v-turbo", "zhipuai-coding-plan/glm-5v-turbo", "zhipuai/glm-5v-turbo" ], "mergedProviderModelRecords": 12, "limits": { "contextTokens": 202800, "inputTokens": 202800, "outputTokens": 131100, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false, "structuredOutput": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.72, "output": 3.2 } }, { "source": "models.dev", "provider": "aihubmix", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.169008, "input": 0.7042, "output": 3.09848 } }, { "source": "models.dev", "provider": "cortecs", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.308, "cacheWrite": 1.544, "input": 1.235, "output": 4.118 } }, { "source": "models.dev", "provider": "kilo", "model": "z-ai/glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "siliconflow", "model": "zai-org/GLM-5V-Turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheWrite": 0, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "vercel", "model": "zai/glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "zai-coding-plan", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zai", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "cacheWrite": 0, "input": 1.2, "output": 4 } }, { "source": "models.dev", "provider": "zenmux", "model": "z-ai/glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.1743, "input": 0.726, "output": 3.1946 } }, { "source": "models.dev", "provider": "zhipuai-coding-plan", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0, "cacheWrite": 0, "input": 0, "output": 0 } }, { "source": "models.dev", "provider": "zhipuai", "model": "glm-5v-turbo", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 1.2, "cacheWrite": 0, "input": 5, "output": 22 } } ] }, "metadata": { "displayNames": [ "GLM 5 Vision Turbo", "GLM 5V Turbo", "GLM-5V-Turbo", "Z.ai: GLM 5V Turbo", "zai-org/GLM-5V-Turbo" ], "families": [ "glm", "glmv" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 12 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "aihubmix", "providerName": "AIHubMix", "providerDoc": "https://docs.aihubmix.com", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM 5 Vision Turbo", "family": "glmv", "metadata": { "lastUpdated": "2026-05-09", "openWeights": false, "releaseDate": "2026-05-09" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "cortecs", "providerName": "Cortecs", "providerApi": "https://api.cortecs.ai/v1", "providerDoc": "https://api.cortecs.ai/v1/models", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "kilo", "providerName": "Kilo Gateway", "providerApi": "https://api.kilo.ai/api/gateway", "providerDoc": "https://kilo.ai", "model": "z-ai/glm-5v-turbo", "modelKey": "z-ai/glm-5v-turbo", "displayName": "Z.ai: GLM 5V Turbo", "metadata": { "lastUpdated": "2026-04-11", "openWeights": true, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-5v-turbo", "modelKey": "z-ai/glm-5v-turbo", "displayName": "GLM 5V Turbo", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "siliconflow", "providerName": "SiliconFlow", "providerApi": "https://api.siliconflow.com/v1", "providerDoc": "https://cloud.siliconflow.com/models", "model": "zai-org/GLM-5V-Turbo", "modelKey": "zai-org/GLM-5V-Turbo", "displayName": "zai-org/GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "vercel", "providerName": "Vercel AI Gateway", "providerDoc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "model": "zai/glm-5v-turbo", "modelKey": "zai/glm-5v-turbo", "displayName": "GLM 5V Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai-coding-plan", "providerName": "Z.AI Coding Plan", "providerApi": "https://api.z.ai/api/coding/paas/v4", "providerDoc": "https://docs.z.ai/devpack/overview", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zai", "providerName": "Z.AI", "providerApi": "https://api.z.ai/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "z-ai/glm-5v-turbo", "modelKey": "z-ai/glm-5v-turbo", "displayName": "GLM 5V Turbo", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01" } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai-coding-plan", "providerName": "Zhipu AI Coding Plan", "providerApi": "https://open.bigmodel.cn/api/coding/paas/v4", "providerDoc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } }, { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zhipuai", "providerName": "Zhipu AI", "providerApi": "https://open.bigmodel.cn/api/paas/v4", "providerDoc": "https://docs.z.ai/guides/overview/pricing", "model": "glm-5v-turbo", "modelKey": "glm-5v-turbo", "displayName": "GLM-5V-Turbo", "family": "glm", "metadata": { "lastUpdated": "2026-04-01", "openWeights": false, "releaseDate": "2026-04-01", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "z-ai/glm-5v-turbo:thinking", "provider": "z-ai", "model": "glm-5v-turbo:thinking", "displayName": "GLM 5V Turbo Thinking", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/z-ai/glm-5v-turbo:thinking" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 202800, "inputTokens": 202800, "outputTokens": 131100, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "z-ai/glm-5v-turbo:thinking", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.24, "input": 1.2, "output": 4 } } ] }, "metadata": { "displayNames": [ "GLM 5V Turbo Thinking" ], "releaseDate": "2026-04-02", "lastUpdated": "2026-04-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "z-ai/glm-5v-turbo:thinking", "modelKey": "z-ai/glm-5v-turbo:thinking", "displayName": "GLM 5V Turbo Thinking", "metadata": { "lastUpdated": "2026-04-02", "openWeights": false, "releaseDate": "2026-04-02" } } ] }, { "id": "z-ai/glm-for-coding", "provider": "z-ai", "model": "glm-for-coding", "displayName": "glm-for-coding", "family": "glm", "sources": [ "models.dev" ], "providers": [ "302ai" ], "aliases": [ "302ai/glm-for-coding" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "302ai", "model": "glm-for-coding", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.086, "output": 0.343 } } ] }, "metadata": { "displayNames": [ "glm-for-coding" ], "families": [ "glm" ], "releaseDate": "2025-09-30", "lastUpdated": "2025-09-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "302ai", "providerName": "302.AI", "providerApi": "https://api.302.ai/v1", "providerDoc": "https://doc.302.ai", "model": "glm-for-coding", "modelKey": "glm-for-coding", "displayName": "glm-for-coding", "family": "glm", "metadata": { "lastUpdated": "2025-09-30", "openWeights": false, "releaseDate": "2025-09-30" } } ] }, { "id": "z-ai/glm-latest", "provider": "z-ai", "model": "glm-latest", "displayName": "GLM Latest", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/zai-org/glm-latest" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 200000, "inputTokens": 200000, "outputTokens": 131072, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "zai-org/glm-latest", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.15, "input": 0.75, "output": 2.6 } } ] }, "metadata": { "displayNames": [ "GLM Latest" ], "releaseDate": "2026-05-03", "lastUpdated": "2026-05-03", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "zai-org/glm-latest", "modelKey": "zai-org/glm-latest", "displayName": "GLM Latest", "metadata": { "lastUpdated": "2026-05-03", "openWeights": false, "releaseDate": "2026-05-03" } } ] }, { "id": "z-ai/glm-z1-32b-0414", "provider": "z-ai", "model": "glm-z1-32b-0414", "displayName": "GLM Z1 32B 0414", "family": "glm-z", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/THUDM/GLM-Z1-32B-0414" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "inputTokens": 128000, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "THUDM/GLM-Z1-32B-0414", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "GLM Z1 32B 0414" ], "families": [ "glm-z" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "THUDM/GLM-Z1-32B-0414", "modelKey": "THUDM/GLM-Z1-32B-0414", "displayName": "GLM Z1 32B 0414", "family": "glm-z", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "z-ai/glm-z1-9b-0414", "provider": "z-ai", "model": "glm-z1-9b-0414", "displayName": "GLM Z1 9B 0414", "family": "glm-z", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/THUDM/GLM-Z1-9B-0414" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 8000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "THUDM/GLM-Z1-9B-0414", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 0.2 } } ] }, "metadata": { "displayNames": [ "GLM Z1 9B 0414" ], "families": [ "glm-z" ], "releaseDate": "2025-04-14", "lastUpdated": "2025-04-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "THUDM/GLM-Z1-9B-0414", "modelKey": "THUDM/GLM-Z1-9B-0414", "displayName": "GLM Z1 9B 0414", "family": "glm-z", "metadata": { "lastUpdated": "2025-04-14", "openWeights": false, "releaseDate": "2025-04-14" } } ] }, { "id": "z-ai/glm-z1-air", "provider": "z-ai", "model": "glm-z1-air", "displayName": "GLM Z1 Air", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-z1-air" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-z1-air", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.07, "output": 0.07 } } ] }, "metadata": { "displayNames": [ "GLM Z1 Air" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-z1-air", "modelKey": "glm-z1-air", "displayName": "GLM Z1 Air", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "z-ai/glm-z1-airx", "provider": "z-ai", "model": "glm-z1-airx", "displayName": "GLM Z1 AirX", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-z1-airx" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 32000, "inputTokens": 32000, "outputTokens": 16384, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-z1-airx", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.7, "output": 0.7 } } ] }, "metadata": { "displayNames": [ "GLM Z1 AirX" ], "releaseDate": "2025-04-15", "lastUpdated": "2025-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-z1-airx", "modelKey": "glm-z1-airx", "displayName": "GLM Z1 AirX", "metadata": { "lastUpdated": "2025-04-15", "openWeights": false, "releaseDate": "2025-04-15" } } ] }, { "id": "z-ai/glm-zero-preview", "provider": "z-ai", "model": "glm-zero-preview", "displayName": "GLM Zero Preview", "sources": [ "models.dev" ], "providers": [ "nano-gpt" ], "aliases": [ "nano-gpt/glm-zero-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 8000, "inputTokens": 8000, "outputTokens": 4096, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "structuredOutput": false, "toolCalling": false, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "nano-gpt", "model": "glm-zero-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 1.802, "output": 1.802 } } ] }, "metadata": { "displayNames": [ "GLM Zero Preview" ], "releaseDate": "2024-12-01", "lastUpdated": "2024-12-01", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "nano-gpt", "providerName": "NanoGPT", "providerApi": "https://nano-gpt.com/api/v1", "providerDoc": "https://docs.nano-gpt.com", "model": "glm-zero-preview", "modelKey": "glm-zero-preview", "displayName": "GLM Zero Preview", "metadata": { "lastUpdated": "2024-12-01", "openWeights": false, "releaseDate": "2024-12-01" } } ] }, { "id": "zeldoc/z-code", "provider": "zeldoc", "model": "z-code", "displayName": "Z-Code", "sources": [ "models.dev" ], "providers": [ "zeldoc" ], "aliases": [ "zeldoc/z-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 262144, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "structuredOutput": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zeldoc", "model": "z-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Z-Code" ], "knowledgeCutoff": "2025-01", "releaseDate": "2026-04-15", "lastUpdated": "2026-04-15", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zeldoc", "providerName": "Zeldoc", "providerApi": "https://api.zeldoc.ai/v1", "providerDoc": "https://docs.zeldoc.ai", "model": "z-code", "modelKey": "z-code", "displayName": "Z-Code", "metadata": { "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-15", "openWeights": false, "releaseDate": "2026-04-15", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/agnes-1.5-lite", "provider": "zenmux", "model": "agnes-1.5-lite", "displayName": "Agnes 1.5 Lite", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/sapiens-ai/agnes-1.5-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "sapiens-ai/agnes-1.5-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.12, "output": 0.6 } } ] }, "metadata": { "displayNames": [ "Agnes 1.5 Lite" ], "releaseDate": "2026-03-26", "lastUpdated": "2026-03-26", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "sapiens-ai/agnes-1.5-lite", "modelKey": "sapiens-ai/agnes-1.5-lite", "displayName": "Agnes 1.5 Lite", "metadata": { "lastUpdated": "2026-03-26", "openWeights": false, "releaseDate": "2026-03-26" } } ] }, { "id": "zenmux/agnes-1.5-pro", "provider": "zenmux", "model": "agnes-1.5-pro", "displayName": "Agnes 1.5 Pro", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/sapiens-ai/agnes-1.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "sapiens-ai/agnes-1.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.16, "output": 0.8 } } ] }, "metadata": { "displayNames": [ "Agnes 1.5 Pro" ], "releaseDate": "2026-03-21", "lastUpdated": "2026-03-21", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "sapiens-ai/agnes-1.5-pro", "modelKey": "sapiens-ai/agnes-1.5-pro", "displayName": "Agnes 1.5 Pro", "metadata": { "lastUpdated": "2026-03-21", "openWeights": false, "releaseDate": "2026-03-21" } } ] }, { "id": "zenmux/doubao-seed-1.8", "provider": "zenmux", "model": "doubao-seed-1.8", "displayName": "Doubao-Seed-1.8", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-1.8" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-1.8", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.0024, "input": 0.11, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Doubao-Seed-1.8" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-12-18", "lastUpdated": "2025-12-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-1.8", "modelKey": "volcengine/doubao-seed-1.8", "displayName": "Doubao-Seed-1.8", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-18", "openWeights": false, "releaseDate": "2025-12-18", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/doubao-seed-2.0-code", "provider": "zenmux", "model": "doubao-seed-2.0-code", "displayName": "Doubao Seed 2.0 Code", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-2.0-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 32000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-2.0-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.9, "output": 4.48 } } ] }, "metadata": { "displayNames": [ "Doubao Seed 2.0 Code" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-03-20", "lastUpdated": "2026-03-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-2.0-code", "modelKey": "volcengine/doubao-seed-2.0-code", "displayName": "Doubao Seed 2.0 Code", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "openWeights": false, "releaseDate": "2026-03-20" } } ] }, { "id": "zenmux/doubao-seed-2.0-lite", "provider": "zenmux", "model": "doubao-seed-2.0-lite", "displayName": "Doubao-Seed-2.0-lite", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-2.0-lite" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-2.0-lite", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.02, "cacheWrite": 0.0024, "input": 0.09, "output": 0.51 } } ] }, "metadata": { "displayNames": [ "Doubao-Seed-2.0-lite" ], "knowledgeCutoff": "2026-02-14", "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-2.0-lite", "modelKey": "volcengine/doubao-seed-2.0-lite", "displayName": "Doubao-Seed-2.0-lite", "metadata": { "knowledgeCutoff": "2026-02-14", "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/doubao-seed-2.0-mini", "provider": "zenmux", "model": "doubao-seed-2.0-mini", "displayName": "Doubao-Seed-2.0-mini", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-2.0-mini" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-2.0-mini", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "cacheWrite": 0.0024, "input": 0.03, "output": 0.28 } } ] }, "metadata": { "displayNames": [ "Doubao-Seed-2.0-mini" ], "knowledgeCutoff": "2026-02-14", "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-2.0-mini", "modelKey": "volcengine/doubao-seed-2.0-mini", "displayName": "Doubao-Seed-2.0-mini", "metadata": { "knowledgeCutoff": "2026-02-14", "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/doubao-seed-2.0-pro", "provider": "zenmux", "model": "doubao-seed-2.0-pro", "displayName": "Doubao-Seed-2.0-pro", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-2.0-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-2.0-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.09, "cacheWrite": 0.0024, "input": 0.45, "output": 2.24 } } ] }, "metadata": { "displayNames": [ "Doubao-Seed-2.0-pro" ], "knowledgeCutoff": "2026-02-14", "releaseDate": "2026-02-14", "lastUpdated": "2026-02-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-2.0-pro", "modelKey": "volcengine/doubao-seed-2.0-pro", "displayName": "Doubao-Seed-2.0-pro", "metadata": { "knowledgeCutoff": "2026-02-14", "lastUpdated": "2026-02-14", "openWeights": false, "releaseDate": "2026-02-14", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/doubao-seed-code", "provider": "zenmux", "model": "doubao-seed-code", "displayName": "Doubao-Seed-Code", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/volcengine/doubao-seed-code" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "volcengine/doubao-seed-code", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.03, "input": 0.17, "output": 1.12 } } ] }, "metadata": { "displayNames": [ "Doubao-Seed-Code" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-11-11", "lastUpdated": "2025-11-11", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "volcengine/doubao-seed-code", "modelKey": "volcengine/doubao-seed-code", "displayName": "Doubao-Seed-Code", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-11", "openWeights": false, "releaseDate": "2025-11-11", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/ernie-5.0-thinking-preview", "provider": "zenmux", "model": "ernie-5.0-thinking-preview", "displayName": "ERNIE 5.0", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/baidu/ernie-5.0-thinking-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "baidu/ernie-5.0-thinking-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.84, "output": 3.37 } } ] }, "metadata": { "displayNames": [ "ERNIE 5.0" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-01-22", "lastUpdated": "2026-01-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "baidu/ernie-5.0-thinking-preview", "modelKey": "baidu/ernie-5.0-thinking-preview", "displayName": "ERNIE 5.0", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-22", "openWeights": false, "releaseDate": "2026-01-22" } } ] }, { "id": "zenmux/hy3-preview", "provider": "zenmux", "model": "hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/tencent/hy3-preview" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "tencent/hy3-preview", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.058, "cacheWrite": 0, "input": 0.172, "output": 0.572 } } ] }, "metadata": { "displayNames": [ "Hy3 preview" ], "families": [ "Hy" ], "releaseDate": "2026-04-20", "lastUpdated": "2026-04-20", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "tencent/hy3-preview", "modelKey": "tencent/hy3-preview", "displayName": "Hy3 preview", "family": "Hy", "metadata": { "lastUpdated": "2026-04-20", "openWeights": true, "releaseDate": "2026-04-20", "reasoningOptions": [ { "type": "effort", "values": [ "none", "low", "high" ] } ] } } ] }, { "id": "zenmux/kat-coder-pro-v2", "provider": "zenmux", "model": "kat-coder-pro-v2", "displayName": "KAT-Coder-Pro-V2", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/kuaishou/kat-coder-pro-v2" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 80000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "kuaishou/kat-coder-pro-v2", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 1.2 } } ] }, "metadata": { "displayNames": [ "KAT-Coder-Pro-V2" ], "releaseDate": "2026-03-30", "lastUpdated": "2026-03-30", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "kuaishou/kat-coder-pro-v2", "modelKey": "kuaishou/kat-coder-pro-v2", "displayName": "KAT-Coder-Pro-V2", "metadata": { "lastUpdated": "2026-03-30", "openWeights": false, "releaseDate": "2026-03-30" } } ] }, { "id": "zenmux/ling-1t", "provider": "zenmux", "model": "ling-1t", "displayName": "Ling-1T", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/inclusionai/ling-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "inclusionai/ling-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.56, "output": 2.24 } } ] }, "metadata": { "displayNames": [ "Ling-1T" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-10-09", "lastUpdated": "2025-10-09", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "inclusionai/ling-1t", "modelKey": "inclusionai/ling-1t", "displayName": "Ling-1T", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-10-09", "openWeights": false, "releaseDate": "2025-10-09" } } ] }, { "id": "zenmux/mimo-v2-flash", "provider": "zenmux", "model": "mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/xiaomi/mimo-v2-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262144, "outputTokens": 65536, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "xiaomi/mimo-v2-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.01, "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "MiMo-V2-Flash" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12-01", "releaseDate": "2025-12-16", "lastUpdated": "2026-02-04", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "xiaomi/mimo-v2-flash", "modelKey": "xiaomi/mimo-v2-flash", "displayName": "MiMo-V2-Flash", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "openWeights": true, "releaseDate": "2025-12-16", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/mimo-v2-omni", "provider": "zenmux", "model": "mimo-v2-omni", "displayName": "MiMo V2 Omni", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/xiaomi/mimo-v2-omni" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 265000, "outputTokens": 265000, "supports1MContext": false }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": true, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "xiaomi/mimo-v2-omni", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 } } ] }, "metadata": { "displayNames": [ "MiMo V2 Omni" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "xiaomi/mimo-v2-omni", "modelKey": "xiaomi/mimo-v2-omni", "displayName": "MiMo V2 Omni", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/mimo-v2-pro", "provider": "zenmux", "model": "mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/xiaomi/mimo-v2-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1000000, "outputTokens": 256000, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "xiaomi/mimo-v2-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo V2 Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-03-18", "lastUpdated": "2026-03-18", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "xiaomi/mimo-v2-pro", "modelKey": "xiaomi/mimo-v2-pro", "displayName": "MiMo V2 Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "openWeights": false, "releaseDate": "2026-03-18", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/mimo-v2.5", "provider": "zenmux", "model": "mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/xiaomi/mimo-v2.5" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": true, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": true, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "xiaomi/mimo-v2.5", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.08, "input": 0.4, "output": 2 }, "tiered": { "contextOver200K": { "input": 0.8, "output": 4, "cache_read": 0.16 }, "tiers": [ { "input": 0.8, "output": 4, "cache_read": 0.16, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "xiaomi/mimo-v2.5", "modelKey": "xiaomi/mimo-v2.5", "displayName": "MiMo-V2.5", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/mimo-v2.5-pro", "provider": "zenmux", "model": "mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/xiaomi/mimo-v2.5-pro" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 1048576, "outputTokens": 131072, "supports1MContext": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": true }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "xiaomi/mimo-v2.5-pro", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.2, "input": 1, "output": 3 }, "tiered": { "contextOver200K": { "input": 2, "output": 6, "cache_read": 0.4 }, "tiers": [ { "input": 2, "output": 6, "cache_read": 0.4, "tier": { "size": 256000 } } ] } } ] }, "metadata": { "displayNames": [ "MiMo-V2.5-Pro" ], "families": [ "mimo" ], "knowledgeCutoff": "2024-12", "releaseDate": "2026-04-22", "lastUpdated": "2026-04-22", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "xiaomi/mimo-v2.5-pro", "modelKey": "xiaomi/mimo-v2.5-pro", "displayName": "MiMo-V2.5-Pro", "family": "mimo", "metadata": { "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "openWeights": true, "releaseDate": "2026-04-22", "reasoningOptions": [ { "type": "toggle" } ] } } ] }, { "id": "zenmux/ring-1t", "provider": "zenmux", "model": "ring-1t", "displayName": "Ring-1T", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/inclusionai/ring-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 128000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "inclusionai/ring-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.11, "input": 0.56, "output": 2.24 } } ] }, "metadata": { "displayNames": [ "Ring-1T" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-10-12", "lastUpdated": "2025-10-12", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "inclusionai/ring-1t", "modelKey": "inclusionai/ring-1t", "displayName": "Ring-1T", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-10-12", "openWeights": false, "releaseDate": "2025-10-12" } } ] }, { "id": "zenmux/ring-2.6-1t", "provider": "zenmux", "model": "ring-2.6-1t", "displayName": "inclusionAI: Ring-2.6-1T", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/inclusionai/ring-2.6-1t" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 262000, "outputTokens": 65000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "inclusionai/ring-2.6-1t", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "cacheRead": 0.06, "input": 0.3, "output": 2.5 } } ] }, "metadata": { "displayNames": [ "inclusionAI: Ring-2.6-1T" ], "knowledgeCutoff": "2025-12-31", "releaseDate": "2026-05-07", "lastUpdated": "2026-05-14", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "inclusionai/ring-2.6-1t", "modelKey": "inclusionai/ring-2.6-1t", "displayName": "inclusionAI: Ring-2.6-1T", "metadata": { "knowledgeCutoff": "2025-12-31", "lastUpdated": "2026-05-14", "openWeights": true, "releaseDate": "2026-05-07" } } ] }, { "id": "zenmux/step-3", "provider": "zenmux", "model": "step-3", "displayName": "Step-3", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/stepfun/step-3" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 65536, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "stepfun/step-3", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.21, "output": 0.57 } } ] }, "metadata": { "displayNames": [ "Step-3" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2025-07-31", "lastUpdated": "2025-07-31", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "stepfun/step-3", "modelKey": "stepfun/step-3", "displayName": "Step-3", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-31", "openWeights": false, "releaseDate": "2025-07-31" } } ] }, { "id": "zenmux/step-3.5-flash", "provider": "zenmux", "model": "step-3.5-flash", "displayName": "Step 3.5 Flash", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/stepfun/step-3.5-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "outputTokens": 64000, "supports1MContext": false }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachments": false, "audioInput": false, "audioOutput": false, "imageInput": false, "imageOutput": false, "openWeights": false, "pdfInput": false, "reasoning": false, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "stepfun/step-3.5-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.1, "output": 0.3 } } ] }, "metadata": { "displayNames": [ "Step 3.5 Flash" ], "knowledgeCutoff": "2025-01-01", "releaseDate": "2026-02-02", "lastUpdated": "2026-02-02", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "stepfun/step-3.5-flash", "modelKey": "stepfun/step-3.5-flash", "displayName": "Step 3.5 Flash", "metadata": { "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-02", "openWeights": false, "releaseDate": "2026-02-02" } } ] }, { "id": "zenmux/step-3.7-flash", "provider": "zenmux", "model": "step-3.7-flash", "displayName": "Step 3.7 Flash", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/stepfun/step-3.7-flash" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "stepfun/step-3.7-flash", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0.2, "output": 1.15 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash" ], "knowledgeCutoff": "2026-01-01", "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "stepfun/step-3.7-flash", "modelKey": "stepfun/step-3.7-flash", "displayName": "Step 3.7 Flash", "metadata": { "knowledgeCutoff": "2026-01-01", "lastUpdated": "2026-05-29", "openWeights": true, "releaseDate": "2026-05-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] }, { "id": "zenmux/step-3.7-flash-free", "provider": "zenmux", "model": "step-3.7-flash-free", "displayName": "Step 3.7 Flash (Free)", "sources": [ "models.dev" ], "providers": [ "zenmux" ], "aliases": [ "zenmux/stepfun/step-3.7-flash-free" ], "mergedProviderModelRecords": 1, "limits": { "contextTokens": 256000, "inputTokens": 256000, "outputTokens": 256000, "supports1MContext": false }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachments": true, "audioInput": false, "audioOutput": false, "imageInput": true, "imageOutput": false, "openWeights": true, "pdfInput": false, "reasoning": true, "temperature": true, "toolCalling": true, "videoInput": false, "supports1MContext": false }, "pricing": { "currency": "USD", "normalizedUnit": "per1MTokens values are USD per 1,000,000 tokens; non-token values keep the unit named by their object key.", "offers": [ { "source": "models.dev", "provider": "zenmux", "model": "stepfun/step-3.7-flash-free", "sourceUrl": "https://models.dev/api.json", "sourceUnit": "usd_per_1m_tokens", "per1MTokens": { "input": 0, "output": 0 } } ] }, "metadata": { "displayNames": [ "Step 3.7 Flash (Free)" ], "knowledgeCutoff": "2026-01-01", "releaseDate": "2026-05-29", "lastUpdated": "2026-05-29", "providerModelRecordCount": 1 }, "sourceRecords": [ { "source": "models.dev", "sourceUrl": "https://models.dev/api.json", "provider": "zenmux", "providerName": "ZenMux", "providerApi": "https://zenmux.ai/api/v1", "providerDoc": "https://docs.zenmux.ai", "model": "stepfun/step-3.7-flash-free", "modelKey": "stepfun/step-3.7-flash-free", "displayName": "Step 3.7 Flash (Free)", "metadata": { "knowledgeCutoff": "2026-01-01", "lastUpdated": "2026-05-29", "openWeights": true, "releaseDate": "2026-05-29", "reasoningOptions": [ { "type": "effort", "values": [ "low", "medium", "high" ] } ] } } ] } ] }